If there’s a single ‘universal’ business truth from the last three years, it’s that the Covid-19 pandemic has significantly impacted growth. In many sectors, that impact has been negative.

But that’s not the case for ecommerce.

Nationwide lockdowns had a big effect on the wider economy, with many businesses putting the brakes on planned investment, but with consumers stuck at home our online purchases skyrocketed:

Global ecommerce sales grew by an average of 20.33% year-on-year from 2014 to 2019, and by just 12.37% from 2018 to 2019. However, in 2020 online sales increased by 25.72% to $4.2 trillion.

Ecommerce sales increased by a further 22.66% in 2021, but the pace of growth slowed in 2022, rising by just 9.71%.

The sector is projected to grow by 10.37% this year, another modest increase compared to the boom of 2019-21, but ecommerce remains bullish despite the current economic landscape.

Of course, just because the sector is continuing to grow during tough times, that doesn’t mean your ecommerce business is seeing the same results.

With consumer spending power reduced by inflation and businesses being more cautious with where they invest their money, there’s a good chance that you’re seeing sales volume fall—despite what the macro statistics might be saying.

These five strategies can drive increased ecommerce revenue in 2024

The economy is in bad shape and the giants of ecommerce are piling on the pressure, but that doesn’t mean you can’t succeed in 2024 and beyond.

Last year, Brightpearl’s annual Lightning 50 table identified the UK and US’ fastest growing ecommerce retailers. In the UK, the top five were Pinter, Progress JJ, Passenger, Kick Game and Wild Cosmetics. These brands aren’t yet household names, but they’re making waves in a competitive ecommerce marketing landscape:

In order to emulate these ecommerce brands and grow your revenue next year, you need to be across the following five strategies—and challenge your marketing and customer service teams to build them into their planning.

1. Adopt a multi-channel approach

Research by the Harvard Business Review found that a massive 73% of shoppers will browse several channels before buying a product, which means you need to be maximising your visibility with an omnichannel approach.

Another interesting statistic to come out of the HBR study was that these multi-touch point customers were more valuable compared to single channel customers, spending on average 4% more on every shop in-store and 10% more online. The study also revealed the impact of pre-purchase research, with ‘deliberate searching’ leading to greater value purchases. Without an omnichannel presence, the only touch point you control during this research phase is your own website.

Further evidence of the benefits of an omnichannel strategy can be found in an SAP study in which companies reported increased sales, increased customer loyalty, a better competitive advantage and a better customer experience.

We’ll look at the threat the likes of Amazon pose to smaller and independent retailers later in this article, but sometimes if you can’t beat them, join them.

Amazon is the world’s largest marketplace, so like it or not, if you don’t have a presence there you’ll be missing out on a lot of product searches. In fact, 66% of consumers from the EU5 countries (UK, Germany, France, Italy and Spain) and the US start their search for products on Amazon rather than search engines. Selling into the US market? Almost nine out of ten (89%) of US consumers say they’re more likely to buy products on Amazon than any other ecommerce website.

Ultimately, you’ve got two options: treat Amazon as a competitor or embrace the platform as an additional revenue generator.

Who’s doing this well?

Passenger Clothing (#3 on the fastest growing ecommerce brand list) fully embraces the multi-channel approach.

Passenger’s range of outdoor apparel and footwear can be found on numerous online stores, including Amazon, John Lewis, Cotswold Outdoor and OPUMO.

Their full range is available directly from Passenger-Clothing.com, but if they were restricted to just selling to their estimated 27,000 monthly website visitors, they wouldn’t be among the fastest growing ecommerce retailers in the UK.

2. Acquire zero and first party data

In order for you to grow and hit your revenue targets you need to expand your customer base, and this requires data.

However, this is getting harder to come by.

With web browsers dropping the use of third-party cookies, regulations around privacy—such as GDPR in the EU and the UK’s 2018 Data Protection Act—as well as increased consumer awareness about how their data is being used, you need to get better at acquiring first and zero-party data in 2024.

Zero-party data	First-party date	Second-party data
Data the consumer intentionally and proactively shares with you, which can be collected via website forms, polls and surveys.	Data collected directly from your audience, including from previous purchases, website analytics and social media platforms.	Data you didn’t collect yourself, for example via a trusted partner.

While second-party data can still be useful, privacy laws have made it more complicated to leverage, particularly in a B2C market. What’s more, the sheer volume of marketing messaging consumers receive into their email inboxes and on social media has made it less effective.

This is why it’s so important to leverage the data your customers and potential customers have actually provided to you directly—and be better at acquiring it.

As Fatemeh Khatibloo, VP principal analyst at Forrester, said during an interview with Wayin, “zero-party data is gold.”

“When a customer trusts a brand enough to provide this really meaningful data it means the brand doesn’t have to go off and infer what the customer wants or what their intentions are.”

Of course, the challenge is in acquiring this data in the first place…

Who’s doing this well?

Fans of your brand might not need much encouragement to sign-up for your newsletter to receive new product updates, but new customers need an incentive.

Both Progress Jiu Jitsu and Naturewall offer just that, offering discounts in exchange for potential customer data:

3. A social commerce strategy is vital to capture the next generation of consumers

It’s important for ecommerce retailers to adopt an omnichannel approach in 2024, but some channels are more important than others, and social should be a top priority for you next year.

First and foremost, your social media strategy should be informed by your target market, so if you typically sell products to the over-50s you probably don’t have to worry about your TikTok presence right now.

However, if you’re selling to a millennial or Gen-Z audience, these channels are no longer something that can be neglected. In fact, a 2021 study found that social media was the preferred shopping channel for these demographics in the US market.

“Younger generations find authenticity and trust in different places than older generations,” said William Margaritis, senior VP of digital and ecommerce at Reprise Digital, during an interview with The Drum.

“Predominantly, they trust their peers and they trust influencers. As brands reduce spend and are less present in the shopping conversation, peers and influencers will rise.

“Social commerce and live commerce have already become regular means of shopping in Asia and are rising rapidly in Latin America. The US and Europe won’t be far behind.”

‘36% of shoppers would be more likely to buy on social media if they had the ability to purchase in-app.’

Executed correctly and your social channels will build trust, drive brand awareness, customer engagement and sales.

The reason social commerce can be so effective is in its convenience, eliminating steps from the purchase process and allowing a consumer to go from product discovery to purchase within seconds.

Instagram Shopping is a great example of social commerce, with your customers able to browse and purchase items directly within the platform, without having to be redirected to your website—and this is powerful. A study by Curalate found that more than one third (36%) of shoppers would be more likely to buy something they discovered on social media if they had the ability to directly purchase in-app.

Pinterest is another platform that offers ecommerce brands a revenue opportunity. Nine out of ten Pinterest users have used the platform for purchase inspiration, while almost all of them (98%) have tried a brand they discovered there.

Pinterest’s Product Pins have been optimised to make purchasing through the platform as easy as possible, with a little price tag in the corner indicating that the item is available to buy. When clicked (or tapped), they show info only available on Product Pins, including product description and brand name, as well as boasting a larger product tile.

4. Customer lifetime value will be one of the most important success metrics in 2024 (and beyond)

Ecommerce competition is increasing and it’s getting harder to attract new customers—especially in the current economic climate—and this is why it’s so important to put an emphasis on increasing customer lifetime value in 2024.

When your customers return more consistently you have more flexibility in terms of what you can spend to acquire them, but maximising LTV requires first-class customer service.

However, customer service ‘skimpflation’ is on the rise according to a Ujet.cx report.

The study found that two thirds of consumers had experienced brands cutting back on customer service in the past six months, specifically in the areas of quality of service, wait times, and expertise and helpfulness.

Consumers take this seriously, with 87% reporting that they’d spend less or stop shopping altogether with an ecommerce retailer if they cut corners with their customer service.

Maximising LTV isn’t just about customer service though, and there are marketing strategies you can adopt that will stimulate more frequent orders, and increase average order values.

What’s the state of your post-purchase follow-up with customers? Are you making sure you stay top of mind and using their purchase history to share relevant discounts and product offers?

Are you doing analysis to see which products are frequently bought together and cross-promoting them at the checkout?

Growing sales volume and bringing in new customers is great, but increasing customer LTV and AOV is going to be crucial to growing your revenue in 2024, while these are the metrics that deliver stronger revenue results over time. Make sure you’re challenging your marketing team to put work into growing these metrics and report on them frequently.

Who’s doing this well?

One of the main drivers of Wild Cosmetics’ (aka Wild) success (#5 on the fastest growing ecommerce brand list) is their exceptional reputation for product quality and customer service—and this helps to maximise LTV.

Wild boasts a Trustpilot score of 4.7 from 28,600 reviews, with many of those reviews calling out the brand’s excellent customer service.

Wild offers customers the choice between one-off purchases and a subscription model, while their cancellation/refund policy is also highly customer-centric. Subscriptions can be cancelled at any time (customers aren’t locked in for any set period) and new customers get a 30-day satisfaction guarantee, ensuring a complete refund if they’re unhappy with the product.

5. If you’re not mobile-first, you’ll never be ahead

Retail mcommerce (ecommerce sales on a mobile device) is expected to account for almost half (43.4%) of all retail ecommerce sales in 2023, so if your online store’s mobile experience hasn’t been optimised you will be losing out on a huge proportion of your potential revenue.

Of course, the need for a strong mobile presence isn’t anything new. The difference now is that ecommerce businesses need to be mobile-first, and if you neglect this you’re going to see a significant impact on mobile sales. One survey of UK consumers found that two thirds would abandon purchases on a mobile device if the process was too difficult. If retail mcommerce is indeed responsible for almost half of all ecommerce sales, you can’t afford to risk 66% of those.

A mobile-first approach doesn’t just mean the website homepage fits nicely on a smaller screen. The experience has to be fast, have a streamlined layout, be easy to navigate and have a simple and straightforward checkout process. You also need to design the website with touch screens in mind, with buttons and links large enough to tap easily without misclicking.

Who’s doing this well?

Footwear and apparel retailer Kick Game (#4 on the fastest growing ecommerce brand list) embodies the mobile-first approach.

The homepage is sleek and uncluttered, their category pages are clearly laid out with lots of breathing space afforded to different sections, while the specific product pages are easy to navigate with large images of the products.

The checkout process is also very efficient, with payment options displayed immediately within two taps of adding a product to the cart. Cumbersome checkout processes are one of the biggest drivers of lost revenue, with studies over the last decade putting cart abandonment rates anywhere between 56.82% and 81.4%.

The key challenges restricting your growth

There are a myriad of unique factors that have an impact on every business, but if you’re an ecommerce retailer it’s likely one of these five key challenges are restricting your growth in 2023.

1. The competition from Amazon

A key challenge for brands across all sectors is how to beat the competition, but in the ecommerce market there’s one business that reigns supreme: Amazon.

As of June 2022, Amazon dominated the US ecommerce market by such a large margin that it exceeded the combined market share of Walmart, Apple, eBay, Target, The Home Depot, Best Buy, Costco, Kroger, Wayfair and Macy’s.

Amazon dominates the UK ecommerce market too, although not by quite as large a margin:

The impact of Amazon on the wider ecommerce market has been so great it’s got its own name: the ‘Amazon Effect’.

There are three primary side effects of this.

1. It’s harder for smaller ecommerce retailers to stand out

The dominance of Amazon isn’t restricted to the economic landscape but the search one too.

Google a product and an Amazon listing won’t be far away, regardless of whether that’s electronics, DIY equipment, children’s toys or beauty products. The ecommerce giant appears in Google Ads listings, organic search results and is often the first Google Shopping result, and this was demonstrated in a 2021 Searchmetrics study of the search landscape of seven ecommerce verticals.

The graph below, comparing the organic traffic of Amazon versus the UK’s largest retailers, illustrates this organic stranglehold:

Their market share might not be as high in comparison to the US market, but this domination over the SERPs shows how hard it is for the big players, let alone smaller ecommerce retailers.

Amazon came out on top in four of them (Apparel, Beauty, Health and Sporting Goods), while it was second in the other three (DIY, Furniture and Electronics).

This means that, unless someone is already aware of your brand, it’s going to be hard to get discovered online in the first place.

2. The expectation of cheap / free delivery

Although not available for all products, Amazon Prime has changed the game when it comes to delivery. Free next day delivery (and in some cases same day delivery) is no longer seen as exceptional, but it’s simply not economically viable for many standalone ecommerce retailers.

If consumers can buy the same product from Amazon and receive it 24 hours later free of charge, why would they pay for slower delivery?

3. It’s hard to compete with Amazon on price

Amazon is an aggregated marketplace and this means it can connect consumers with the products they want at the best possible price. What’s more, the scalability of a corporation as big as Amazon means it can work to much smaller margins compared to standalone ecommerce retailers.

The cost of living crisis will be adding to this pressure, with consumers more likely to prioritise price over other factors such as brand loyalty. Consumers might prefer to support local and/or independent retailers, but with household finances tight they’re more likely than ever before to choose the cheapest option.

2. The cost of living crisis

The majority of Britons are feeling the pinch at the moment, with the cost of living crisis and soaring interest rates impacting households across the income spectrum. A report looking at how the crisis has affected UK, US and German consumers published by Digital River found that less than half of UK adults (47%) reported being ‘currently financially comfortable’, compared to more than a third (35%) ‘getting by’ and 17% who are ‘struggling’.

As mentioned above, the growth in ecommerce sales slowed in 2022, with 41% of consumers saying that online purchases would be one of the first expenditures they’d cut if they needed to reduce their spending.

However, soaring interest rates and inflation will have hit your ecommerce business in other ways too, with increasing overhead costs and high interest rates making new hires and investment more of a risk.

3. Customer expectations around sustainability

Given the economic climate, price is one of the primary decision factors for consumers right now, but it’s not the only decision factor.

We’re more aware of how our actions and choices affect the environment than ever before, and this is driving one of the most critical trends in global ecommerce: sustainability.

Ensuring sustainable business practices can mean additional overhead costs to retailers, specifically around manufacturing and distribution, but it’s also an opportunity to de-risk your business.

For decades, globalisation and the low cost of production overseas has seen local manufacturing decline, but the pressure on global supply chains caused by Covid-19 (and Brexit in the UK specifically) and increasing transportation costs mean more and more companies are returning to local production.

What’s your background in the ecommerce space?

Aira has worked with ecommerce brands just like you before—and we’ve got receipts…

Discover how we helped ecommerce retailers just like you to increase their revenue, including average order value and customer lifetime value.

Don’t worry, this isn’t another post about how “everything is changing”. In fact it’s about a problem that digital marketers have been facing for a long time. Forecasts.

It’s also about how ‘fan’ charts (like the one below) can help. You can’t normally make them in Google Sheets but we’ve put together a no-code-needed solution for you to do just that!

Forecasts - the impossibility of predicting the future

Forecasting is a big source of tension in businesses.

On the one hand, in most cases it’s a bad idea for a company to make decisions totally at random. Not many people would suggest changing your marketing spend every month based on a dice roll.

On the other hand, it can take months or years to roll out big business changes. So, to know what a reasonable decision is, we have to know what’s going to happen a long way in the future—we need to forecast.

I know that some marketing specialists will tense up reading that sentence, because it’s impossible to know what will happen in the future, right?

Ignoring global pandemics, recessions, and machine learning revolutions, there's all kinds of changes that can mean the next year for our business will completely change.

Even if we know the next 12 months will be exactly the same as the last, it’s pretty difficult to know exactly what worked last year, and by exactly how much. We end up having to get into that messy realm of attribution. We'll cover that in a later post.

So, business leaders need to make a decision based on something, whether that be a forecast or evidence to prove their decision is justified. Meanwhile, most specialists tend to be uncomfortable with giving a forecast the whole company will work towards because the expertise they use to produce the figure tells them just how flawed that figure can be.

What’s the solution? Refuse to make a prediction? Go back to rolling the dice? Pick a number out of the air?

Not quite.

Reminding ourselves that no one needs it to be exact

If you sit down with a business leader and ask them whether they are expecting a perfect prediction to base their decisions on (down to the dollar/pound), they would probably look at you as if you’re mad. They know these things can’t be exact, but they also know that an informed guess is still probably better than that dice roll.

Of course, it can be easy to forget that we don’t need an exact number when we’re talking about forecasts. If an agency is talking to you about £100K growth, that’s the number you’re going to discuss. You won’t keep saying “plus or minus 10%”.

The real fear that specialists have is that everyone agrees “this forecast isn’t exact” at the time, but at some point (maybe when the CEO looks at your projections, maybe when it’s time to review results) someone forgets that it’s a best guess and starts holding people to account over one number.

We’re not going to talk about avoiding blame culture here (perhaps a good future topic for Paddy Moogan’s ‘The New Leader’). Instead, we’re going to talk about a visual way to remind everyone, every time they look at a forecast, that our prediction falls within a range. Introducing fan charts.

I’m a big fan of fan charts

This is a fan chart which my colleague, Dave, made in Google Sheets. Don't worry about the specific data it’s showing, let’s just think about what it communicates.

When I read this chart, one of the things I think is “we’ve got a pretty clear idea of revenue until about half way through the year, and then it could fall in a range”.

Of course the other thing I think is “Wahey 📈📈📈”, but fan charts work just as well if it’s 📉📉📉.

You might recognise fan charts from tools like Causal Impact or Facebook Prophet, they are both great forecasting and statistical analysis tools we use at Aira.

Example from Casual Impact

Example from Facebook Prophet

To use those predictive models the way we do at Aira, you usually need to be able to code (or you need access to a team like Aira’s Innovations team). But you don’t need code for the visualisation, which I think is a really overlooked part of their value.

Just having the quick, visual cue that the real answer probably falls somewhere within a range can speed up communication massively.

How do I make a fan chart in Google Sheets?

Luckily enough, Dave Westby and I put together a template sheet which you can use right here.

Just paste your data into this table. You don’t have to work in months, it can be in days, weeks, years, whatever. You can add as many rows as you want below the table and they will appear in the chart.

The ‘Revenue (Low)’ column is what you think the worst-case scenario is, ‘Revenue (high)’ is best case. You can rename the columns of course.

If you’re using the fan chart to show a combination of past data and a future prediction, you can use the ‘Past data’ column to mark a row as historical, and that’ll create the orange line in the chart.

If you don’t know what your upper/lower bounds are but you think it could be plus or minus 20%, there’s also a tab where you can just put the number you want to chart, and then write your % margin of error and it will automatically calculate a fan chart for you.

Go forth and use fan charts!

As I mentioned before - there are some really powerful tools like Causal Impact and Facebook Prophet which produce fan charts as a kind of side effect of statistical analysis. The mathematical work that those libraries do is very valuable, but I think the fan chart visualisations are very much overlooked.

Thanks to tools like those, fan charts are an increasingly common way to express uncertainty so that business leaders can understand it and still make decisions.

Even if we only use them to reduce that friction, to get to the important conversations about how we’ll try to achieve the forecast, that’s a huge benefit.

So in summary:

• Forecasting is hard, and it’s basically impossible to get exact numbers
• We still need to base decisions on something, so our best options are to be as accurate as possible, and communicate our limitations
• Fan charts are a huge help in communicating limitations of a forecast
• Use our sample sheet to make your own!

A lot of things are going in the wrong direction—but your revenue doesn’t have to.

Soaring inflation, rising interest rates, low growth, the constant spectre of recession—suffice to say, it’s arguably the worst time for consumers and businesses since the 2008 financial crisis.

The double whammy of Covid-19 followed by the war in Ukraine has led to unprecedented pressure on global supply chains and commodity prices, and this is significantly impacting the prices consumers and businesses are paying for goods and services. The unpredictability of these macro issues are leading to delays in investments, with greater scrutiny of purchasing decisions.

The SaaS sector is feeling significant pressure, and across the industry this is manifesting in reduced sales, pressure to reduce cost and a need to maintain existing client relationships. Meanwhile, some of the biggest players in the industry have had to make significant layoffs.

According to Layoffs.fyi, at the time of writing almost 800 separate companies have laid off over 210,000 employees. This includes approximately 12,000 at Google, 10,000 at Meta and 10,000 at Microsoft.

Many of our clients in this sector are feeling their own versions of this pressure—no doubt your organisation is feeling the strain too.

In this article we’re going to take a look at what SaaS leaders are saying about the current situation, the big issues you’re probably facing and, most importantly, how you can deal with them.

Want the highlights? Download the report's executive summary.

The view from the top - what SaaS leaders are saying

The threats in the current economy can’t be denied, but when Salesforce President & CMO Sarah Franklin, Box CMO Chris Koehler, and Attentive CMO (and ex-Twilio CMO) Sara Varni came together for Mutiny’s The Second Lever conference, the message was clear: this is an opportunity for SaaS vendors.

Inevitably, your potential customers are anxious about inflation, supply chain disruption and labour shortages, but SaaS can actually help businesses meet these challenges.

"The three CMOs were also unanimous in the response to whether now was the time to cut marketing budgets—100% no."

“The good thing about SaaS businesses is that technology is the solution our customers are seeing as the way that they’re going to automate themselves, get more productivity, more efficiency, and just help businesses run better,” said Franklin.

Chris Koehler agreed that difficult economic conditions don’t mean that the pain points your software can solve are going away: “It doesn’t matter if you’re an SMB…or a large enterprise: You’re trying to figure out, ‘How do I create a better customer experience? How do I engage my customers? And quite frankly, how do I make my employees collaborate in a world that is very hybrid?’”

The three CMOs were also unanimous in the response to whether now was the time to cut marketing budgets—100% no.

“Let’s not talk about how we cut; let’s talk about how we can be more efficient…Cutting marketing is very short-term thinking, and that’s what’s going to cut your future growth,” said Franklin.

SaaStr founder and host Jason Lemkin agreed: “When you cut marketing you cut the medium term. You’re cutting off your pipeline in one, or maybe even two years.”

This isn’t to say you shouldn’t be making sure you’re spending your marketing budget more wisely.

At SaaStr 2022, 6sense CMO Latané Conant explained her approach to ensuring marketing campaigns are performing: follow the red.

“Whenever I see an underperforming metric in my marketing dashboard, I proactively investigate to see what needs to be done to turn it green.”

These SaaS marketing leaders might be preparing to double down on their marketing in the wake of the current economic crisis, but are they in the minority?

Many SaaS organisations will take the opposite view to the CMOs we’ve looked at here and, while exercising prudence during tough times is always wise, there are some common mistakes businesses make that will only make things worse…

6 issues SaaS leaders are facing… and how you can tackle them

Issue #1: Marketing budgets under pressure

During challenging times, marketing is often one of the first departments to be scaled back. Many organisations view marketing as a luxury and instead prioritise core operational expenses they deem essential to keeping the business running.

There’s also the argument that, if consumers and businesses are investing less money anyway, marketing to your prospects at the same level as during good times is a waste of money.

It’s a common reaction, but research suggests that doing so hurts organisations in the medium term. 

A study conducted by McGraw-Hill Research (now part of S&P Global Market Intelligence) in 1986 found that ‘firms that maintained or increased advertising during the 1980-81 recession averaged significantly higher sales growth during the recession and for the following three years than those which eliminated or decreased advertising.’

Note the reference there to ‘the following three years’. Increasing marketing spend during an economic downturn might not lead to immediate results, but you’re laying the foundations for success when the recovery begins.

In the wake of the 2008 financial crisis, Peter Steidl highlighted data which supports this from the Profit Impact of Marketing Strategies (PIMS) in his book ‘Survive, Exploit, Disrupt: Action Guidelines for Marketing in a Recession’.

The PIMS database showed that return on capital employed (ROCE) increased by 8% for companies that increased marketing spend, by 9% for companies that maintained spending, and 10% for companies that cut spending. Fine margins, but that would suggest you should cut your marketing spend, right?

However, when you look at the difference in performance once the recovery begins, it’s clear who comes out on top. In the first two years following a recession, ROCE increased by 4.3% for organisations that increased spend, compared to just 0.6% for companies that maintained spending, and a drop of 0.8% for companies that cut spending.

There’s a great example from recent history that demonstrates this dynamic.

In the wake of Covid, the travel industry was among the biggest losers. National lockdowns and travel restrictions were in place throughout 2020 and 2021, but Airbnb and VRBO responded very differently.

Airbnb slashed their ad spend during this time, but VRBO stepped it up. Between January and February 2021, VRBO spent $90.8million in advertising, while Airbnb spent just $8.9million.

The result?

VRBO’s bookings recovered by 61%, compared to a 15% drop for Airbnb in the same period.

“Be fearful when others are greedy, and greedy when others are fearful.”

— Warren Buffet

How to tackle it: Don’t talk about how you can cut, talk about how you can be more efficient

You don’t necessarily have to take VRBO’s approach and increase marketing spend, but the mistake is thinking in terms of cuts rather than efficiency.

You need to get forensic in looking at your current marketing and identifying what’s working, what’s underperforming and what’s flat-out failed. Shift budget towards ad campaigns that deliver the highest ROI, be more discerning in the events you sponsor and scrutinise every penny spent—but don’t just implement a blanket cut in your marketing budget. Pulling money from marketing and taking decisions that aren’t backed by data is just as likely to cost the organisation money as save it.

Issue #2: Neglecting the decision makers

If you’re selling to a B2B market, who’s the person you need to convince to invest? Is it the employee(s) who will be using your software every day, or the CXO controlling the purse strings?

Of course, there will be multiple stakeholders in a B2B sales process, but the final decision maker is typically at board level. That’s not a profound statement, but then why do so many SaaS vendors prioritise the user buyer in their marketing messaging?

You talk about specific features and why your software is easier to use than your competitors’ products.

Valuable points to make, but the economic buyer doesn’t care about that fancy widget that no other software offers. They care about how your product is going to impact the top or bottom line.

How to tackle it: create messaging for both user and economic buyers

In B2B SaaS sales cycles the user buyer is often the person conducting the initial research. They’ll also be the first person to make an enquiry, so it’s essential you have compelling marketing messages ready for them.

However, the further you get into the sales process, the more economic buyers will get involved. Once in the room with CXOs, you can’t just deliver the same messaging as with user buyers.

These two groups have unique challenges and you need to be able to show your solution delivers for everyone’s needs.

How to sell to user buyers

In many ways, user buyers are your reason for being. Making their day-to-day job easier is what your product is designed to do, and this is how they’re going to judge your solution.

This means they want to evaluate user experience and operational impact. Testimonials and reviews from satisfied users are great here, but the best way for them to do so is through hands-on experience of the software via demonstrations and free trials.

How to sell to economic buyers

If you’ve got a list of target accounts you can either start by trying to get in front of user buyers, or go straight to the decision makers. This is harder, but can be a faster route to sale.

Lots of organisations are trying to secure meetings with the same economic buyers you are, and they’re getting reached out to a lot. This means you need to give them a very good reason to take a call or book a meeting with you.

Generic elevator pitches won’t cut it. Make sure you’ve got some quantifiable benefits you can offer straight out of the gate to grab their attention.

For the sales pitch itself, remember that economic buyers aren’t solutions experts like the user buyers you’re trying to sell to, and they don’t have the time to be. In the majority of cases, they simply want to understand the potential return on investment.

During sales pitches, economic buyers love to see case studies and examples of where you’ve helped businesses like theirs increase revenue and reduce costs.

It helps to get straight to the point with economic buyers too, so avoid padding your presentations with information that’s not going to interest them, such as company history and culture. The specifics of your SaaS solution are important for user buyers, but economic buyers don’t need to understand how the platform can be used day-to-day, so communicate this with user buyers when the economic buyers aren’t in the room.

Put together an org chart

Every stakeholder needs to be considered and engaged with for a B2B SaaS sales pitch to go smoothly. We’ve talked about both economic and user buyers, but there are key differences within these groups you need to have visibility of.

A detailed org chart will map out everyone within the business and what you need to do to get them onboard: what pains are they experiencing, what are they trying to achieve, what objections might they have to your solution?

This will take some time to research, and you might need to get the support of your Champion within the organisation to make sure it’s accurate, but it’ll be worth the time investment.

Issue #3: Pressure to prioritise the bottom of the funnel

When generating new revenue becomes more of a concern, SaaS vendors often focus more of their efforts on the bottom of the funnel. This isn’t a mistake. In fact, we recommend to the SaaS companies we work with to start at the bottom and work backwards, prioritising tactics that will deliver the fastest ROI.

The issue is when you only focus on the bottom of the funnel. Afterall, 96% of visitors that come to your website are not ready to buy.

Sales teams abandon value-led comms in favour of outbound efforts with cold calls and emails. Marketing stops creating awareness-level content and instead focuses on pushing features and benefits of their software.

It's not a mistake to focus more of your efforts on the bottom of the funnel. The issue is when you only focus on the bottom of the funnel.

There are two problems with this strategy.

Firstly, outbound sales can work for you, but it’s hard. Developments in tech and automation have simplified the process in recent years, but response rates have reduced dramatically. Tools, people and economic state make this an expensive—and not always predictable—channel to facilitate growth.

Secondly, neglecting the top and middle of the funnel will see your pipeline dry up in the medium to long term. Event sponsorships, gated content and brand awareness efforts won’t necessarily drive sales today, but they do drive the leads that will become new customers tomorrow.

Further to the above statistic highlighted by the Adobe eBook on lead generation, a 2022 study published by LinkedIn’s B2B Institute and the University of South Australia’s Ehrenberg-Bass Institute for Marketing Science found that just 5% of a business’ total addressable market has intent to buy. Further to this, research by Gartner revealed that 83% of a lead’s journey is not spent with a sales rep. The final 17% is where a lead is closed and becomes a customer, but they’ll never get there without being nurtured throughout the funnel.

83% of a lead’s journey is not spent with a sales rep:

That 5% might be where the money can be found today, but neglecting the remaining 95% is going to cost you opportunities in the future.

How to tackle it: implement a multi-channel marketing strategy

If growing revenue quickly is a priority, putting more resources into the bottom of the funnel isn’t a mistake, but it could be if it’s at the expense of all your other channels.

Make sure you continue with a multi-channel marketing strategy. That means keep posting on your social media channels. Continue creating educational content that helps your prospects understand the solutions to their challenges.

Sales’ time will be much better spent reaching out to warmer leads, and it will also help to ensure your pipeline is healthier in 6-12 months. Additionally, utilising both brand building and performance elements in a campaign often increases overall return on ad spend compared with spending on performance channels alone.

Two great examples that demonstrate the impact of brand building - specifically content marketing - are Lumen5 and Moosend.

Lumen5, a dedicated social media marketing tool, went from 25,000 website visits to over 500,000 in less than a year thanks to content marketing—but they also created multiple content offers that captured leads who were at different stages of their buyer’s journey.

For Moosend, a marketing platform specialising in email marketing, a full funnel marketing strategy increased their organic traffic by 10X, while they’ve also created a number of gated resources for converting that traffic into leads, including webinars and infographics.

Issue #4: It’s hard to stand out in a crowded SaaS market

You’ve identified your user’s pain points and solved them with an effective SaaS solution. Your pricing is competitive and the UI is slick.

But guess what? You’re not necessarily as special as you think you are.

Back in 2012, the average number of competitors for SaaS firms was three. By 2017 this increased to nine, and the SaaS market is still growing rapidly. The global SaaS market is expected to hit $720.44billion by 2028.

Your solution might be the best around, but don’t overestimate your USPs and expect them to speak for themselves.

This isn’t just about the specific features of the software. For example:

• Your solution might have the most comprehensive functionality, but if your onboarding and knowledge base is poor people won’t be able to use it.
• You might be the lowest cost solution on the market, but you don’t offer a free trial.

How to tackle it: effectively differentiate yourselves from the competition

In order to ensure your SaaS product stands out from the crowd, you need to understand what the crowd is offering.

Conduct thorough competitor analysis to identify their strengths and weaknesses, and user research to discover what your prospective customers actually want from a SaaS product.

From this research you should develop (or refine) your ideal customer profiles (ICP) and buyer personas.

Note that these aren’t the same thing.

ICPs are only relevant to B2B SaaS vendors, and describe what your perfect customer looks like—a fictitious company that boasts all of the qualities you’d want from a customer that’s the best possible fit for your products or services.

Help me define my ideal customer profiles

By contrast, buyer personas are a semi-fictional representation of the people that buy from you. For B2B SaaS sales, they refer to the decision makers involved in the sales cycle, including both user and economic buyers.

Help me define my buyer personas

Having a clear understanding of what motivates your customers will help define your marketing efforts, as well as how your product and processes can be optimised.

If you’re best-in-class in one aspect of your solution make sure you’re emphasising that during sales meetings. If you’re lagging behind in another, put more effort into improving that aspect of your offering.

In a crowded SaaS market differentiation is essential, and this requires an organisation-wide effort to understand and communicate where the value in your solution lies.

Also remember that businesses and consumers make decisions based on subjective criteria too, so it’s not enough to simply push software features and neglect to consider how your marketing and sales strategy makes your target audience feel.

There’s also a connection here as to why cutting marketing budgets is a mistake. Reducing your presence in the market will give your competitors an advantage in the fight for your target market’s attention, and it might be hard to recover when the economy improves.

Once you’ve clearly identified the needs and challenges of your target market, and how you stack up against the competition, you need to nail your value proposition to ensure you’re standing out in your market and speaking directly to your personas. Again, this requires input from multiple teams—not just marketing. Sales, account managers and customer success reps will all have valuable input here in helping marketing to craft messaging that answers the target market’s pain points, having engaged with them throughout different stages of the user journey.

Issue #5: Pressure to focus on new leads/sales at the expense of existing users

We get it.

Growth is slowing down, the economic forecasts aren’t looking good and you’re worried about hitting your revenue targets. It’s time to focus all our efforts on generating new leads and closing new customers, right?

This isn’t just a common mistake that SaaS organisations make—it’s a mistake businesses across sectors make.

Yes, generating new business is crucial to growth, but it’s your current users who are the foundation of your annual recurring revenue (ARR).

If the organisation neglects existing users you’re going to see an increase in churn and find it even harder to meet those growth goals.

Current users who are the foundation of your annual recurring revenue (ARR).

Kevin Stoll, Vice President of Capgemini told SaaStock: “You still see large organisations overspending in areas that aren’t related to retention of customers.

“They still have too many focuses: they’re trying to break into multiple geos and launch new products.”

But what might this ‘neglect’ look like?

• Cutting the Customer Success and Service teams and trying to manage existing users with less resources.
• Focusing all of your marketing efforts on new business and not sharing product updates, special offers and educational content with existing customers.
• Focusing all of your sales efforts on new business and missing out on upsell and cross-sell opportunities from existing customers.

How to tackle it: Work closely with Customer Success teams to ensure you’re driving retention and long term usage

New business will (almost) always generate greater net new revenue, but you’re not going to grow MRR and ARR without a satisfied existing customer base, and there are three key reasons for this:

Increased customer churn

A 2022 survey of 110 private SaaS companies found that the median gross dollar churn for the sector is 14%.

The more you shift your focus from existing users to new business, that 14% is only going to increase, but you’ll also see an increase in involuntary churn: the result of expired credit cards, technical issues etc. It’s estimated that as much as 40% of churn could be caused by losing customers who don’t even want to leave.

Fewer positive reviews and referrals

One of your most powerful sales tools are existing users.

G2’s 2021 Software Buyer Behavior Report found that ‘86% of software buyers, across segments, use peer review sites when buying software’, which means your potential new customers will be deterred by negative reviews—or a lack of positive ones.

This is the rationale behind HubSpot’s Flywheel model.

It explains the momentum gained when the entire organisation is aligned around delivering an exceptional customer experience.

Existing customers are also a new revenue opportunity

As mentioned above, a new customer will probably always offer a larger net new revenue opportunity—but upsells and cross-sells from existing (and, most importantly, satisfied) customers might be easier to close.

“The cost of acquisition is quite a bit lower. You already know their preferences and what they do, and they know how they use your product,” said Kevin Stoll.

They already know your product, hopefully understand its value, and will be more open to investing more money than someone who’s never used the software before.

Issue #6: It’s hard to find the right marketing partner

The vast majority of organisations—from B2B to B2C, from SaaS to ecommerce—use similar strategies and market themselves across the same platforms. So, as long as you’re working with marketing experts, you’re in safe hands, right?

Not really.

A marketer or marketing agency who doesn't specialise in a particular niche (such as SaaS) might be an expert in Google Ads, SEO, copywriting or social media, but they don’t necessarily know your market, understand a SaaS sales cycle or the KPIs that matter most to you.

How to tackle it: work with SaaS marketing experts

If you’re looking to make an internal hire or employ the services of an agency or freelancer, make sure they have experience in the SaaS market. If it’s the latter, ask for case studies and testimonials from SaaS organisations they’ve worked with.

Not every agency will be able to back up their claims with examples that demonstrate genuine results. Some can...

The latest edition of Aira’s innovation update is here! Fortunately, it’s really not hard to come up with things to talk about.

Again, we’ve got a quick summary of some of the stuff we’ve been reading recently, some updates of what we’ve been doing at Aira, and this time some details on some of the ways our Consultants have been using new tools.

What we’ve been reading

To be honest, we’re finding it hard to cut down our reading list for these updates, but here’s a selection of interesting pieces on some different topics:

• Recast did a great quick-read on how companies of different sizes/stages of growth should think about attribution. Honestly, for a Mixed Media Modelling tool company, it’s pretty impressive that Recast dedicates so much time to telling people when they might not need MMM.
• YouGov released a whitepaper about how consumers are responding to the cost-of-living crisis. They cover 13 countries but with a particular focus on the UK and US. Some interesting stats in there but, as with anything survey-based, it’s worth bearing in mind the data can be skewed by who happened to respond.
• Google have created a Machine Learning model that can take an item of clothing and show how it would look on different body types. While this is cool, we imagine that most clothing companies will want more control over the way customers see their clothes than simply relying on Google correctly guessing what designers changed between sizes.
• McKinsey think that AI is going to add 4.4 trillion to the global economy, but only as long as we make sure people are supported as they adapt roles/change jobs (this is not a short read)

What we’ve been doing

• We shared an internal tool we’ve been using to reformat tables to be presentable (this kind of unexciting work is exactly the kind of thing we want to take off consultants’ plates)
• We hosted our first HubSpot User Group in June, with a range of talks on AI. External speaker Claudia Higgins from Conductor spoke about the state of AI in SEO and was followed up by Aira’s very own David Westby who looked at AI, Google and Accountability with a keen focus on the changes being implemented by the search engine and the potential ramifications for businesses. Matthew Purchase, also from Aira, delivered a talk on a brief history of AI and HubSpot, looking at the existing AI features within the platform, the recent acquisitions ,and speculated on where this could go.
• We announced the return of MKGO for this September, with free tickets currently available here. The event will be held at Milton Keynes Gallery, and we've got some great speakers lined up, including Azeem Ahmad, Mehul Garg and our very own Katherine Monkcom, so what are you waiting for? Grab your free ticket before they run out!

What we’ve been thinking - Everyone is innovating

At Aira we believe pretty strongly that innovation shouldn’t just come from the ‘Innovation’ team - they should come from the people working directly on client problems. People who are getting daily exposure to what our clients need. It’s the same reason our Consultants are the ones who wrote up their perspective on how Google’s adoption of AI is likely to change the search landscape.

In this update we wanted to share some stories about how our Consultants are using tools like ChatGPT to supercharge their day-to-day work.

Building two image compression tools using ChatGPT - Mathew Stuckey

I recently did some work for a client which required compressing a large amount of their image catalogue in a bid to improve load times.

After becoming frustrated with the constant back and forth due to the file limits imposed by web-based tools, I decided to look into creating my own image compression tool via ChatGPT which I could run through codepen.io (check it out here!).

Initially, I’d simply asked if it could “code me an image compression tool”, which obviously it told me it could do easily, and then gave me a code script that didn’t function in the slightest. 

I spent a lot of time chatting with GPT, simply telling it that the tool didn’t work listening to its apologies and then retrying with the next line of code it gave me. Eventually I gave up. 

But the next day, after hitting another file limit on a free tool, I revisited the idea. After some reading up on image compression and GPT prompting, I eventually came up with the following prompt;

“You are a high-end developer with substantial knowledge of coding and image compression techniques.

I would like you to give me the individual HTML, CSS and Javascript code for an image compression tool. The tool should be able to handle both JPEG and WEBP files.

It should allow for multiple files to be uploaded at once up to a limit of 20.

The tool will then compress those files using lossy compression for the webp and jpeg at a rate of 0.3.

The tool should have a progress bar so that the user can see the status of the compression job. 

The output should be a list, so that the user can redownload the individual files as they need.

The tool should be styled in a simple, modern way and be easy to navigate for users.”

This gave me a MUCH better looking output which, after copying into Codepen, still didn’t work at all.

But it was far closer.

One of the benefits of using a tool like Codepen is it allowed me to have a back and forth with GPT by just presenting it with any errors that were shown in the console box, it was then able to assess the error and adjust the code accordingly. 

In fact, after copy and pasting the single error that was thrown up this time around, GPT was able to debug its own code and promptly provided me with an amended version of the Javascript.

Once this code was swapped over, success! I now had a fully functional compression tool that would allow me to compress client images without any intrusive ads, usage limits or requirements to upgrade to a pro version.

The success of this made me look into other tools I could also create using the power of GPT. So, I also put together a similar WEBP conversion tool which can take multiple image files and convert them all into WEBP format, with the output being an automatically downloaded .zip file of the new images. 

Where tools like Convertio only allow for two conversions at a time, I can now transfer an entire image catalogue in one go and convert a client's images to a faster format in one click. This saves a huge amount of time and effort, meaning I have more time to focus on work elsewhere.

Categorising content using ChatGPT - Kathryn Monkcom

Like my colleagues, I’ve been spending some time investigating ways in which ChatGPT can help us do better work, faster. Of course, we don’t always just assume these tools are the best ones for the job and ,in this case, GPT isn’t ready to fly solo, but there’s a couple of things we can do now.

When it comes to inbound strategy, planning concepts for gated content can be one of the more time-consuming tasks. It often comes down to:

1. Research what’s already out there
2. Come up with some new ideas and choose one
3. Test how it performs
4. Repeat

A good way to narrow down your options is to try to find examples of high traffic content that not many people have covered. And the best way to do that is to scrape as many websites as possible in your niche, categorise the content and see what’s getting a lot of traffic, but doesn’t seem to be covered in much detail.

I wanted to see if GPT could help us speed up the categorisation step. I found that I had to do a lot of manual cleanup on the output, so I don’t think it’s quite ready to do everything yet. I ended up using GPT as a first pass, followed by some trusty RegEx and then my own manual checking. 

Here’s my process to give you a head start so you can come to your own conclusions - or come up with something better!

1. I used Ahrefs to scrape my client’s site, and their competitors, getting monthly traffic and a title for each page
2. I used GPT for Sheets™ and Docs™ to group the pages into one of: Checklist, Guide, Resource, Ebook, Template, Other. You could also use it to group by topic or theme, i.e. ‘Marketing Automation’ or ‘Strategy’.
3. I then used sheet regex formulas over the same page titles to put together flexible categories based on the same terms. This was a great way to sense-check/overrule GPT categories.
4. For each group I counted up the traffic, and the total number of pages, to find categories where there was lots of traffic but not that many pages.

By looking at traffic numbers and page count I could quickly see that Checklists were one of the best performing but least used formats. My client had been focusing all their time on guides, which performed well but had a lot of competition. This was great insight that helped us plan our next few months of highly effective content.

As I mentioned, GPT didn’t do a great job of categorising the pages alone. It seemed to rely a lot on exact word match. For now - RegEx is more reliable but I did get some help from our GPT-based “make me a formula” tool to speed that up, so there was still some value to be had there!

The next thing we’re going to try is scraping the sites further to get page content and check them for related words or phrases. With that extra information, GPT may well take the lead!

Prompt engineering to help with SEO tasks - Matthew Kohli

I am a well-known ChatGPT-enthusiast at Aira and I’ve spent quite a lot of time looking for ways to use the tool to improve our work. For example, our copy briefing process.

Aira’s copy briefing process goes something like this;

1. SEO Strategist does keyword research, competitor analysis, and client interviews to understand the industry
2. SEO Strategist turns that research into a detailed brief (with recommended structure and titles)
3. An expert copywriter (normally expert in both copywriting and the client industry) writes the content.

In my experience, GPT can’t do steps 1 or 3. It gets facts wrong, doesn’t have the depth of a good copywriter, and doesn’t care about business impact (not to mention all the industry context it is missing). However, it is pretty great at rewriting or restructuring information, so it can speed up step 2 by a lot.

Here’s the process I use:

First, complete your research (kind of goes without saying) then download “LinkReader” and “Webflow” ChatGPT plugins. Finally, use this prompt structure:

Here’s the output:

Meta Description: "Boost your SEO with our comprehensive guide on internal linking. Learn the basics, best practices, and strategies to improve your site's performance."

Heading level and title	Brief explainer for the writer
H1: Internal Linking For SEO: Comprehensive Guide	This is the main title of the article. It should introduce the topic and grab the reader's attention.
H2: Understanding the Basics of Internal Linking	Explain what internal linking is, why it's important, and how it impacts SEO.
H3: What is Internal Linking?	Define internal linking in a simple, easy-to-understand way.
H3: The Importance of Internal Linking for SEO	Discuss the benefits of internal linking for SEO, including site navigation, spreading link equity, and improving page authority.
H2: Internal Linking Best Practices	Provide a detailed guide on how to effectively implement internal linking strategies.
H3: Using Anchor Text Effectively	Discuss the importance of anchor text in internal linking and provide tips on how to choose the right anchor text.
H3: Balancing Link Value	Explain how to balance the distribution of link value across the website.
H3: Creating a User-Friendly Link Structure	Discuss how to create a link structure that enhances user experience and boosts SEO.
H2: Developing an Effective Internal Link Strategy	Provide a step-by-step guide on how to develop an effective internal link strategy.
H3: Conducting an Internal Link Audit	Discuss how to conduct an internal link audit and why it's important.
H3: Identifying Opportunities for Internal Links	Provide tips on how to identify opportunities for internal links within the website.
H3: Implementing the Internal Link Strategy	Discuss how to implement the internal link strategy, including adding new links and updating existing ones.
H2: Case Study: Successful Internal Linking in Action	Provide a case study or example of a successful internal linking strategy. This could be a client success story or a well-known example in the industry.
H2: Common Mistakes to Avoid in Internal Linking	Discuss common mistakes in internal linking and provide tips on how to avoid them.
H2: Conclusion: The Power of Internal Linking for SEO	Wrap up the article by reinforcing the importance of internal linking for SEO and encouraging the reader to implement the strategies discussed.

---

If you have any questions about the topics we've covered in this month's Pulse, don't hesitate to get in touch.

Welcome to the second Marketing Innovation Pulse newsletter. I'm Dave, Senior Data & Insights Consultant at Aira, and part of the innovations team here at Aira.

The main focus of this newsletter is on forecasting. More specifically, SEO forecasting.

With marketing budgets increasingly scrutinised, it’s never been more important to be able to make predictions about what value you’re able to bring (especially as an agency). We’ve spent a lot of time thinking about this… and working on a solution.

This newsletter will give you a bit of an insight into that thinking, as well as what else we’ve been up to.

What we’ve been reading

Unsurprisingly, there’s still a fairly heavy 'Machine Learning' lean this month, but thankfully many of the big tech companies are making moves in one way or another, which means a bit more variety in our reading list!

• We've been reading articles about Perplexity.ai, an interesting ChatGPT alternative, which is meant to be more concerned with factual accuracy and includes embedded links to sources as standard.
• A short thread from Barry Adams about newspapers and zero search volume keywords.
• The announcement about Google Product Studio which could, among other things, help advertisers grab your products out of existing images and put them on a totally different background.
• Canada is preparing to pass a law that makes Facebook pay news sites to distribute their content. In response, Facebook is preparing to stop showing news sites in Canada (starting with a test on 5 June). We’re not sure quite how this will pan out but it’s interesting to watch all the same!
• A fascinating, in-depth article looking at accountability in artificial intelligence. This is likely to be a topic we’ll be hearing and discussing a lot about moving forward. 

What we've been doing

• Aira was welcomed as part of the HubSpot Partner Advisory Council.
• We announced an internal tool that generates Google Sheets formulas based on a description of what you want to do.
• After Google I/O, Paddy shared his thoughts on the latest developments in search, and our search teams shared their thoughts about how AI is likely to change search.
• We tried out 'Baby AGI', which claims to take complicated instructions, build a plan and complete the plan based on making multiple OpenAI API calls. Honestly? We found the results underwhelming.
• We also tried out 'Dalai' a Large Language Model (like GPT) that you can run on your laptop. Interesting, but so incredibly slow that it’s not really useful for much other than research, particularly given how cheap GPT is.

What we've been thinking - the key challenges in building forecasts, and how we approach SEO forecasting

With marketing budgets receiving greater scrutiny within a tougher economic landscape (certainly in the UK), businesses are increasingly focused on how efficient they can be with their marketing spending.

When speaking to different organisations, we’ve noticed an increased emphasis on this question:

“If I were to invest x, what would my return be?”

Generally, SEO professionals can be reluctant to forecast precise numbers (and consequently be accountable for hitting those numbers), as there are many external factors that can impact traffic.

These factors include core algorithm updates from Google, the introduction of new SERP features (especially with the AI changes that Google is planning) and other external factors that can all impact the traffic, conversions and ultimately, revenue.

At Aira, though, we understand that forecasts are crucial to making business decisions, so we’ve put a lot of thought into how best to estimate sessions, conversions and revenue.
In this post, we’ll explain some of the main challenges of forecasting and the strategies we use to handle them.

There are three crucial elements of a forecast

• Business relevance
• Adaptability
• Acceptable degree of accuracy (and inaccuracy communicated clearly)

Business relevance

Each business is unique, and as a result, each website is going to be distinct as well, with varying seasonal demand, conversion rates, average order values and timelags between people visiting the site and the business making money.

If we were to compare an ecommerce website selling shoes with a B2B SaaS company specialising in bespoke ERP software, the levels of traffic, conversions and seasonality will differ wildly.

For the ecommerce website, 90%+ of the website pages are likely to be transactionally focussed (i.e category pages or product pages) and the time between someone visiting the website and then converting is likely to be relatively small, with a substantially lower average order value than the SaaS company.

On the other hand, for a B2B SaaS company, the site is likely to have far more of a mix of informational content, alongside some more commercially focused content. Both of these types of content will have different conversion rates and time lags from an initial visit to the site to the business making money.

As a result, the forecast needs to be able to cater to these different businesses and the way in which they drive traffic and make money.

Adaptability

Forecasts need to be adaptable to the different scenarios.

In an ideal world, a forecast would just require a click and away we go, but in reality, there needs to be a lot more thought that goes on in the background.

Let’s say, for example, that you’re forecasting conversions for an ecommerce site and you’re initially going to focus on improving CRO. You’d want to run the forecast with conversion rates set at the current level, but also run the same tests with an improved conversion rate and compare the two.

The key is asking the right questions and being able to cater to the forecast accordingly.

When it comes to forecasting organic sessions, the key levers we can pull are predominantly centred on improving existing content, producing new content and improving the technical state of the site, and it’s useful to be able to map out different scenarios.

Some of the questions we may ask are:

• If we were to prioritise technical health first, what impact is that going to have on existing content?
• Would we be better focused initially on building new content or optimising existing content (i.e where is there greater opportunity)?
• How will different budgets allow us to do different levels of work - and what consequent impact will that have on the bottom line?

Acceptable degree of accuracy (and inaccuracy communicated clearly)

Forecasts are seldom going to be bang on the money, but a forecast should at least be in the right ballpark.

This greater accuracy comes from:

a) Using historical website data and pattern-based forecasting.

b) Making the forecast bespoke for the specific business and the type of website they have, their conversion rates, lags, average order values, and the types of customers they are looking to engage and take action on their site.

An important element of the forecast result is also communicating the acceptable degree of accuracy and inaccuracy, and transparently displaying a margin of error based on upper and lower limits.

Challenges of forecasting

A forecast is not a guarantee. It’s a prediction based on combining business intelligence and historical data in order to make estimations about the future.

Using historical data is central in order to understand seasonal trends and the overall trend of traffic, and be able to map these into the future. Historical data is also crucial in terms of understanding conversion rates, average order values, time to go from first session to conversion, etc (otherwise we’d just be picking them out of thin air).

There are two main types of forecasting methods that can be used which have their own relative benefits and drawbacks:

• Pattern-based forecasting
• Opportunity-based forecasting

Pure pattern-based approach

Pattern-based forecasting involves analysing past trends, patterns and relationships in the data to project future results. Examples of this include Facebook’s Prophet and Richard Fergie’s Forecast Forge.

Example output using Facebook’s Prophet. 

Benefits:

• The forecasts take in the context of the current site and as a result, understand seasonal variations throughout the year and more effectively map them into the future. 
• The forecasts are grounded in the context of what has been achieved and are therefore able to understand and build forecasts that follow the prior trends - whether that be up or down (or stable).
• If the current projections are down, then the forecast will continue to forecast down. The benefit of this is that the forecast is grounded in reality and won’t always assume an improvement, which is more likely with an opportunity-based forecast. This means that the forecasts are likely to be more representative of the reality of site traffic. 

Challenges:

• Pattern-based forecasts rely on historical data, so if historical data doesn’t exist the model is limited. The general advice is that you’d want at least two years in order for the model to really understand seasonality.
• The model can’t predict what it hasn’t seen before. If we’re forecasting organic sessions based on significant technical improvements and an avalanche of new content, the model, in itself, would not be able to factor that in.
• The model can be overly optimistic. If a new site has launched and has seen a continuous uplift in traffic in the first year, for example, the model will assume that this will continue regardless of the Total Overall Market.
• The model assumes that you’re not going to make any drastic changes which, if you’re an SEO agency, doesn’t really fit in with the type of work you’d like or in most cases need to do.
• The model doesn’t involve looking at what customers actually want and doesn’t lend itself to any action - instead, it is more focused on predictions based purely on if the status quo continued.

Pure ‘Opportunity’-based approach

Opportunity-based forecasting focuses on making future predictions based on how much of a total potential market we'd be able to own. At Aira, we have the Keyword Navigator which allows us to see the maximum number of additional sessions we could acquire from new or existing pages, and how many pages it would take to build/optimise.

Example output from looking purely at incremental traffic.

Benefits:

• In contrast to the pattern-based approach, opportunity-based forecasts don’t assume that we’ll keep growing forever. There is an understanding built in that there is a total addressable market, and it’s more a question of how much of that market we could own.
• It’s grounded in the reality of the market we’re operating in, whether there’s a huge opportunity for growth or whether there are more marginal gains.
• The model is centred on the customers and the specific metrics they are looking for. That means that forecasts can be more impacted by specific actions (as opposed to overall trends, which is more common with pattern-based forecasts).

Challenges:

• Unlike pattern-based forecasts, this approach doesn’t take into account historical trends. For example, if website traffic has been falling year on year, this model will not factor that in and will assume incremental growth year on year.
• Seasonality is often ignored, which again, means that many opportunity forecasts just show incremental growth instead of being able to understand that in ‘low months’ when your products are less popular you might actually expect a drop in traffic.
• Opportunity-based forecasts have a tendency to be too conservative compared to pattern-based forecasts where there is no upper ceiling. This is due to the fact there is a defined upper limit that your forecast couldn’t surpass.
• Using opportunity forecasts is useful for saying ‘this is what is in reach if you do everything possible this year,’ but it takes more time to look at forecasting monthly projections based on a limited amount of activity per month.
• Another issue with this approach is that lags are not often factored in and as a result, the assumption is that as soon as you start working, you instantly see an uptick in sessions and conversions. In reality, there is a time delay in doing the initial work, getting it implemented on-site and then seeing the benefits.

Aira’s solution to forecasting organic performance

At Aira, we’ve developed a solution that allows us to develop forecasts that rely on combining the overall potential traffic from new and existing pages with historical projections from previous years.

This solution can be broken down into:

• Stage 1 - Calculating the total organic traffic opportunity, for us using the Keyword Navigator. You can also see an explanation of some of the reasoning we use in my blog post here.
• Stage 2 - Breaking down the Total Opportunity into tasks and calculating how many of those tasks we could get done over time based on a specific budget.
• Stage 3 - Adding lags in order to cater for time for work to be delivered, implemented on-site and start ranking.
• Stage 4 - Using seasonality to upweight/downweight impact over time.
• Stage 5 - Making everything formulas and variables in order to allow flexibility and map different scenarios.
• Stage 6 - Presenting the forecasts using confidence intervals.

We’ll cover the most important stages in the sections below.

Taking overall opportunity and breaking down to individual tasks

Total potential traffic numbers are a brilliant feature of our Keyword Navigator Tool, as we’re able to see:

• The amount of traffic we could attain from building new pages and optimising existing pages.
• How many pages it would require to build/optimise in order to hit that overall traffic number.

Essentially, we estimate where we could rank based on current search results and we calculate how much more traffic (and revenue) opportunity we have, per keyword, using Search Console clickthrough curve, current site rankings and on-site conversion rate.

However, it would be a pretty wild assumption to assume this is the total addressable market and we’ll get everything in a year unless you do the maths.

Breaking down the potential opportunity into specific tasks allows us to ground these traffic estimations into actual work, which further allows us to estimate how much additional traffic we could look to drive month on month.

This also allows consultants to keep accountability and make considerations for other tasks such as quarterly reviews, technical audits, and weekly meetings where the team is not going to work on tasks that will directly increase traffic (though are still important).

This also allows us to communicate with clients about the rate that we’ll be moving and consequently what we would be able to do with a greater budget, or if we were to prioritise some tasks over others.

To break the traffic estimate down into tasks, we look at things like:

• Are we already ranking for this search? Are we already ranking pretty well? If so, is it a matter of simple optimisations?
• Are we ranking for highly related keywords? Check out this post for how we use SERP similarity to cluster keywords.
• What’s the technical health of the website?

Factoring in lags

We’d all love to publish a new page, and ‘BAM!’ immediately get traffic and conversions coming to our site straight off the bat. In reality, though, there are a number of time lags that are going to impact how long it takes to start benefiting from new content.

The most obvious of these is the time it takes to actually start doing the content-related work, such as finalising the keyword research, writing the briefs, writing the copy, reviewing the copy and finally uploading the copy to the site.

Another consideration is the time it takes for content to be crawled, indexed and rank which can vary significantly between different websites depending on the technical state of their site and the type of site they have (i.e news publisher or jobs site is generally going to have a quicker indexation time compared to a small B2B site).

So, in all of our calculations, we figure out when we’d expect the work to be done and then work out when we’d expect that work to have an impact based on what we understand about lags for that business.

We also factor in the average time between initial sessions becoming conversions which again significantly differ between different types of websites (i.e. ecommerce compared to B2B SaaS). These all help us to allow more realistic predictions of how additional traffic and conversions are likely to occur.

Seasonality

One method for understanding seasonality is simply using last year's traffic, but by using machine learning we create a basic trend line for the coming year, handling seasonality and growth, and smoothing out outliers.

If we just took that as our forecast for the year ahead, we’d run into the issues we mentioned above about pure pattern-based approaches. So instead, we figure out the day-by-day trends and use them to upweight/downweight our impact estimates. If weekly and monthly seasonality shows that a day is typically 50% lower than average, we take our impact estimates for that day (based on Step 2) and drop it by 50%. The same approach works for a steady upward/downward trend over time. This offers all the benefits of pattern-based forecasting but is grounded in the reality of the actual opportunity a business has!

One reason this is important is that prioritising work earlier may well pay dividends if the site is in good shape by the time a high month rolls around. This may be through prioritising content-focused or technical work earlier, or even pulling budget forward in order to capitalise on busier periods.

In the example below we can see that Month 8 is when this search starts to drive a lot of the traffic to the site, therefore prioritising work earlier on will mean that once the busy season rolls around, our new content has already been indexed and is more likely to drive sessions and, ultimately, conversions and revenue.

Making everything formulas and variables

As discussed earlier, having a forecasting model which is flexible and adaptable is really important in order to map out different scenarios. Our forecasting model is based on formulas that allow us to do exactly this.

This allows us to answer questions such as:

• What if we improved the conversion rate?
• What if we frontloaded our budget?
• How would our forecast change if the client’s in-house team took control of the content copy production? Or how would it look if we split this 50/50?
• What is the difference in sessions/conversions with different levels of budget?
• What if we focused on technical SEO initially at the cost of content production?
• What would the model look like if we adjusted the confidence intervals?

What we mean here is, there are probably 10 different things a consultant needs to update manually when changing our forecast. Everything else is totally formula based. There’s no manual copy-pasting of data from one tab to another. It was pretty hard to wrap our heads around some of the array formulas we needed to use, though we were able to call upon Aira’s AI Google Sheet formula helper, ‘make me a formula’, at times for inspiration.

Presenting the forecast with confidence intervals

When presenting the results of the forecast, it’s important to clearly communicate:

1. The number we’re sharing isn’t the only possible outcome
2. What a best case scenario looks like
3. What a worst case scenario looks like

Making the upper and lower bounds on the line graph below was a challenge in itself, but suffice to say it’s all created entirely in Google Sheets. We’ll share how we did it in another post!

To wrap it up

The way that we approach SEO forecasts is a blend of historical data and estimates of how much incremental traffic we can bring based on how much of a total addressable market we are able to claim.

There are plenty of elements that play a role in forecasts and are a combination of using the existing data, adding in business intelligence and making decisions, and mapping out different scenarios about the schemes of work.

Google’s recent generative AI announcement has spun the heads of search enthusiasts over the past week, particularly businesses owners and the marketing community. Paddy, our CEO and co-founder, has recently commented on the changes and summarised the Google I/O announcement.

At Aira, we recognise the gravity of these changes and the need to change with it. SEO is being centred back to its basic principles: marketing your product and your ability to get your message across to the right audience at the right time.

We have already begun embracing this change by gravitating towards performance marketing and away from the traditional marketing approach by removing our digital PR services as they currently stand (you can read more about this change here).

As always, we are very focused on client experience, and as such we’re actively thinking about the impact that these changes could have on their businesses, how we can work better as a strategic partner, as well as serving them and growing their business.

The shift away from traditional SEO as we know it to a broader, more user-centric approach has been an expected shift Google has been leaning towards for some time. We’re excited to see where these new changes take us.

In this post, our experts at Aira have come together to discuss:

• How AI is going to change the face of performance marketing
• The changes we’re already making at Aira in light of AI

It’s become abundantly clear that change is afoot, and in all likelihood these changes will be fundamental to how businesses operate and market via search on a day-to-day basis. Not only this, but the way we operate as an agency will have to change.

Discover below how our experts are incorporating these changes and where we think the industry is headed next.

How is AI going to change the way people search?

Jasmine Lee, SEO Consultant

There’s no question that this is going to lead to huge changes in how SEOs operate. Whilst many marketers are afraid that SEO will become redundant, in my opinion as long as people are still searching for information on the web, SEO will always be around.

There are lots of ways I think AI is going to change search but here are my fundamentals:

• The domination of zero click results: Whilst a basic observation, there’s no avoiding the impact that these changes will have on click-through rates. The basic principles of targeting featured snippets will still apply since Google will be sourcing its information.  However, the importance of wider context, brand authority to speak on particular subjects and content quality will remain pivotal aspects of search strategy. Clicks will be much harder to obtain, but the information Google presents from your website has to be exciting enough to capture the attention of users enough to explore the source.
• Ultra-personalised results pages: I’m of the opinion that we’ll get to a point fairly soon where users will type in a query, and every results page presented to each user will look different. We’ve already seen location-based personalisation for some time - there’s no reason why this won’t be the case when Google will have so much information on individual user preferences and  search trends.
• Rich result importance: Finally, presenting information to Google in the most understandable and accessible way possible will be another vital consideration. I hope you like schema, because I don’t see it going away any time soon based on these changes. We’re already seeing product results using schema, and presenting your information in a prime way for Google search will only offer more opportunities.

How are SEOs at Aira using AI already?

AI is fast becoming a huge advantage for the team at Aira to automate manual tasks and free up time for strategic thinking. From an SEO perspective, we’ve already been working on AI tools that allow grouping keywords by user intent, mass image compression and auto-generation of meta titles and descriptions. These innovations save us much needed time to consult on clients and free us up to work on much higher-value tasks

I want to be clear that AI acts as an assistant and does not replace the value that SEOs can offer businesses. The human, critical thinking element of curating SEO strategy and providing proactive recommendations is something that cannot be replicated by a machine. Our role will change, but not be replaced.

How is AI going to change content marketing and distribution?

Chloe Hutchinson, Head of Content Marketing

The conversational nature of generative AI (i.e. asking follow-up questions without losing the context of initial queries) means that businesses are going to need to better understand customer personas, intent, and the moments and emotions that trigger action at a deeper level than ever before. 

To better market content effectively, understanding who target users are at this deeper level will be vital to being able to predict the questions they’ll ask Google, and where else they might sit online to acquire the answers they’re looking for. This has always been important, but moving forward it’ll be essential that this is at the heart of all content marketing.

Generative AI also means that with follow-up questions, Google will have direct access to an insight they’ve never had before: whether they’ve answered the user’s question or not. This will give them a better understanding of user engagement with the information presented. 

Therefore, the future could offer us insights that simply aren’t available now, such as how many searchers had their queries satisfied by our content - and if not, what common follow-up queries were. If this is the case, we will be able to learn more about our users so we can ‘join the conversation’ (as a brand, or on behalf of clients) - using new insights to personalise, improve, reformat and re-distribute content, to continually optimise performance.

Finally, there is a possibility that AI will change the buyer’s journey. Users in the awareness, consideration and decision stages will utilise AI to find answers and recommendations, meaning they may not even need to visit a brand website. 

This does two things. First it makes attracting target users to a website ever harder (and could decrease organic traffic), which highlights the increasing importance of content distribution, attracting users to your website from various platforms where your target users spend time. Secondly, it increases the importance of the relevance of content on a website, serving user intent and answering user queries to the fullest extent, whilst ensuring all content is optimised to Google quality rater guidelines, to be in with a higher chance of being featured at the top of the SERPs.

We are already using AI in our process to help inspire and provide starting insight for a number of steps in our content marketing process

AI can help to provide some insight into target personas. It can help by identifying most common searches, highlighting problems or pain points, providing insights into a target persona’s potential buyer journey online, and displaying spaces where target personas could sit online via existing featured content. This is taken into a target persona workshop and built upon by the content marketing and consulting team. 

When given enough context, AI can help with ideation thought starters, including types of content that have been well received in the space, types of content which might appeal to a particular target audience, and content ideas which could be used for distribution. The team can then build upon these, looking at them through a target persona lens, adding additional research, brand context and historical knowledge.  

AI can also help with inspiration for press releases, outreach emails, quotes from brands and what else might be of interest to journalists - the team don’t take the outputs directly, but use these to inspire and build upon to create the strongest approach and best quality outputs. 

How is AI going to change copywriting?

Lucy Hancock, SEO Copywriter

I’d say it’s more important than ever to have quality content on your site. Content that reflects your brand, your product or service and helps the user solve their problem. While more people will use AI to write copy, and AI can *technically* write copy, it can’t replace the skill and quality that copywriters have. I’d say tone of voice and context are going to be more vital than ever - as these are things AI struggles to master.

I think we’ll also see less mass content production, with a focus on reviewing/repurposing existing content to maintain its value. Gone are the days of publishing as many blogs as possible! Now, I think the focus will be on refreshing existing content to make it the best it can be.

How are we using AI already in our processes?

While we won’t use AI to write copy at Aira, we have been using it to support copy brief creation and also with our research. AI is great at condensing large quantities of information in a way that’s easy to digest - which is super helpful for copywriters needing to write about tricky topics! 

In the copy team, we’ve found AI works as a great research tool to help us get to grips with complicated topics (asking it to explain a topic in simple terms, for example), generate headings for copy briefs and supporting content ideation. And while it won’t replace the creative minds of our team, it can support us, and in turn, save us time that we can use to do what we love most - write.

How is AI going to change paid media?

Holly Pierce, Paid Media Strategist

AI is already a prominent part of paid media, and we can expect that as time goes on, the adoption and intelligence of AI and machine learning in paid media will continue to improve our activity in efficiency, effectiveness and personalisation. With an industry that is constantly changing with new technologies and updates, being adaptable and experimental is key to staying ahead of competition and performance, and AI is no exception to that.

I can see the continuous development of AI and machine learning changing core specific areas:

1. Ad placement and ad types: With the rise of performance max, I believe that we can expect to see new solutions incorporated into this campaign type as it grows in intelligence. I predict that eventually, this will also lead to sunsetting campaign formats such as Discovery. It will also be interesting how (and if) chatbots such as Chat GPT will be incorporated into the search engine environment, and what effect this will have on the paid advertising space.
2. Continued improvement to AI & machine learning led products: DSAs, performance max, smart shopping, broad match, bidding strategies.
3. Voice and Visual search optimisation.
4. Measurement and predictive analytics: We understand the use of predictive analytics with customer behaviour and identifying trends, but it would be great to see improvements in measurement and business impact reporting predictions.

I believe that the role of a paid media specialist will also continue to change with the rise of intelligence in AI tools, moving daily priorities into three core areas:

1. Data strategy: Ensuring a robust conversion strategy so that the data we feed into the algorithm is most accurate to optimise towards business goals.
2. Creative strategy: Generating and testing tailored creative to construct the most relevant experience to users.
3. CRO: Understanding how we can better websites and landing pages for Google to crawl for automated creative, and fabricate the most seamless user experiences to improve conversion rate.

How are we using AI already in our processes?

AI already plays a fundamental role within paid media strategy. Below are some examples of how we already utilise AI in Paid Media:

1. Ad targeting and audience layering: Google has a vast amount of audience segments generated through machine learning for attributes such as consumer behaviour, interests. We utilise these within our targeting to ensure efficiency that we are reaching the right users, but also layering over observation audiences to discover new insights about our clients ideal customer profiles.
2. Ad creation and optimisation: Using responsive ad formats and providing multiple options for Google’s algorithm to then decide which combination of creative is going to be the most relevant to each individual user.
3. Using and experimenting with Google’s solutions that utilise AI as stated above to create the most relevant solution to each individual.
4. Smart bidding and broad match keywords: Using smart bidding strategies alongside broad keywords to increase opportunity and optimise toward business objectives in real time.
5. Data management: Ensuring we are utilising 1st party data and inputting information related to business objectives back into the algorithm to give Google the ammunition it needs to optimise towards users that are most likely to become customers. 
6. Ideation and experimentation: Using AI-powered tools to discover new audiences, brainstorm new creative ideas. Tools such as Chat GPT can also be great to help with initial stages of research for new clients. 

We are continuously exploring ways to integrate AI into our work at Aira, as a tool to support our human expertise and save time on manual tasks. This leaves more headspace for critical thinking, creative strategy and improving the client experience.

It's been a couple of days since Google I/O and I've reflected a little on the key themes and points. Yesterday, I shared a bunch of thoughts, ideas and notes with the team at Aira. Below is an edited version of what I shared with them.

If you're an Aira client reading this (hi!) and would like to chat more about this, drop your account lead an email and they'd be happy to put you in touch with me. If you're a brand who are looking to stay ahead of what comes next and don't work with us yet, you can email me here to arrange a chat.

Some thoughts on the Search section of Google I/O and the potential impact on clients

Everything in this section relates to this 13 minute segment from Cathy Edwards. If you work in search and haven't watched this yet, I'd highly recommend that you do. Here are a few themes and ideas that I took from Cathy's keynote.

A clear expectation that people will change how they search

The clear highlight here was the introduction of generative AI at the top of search results. The interesting part for me was that there were more than a few references to changing how people search. Here are some examples:

• "Things that you may never have thought to ask search for before."
• "Turn to Google for things that you never thought you could."
• "Unlock new ways to search."

Google are recognising that conversational AI is different to search as we know it right now - they're trying to bring the two products together into one interface. Personally, I'm not convinced that they are compatible in the short to medium term. Is it too much of a behavioural switch? I can see behaviour changing, but very slowly.

The current design also looks a bit, clunky... particularly with the links to sources in the top right corner:

I'd expect this to change over time and be refined more.

Trusting generative AI content

One quote that stuck out to me was "People will always value the opinions of other people" - context was that no matter what AI can do, people will eventually want to know that recommendations/information etc comes from a person. I'm going to agree to a certain extent, but there are also a bunch of queries where people just want facts that aren't debatable or about opinion. So a bunch of queries are at risk of never sending traffic to websites here imo - more on this below.

There is a legitimate question on whether users will even notice that content is from AI as opposed to a human. Assuming that Google keeps marking this content as such, which they strongly implied that they would across multiple formats, I think this is less of a concern.

Thinking beyond the new feature above for a second, where it gets really interesting for me is a scenario where a website publishes AI generated content (not human at all) and that content actually does answer the query of a user who arrives from search. Should Google care that the content wasn't written by a human if the user is happy? I mean, they probably shouldn't if the user is happy, but I suspect that they will care - publicly at least. I don't know what I would do if I were Google here, thankfully, that's not my job! But it's an interesting one to think about because I think that they'll need to balance their desire to satisfy users against the fact that they can't appear to let the floodgates to AI generated content on the web open.

Google also talked about identifying "synthetic" content (specifically, images) via watermarking and metadata. Whilst focused on images, you have to figure that they are looking at all content here eventually as a way to identify AI generated content.

Interesting way to describe it too - I'm predicting that we'll see "synthetic content" added to Google Webmaster/Spam guidelines within 6-12 months.

The impact on search as a channel

Organic search is a risk for sure to some industries (a few noted below). But I still think it's too early to know what the actual impact will be - we all need to play with Bard/Generative AI search to see how it may change things. For me, I still think that AI has a huge trust issue around informational/comparative content. Facts and statistics are easy to get right, but so much of search is people going on a journey and at some point, they want to be told what to think or do by a human. I'm not sure how AI bridges that gap in organic search.

I'd be scared and thinking about how to adapt if I'm any of the following:

• A template website of any kind e.g. legal documents, HR templates, health and safety docs etc.
• StackOverflow/tech support forums.
• Pinterest or any stock image website (more on why later)
• Educational sites that don't have a USP or brand that users buy into.

In regards to paid search, it's not going anywhere and needs to grow to keep shareholders happy. I'd expect it to get more expensive at least in the medium term if generative AI is integrated more into SERPs before Google monetises it - I wonder if they will take a short term hit and show fewer ads, but CPCs will increase to offset things. I wouldn't be surprised if Google reduces the number of Ads at the top of SERPs and drives the price up.

Speaking of revenue for Google, AI as a revenue stream for Google is interesting to think about - there were lots of partners being talked about in the Cloud section of I/O in particular. I suspect that the revenue potential from API access is a drop in the ocean for Google. So I think that partners will be allowed to use AI models by Google in exchange for sending data back in the other direction to refine and help Google learn. PaLM 2 API access are examples of this I think.

I also can't help but think about the cost of integrating AI into each search. Chat GPT costs are high - Google may be able to benefit from their scale here, but obviously has a lot more searches than Microsoft. Does this scale? You'd have to assume that it does because that's what tech does, but if they also want to get more complex with what AI can do, that requires more processing power, so scale savings may get cancelled out. 

Robin also pointed out to me that this is actually part of Satya Nadella's game plan - Google taking a hit on margin on searches hurts them more than Microsoft taking the same hit. Whether this actually happens is another matter, but I think that it's definitely a challenge that Google will be addressing.

What brands should be thinking about

Firstly, don't panic. I've seen a lot of "hot takes" on LinkedIn and Twitter over the last two days and frankly, I think far too many marketers try to be the first to react to these kinds of events, rather than taking a step back and actually thinking about things. So my first piece of advice is not to be one of them.

Secondly, there is clear disruption happening and with disruption comes chaos. Fortunately, chaos and disruption lead to creativity and innovation. So once any initial panic has subsided, I'd be looking at this as an opportunity. SEO in particular has been dead for about 15 years now, we're used to it.

To make things tangible, I do think that brands need to adapt in a few ways. I'm thinking more about this at the moment, but a few initial thoughts come to mind:

• If you've lost organic impressions or traffic already because of featured snippets/answer boxes pushing you further down the SERPs, I'd expect this to get worse and plan for it. Look at the queries that are most at risk and forecast what the downside will be if this gets worse. I suspect that the queries that are already featured snippet heavy are the ones that generative AI will chip away at even more.
• If you provide any kind of content that can be seen as single answer or factual, I'd expect to lose traffic. Again, we've seen this already from Google where they're able to provide a concrete, clear answer to a question within a SERP - meaning that the user doesn't need to click through to a website. If any of your content provides answers to a question that aren't opinion, controversial and literally a fact, then I'd plan for losing traffic.
• Content at the consideration and decision stages of the buyer's journey is about to get a whole lot more important. I think that companies who invest in brand, product and content at these stages of the buyer's journey are more likely to win, even if generative AI within SERPs takes off.

The impact on ecommerce brands

The keynote had some clear examples of commercial queries, one being buying a bike. Links to more products were very prominent within the generative AI box and is built upon their existing Shopping Graph. You have to bet that they have already talked about monetising this.

I did notice on these results that key attributes of a product or retailer stood out massively. Things like discounts, deals, delivery times and return policies all stood out as a point of differentiation. One example search result was "Here are some dresses with two day delivery" - retailers need to enable Google to understand these types of USPs/attributes that they have if they want to stand out.

I think that ecommerce brands need to truly think about what makes their service or product different to everyone else and what value they add to the buyer's journey and the problems that a buyer experiences at the start and middle of that journey.

For me, this isn't new - ecommerce brands who aren't thinking about this are already behind. The fundamentals are still the same, but those who don't address those fundamentals will be left behind with these types of changes from Google.

Changes to local results

There was a brief glimpse into how local results may change with an example comparing different restaurants that a user may want to visit. The result shows three different restaurants side by side and each one had different attributes being displayed.

Like retailers, I think local businesses are going to need to give Google this kind of info to stand a chance of being here in these results.

The impact on image search

Google shared that they have partnered with Adobe Firefly which allows you to use Bard to create images on the fly using Adobe images and technology. I feel like this may have an impact on image search and copying images. You'll basically be able to create unique images for whatever you want, so going to copy them from elsewhere isn't needed as much. I'd worry if I was Pinterest or any stock photo website.

They also talked about improving search results by allowing someone to click a button that shows them more information about the image.

Highlights and further reading

Before going into the highlights and cool new products/tech that was announced. An important piece of context should be kept in mind - the vast majority of Google's revenue still comes from Ads. Sure, their stock price jumped by 5% after Google I/O, but ultimately, their long term roadmap still leads towards selling more and more Ads. So I'd advise keeping that in mind when you think about these updates and where they may lead to.

Interesting product changes and innovations related to AI

• Gmail
  • Help me write - expands on smart compose and will write an email reply for you, using details from the incoming email. You can then refine by making it longer/more formal/elaborate. Pretty nifty little feature and I think it will get used a lot. I'd be interested in how we could/should use it for prompting good replies to client emails.
• Maps
  • Immersive maps are being introduced for 15 major cities by the end of the year which allow you to preview a route before you take it. Pretty cool for walking or biking through cities. The visual demonstration was very impressive and it integrates the weather and air pollution, so you can see if it's likely to rain later when you start your walk.
• Photos
  • Magic editing is being introduced. Advanced photo editing - made me a bit sad tbh, it almost feels like too much editing e.g. changing poses and adding extensions of objects that aren't in shot or taking away clouds to make it look like a sunnier day than it was. Super cool, but I'm not sure that's what photos are about.
• Workspace new features:
  • Help me write - within Docs, you can use it to help you write whatever content you want. I think this may have a big impact on templated document websites such as legal / HR templates / employment contracts etc. The legal industry generally is at risk here I think with the less customised stuff that they do.
  • Help me organise - within Sheets, you can ask it to create a table for you with an abstract description and it will do it. Super cool.
  • Help me visualise - within Slides, you can create images from text in slides to make things more visual. You can also ask it to add speaker notes that are based on your slides. This could have a useful side feature which is to get a "summary" of your slides and see what the takeaways may be.
  • Getting prompts within Google Docs (called Sidekick)
    • They've identified that sometimes, people need help with prompts, so they have developed "Sidekick" which sits at the side of a Doc or email. It helps people continue when they get stuck with writing. For example, you get a few paragraphs into an article, need some help, but don't know how. Sidekick reads the text and gives you some prompts which you can click on and get ideas from. It occurs to me that the same tech could also be used to help someone continue their journey in search too.
  • Sidekick in Gmail - same kind of thing as above but the use case was to summarise email threads and even reference Docs/Sheets/Slides that are included in the thread. Could be mega useful for summarising long email threads with clients.
• Bard new features/integrations - it's clear that they are trying to connect Bard with more Google products. A few examples:
  • Export responses directly into Gmail, Docs and Sheets.
  • Export code to Collab and Replit.
  • Upload an image to Bard and get captions generated to describe that image - my first thought was ALT text generation en masse would be a potential use case here.
  • The presentation really focused on Bard as a standalone tool outside of search i.e. not part of Search itself (although that came later) and then a "Google it" button which allows you to go to Search if you'd like. But it feels like they aren't doubling down on Bard within Search alone - it's still going to be a standalone tool.
  • From within Bard, you can bring in other Google Products e.g. Maps. So the question is - what else can they bring into Bard?
  • They are already connecting with 3rd party apps e.g. Adobe / Redfin / Spotify / Indeed.
• Project Tailwind - scans Drive and uses the content as expertise. So you can essentially get content recommendations from AI based on your own tone/expertise/style etc.
• They are developing more tools for evaluating information and trust.
  • About this image tool - will show when similar images first appeared and were indexed. All Google generated images will have metadata to help identify it. Publishers and creators can do the same and mark them in search as AI generated. You have to bet that they are trying stuff here with other content forms (video and copy) too.
• Universal audio translator is a really cool new tool that translates audio in realtime.
  • Could open up education and learning to new territories without needing to have human translators. Videos/Podcasts etc. Only accessible to authorised partners (for now) to help prevent misuse and deep fake enablement.
• Adversarial testing is something they are developing which is designed to help find fake content/misinformation and highlight it. For example, helping dispel fake moon landings photos - the tech here is surely being used for general information/credibility too on the web too.

We’re delighted to announce that Aira has recently been welcomed as a member of the HubSpot Partner Advisory Council (PAC).

This is an exciting achievement for the agency, as it not only recognises our commitment and engagement with the HubSpot Solutions Partner Program, but also gives us the opportunity to provide valuable feedback and play an active role in improving it.

The HubSpot Partner Advisory Council is a group of handpicked HubSpot agency partners that serve as a sounding board for HubSpot's product development and growth strategies. The council meets regularly to discuss new product features, offer feedback, and share best practices. Members are chosen based on their expertise and commitment to the HubSpot platform.

Aira has been a HubSpot partner for several years, and we have a proven track record of delivering results for our clients who use HubSpot as their CRM. As a member of the PAC, Aira will have access to exclusive training and resources, as well as the opportunity to shape the future of HubSpot.

Being a part of the HubSpot Partner Advisory Council will also give us a chance to network with other industry leaders and gain insights into best practices from other successful HubSpot partners. This will enable the agency to continue to develop and improve our strategies, as well as stay ahead of the curve.

Aira's acceptance into the 2023 HubSpot Partner Advisory Council is a great achievement and testament to our expertise in HubSpot marketing. We look forward to working with HubSpot and our fellow PAC members to deliver improvements to the platform and learn from each other.

Do you ever struggle to keep up with the pace of change in the digital marketing and tech space? That's no surprise, because it's rapid - but we've got you covered.

I'm Robin, Associate Director of Strategy and Innovation at Aira, and I've been wanting to share our thoughts on industry developments, new tech and what we've been working on.

We’ve got some interesting reading to share, a tool we’ve been using at Aira, and thoughts on some of the attribution updates in GA4.

What we’ve been reading

There’s a lot of interesting stuff flying around at the moment. As you might expect a lot of it is related to Machine Learning/GPT-type stuff. This is not going to be all-ML all the time, but this time around we’ll just relax into it and share a bunch of things on that topic.

• 'You Are Not a Parrot' - great article from Intelligencer about the difference between humans and tools like Chat GPT
• Some people are bringing together lots of different LLMs (tools like Chat GPT) to perform more complex tasks. They are messy, cobbled together, and pretty imperfect, but Thomas Smith thinks that in that way they are kind of like the human brain
• Some people think that we should stop training AI systems now, so they signed an open letter calling for a halt to all AI training
• The OpenAI CEO confirming they are not working on GPT-5 and responding to that letter

What we’ve been doing

• You may have seen an announcement from Paddy about Aira’s new approach to content distribution. It might seem like a big shift from the outside, particularly for people who have always known Aira’s Digital PR prowess, but it’s actually a continuation of something we’ve been doing internally for quite some time.
• We shared a tool we’ve been using to generate Title Tags and Meta Descriptions to get past the initial “blank page” stage. That Twitter thread also includes some of Aira’s policies on the role of ML tools in our work.
• Our Paid Media team bagged the UK Paid Media award for best use of Facebook and Instagram ads, and Holly Pierce, one of our Paid Media Consultants won a rising star award.

What we’ve been thinking - GA4 changes and attribution

On 6th April, Ginny Marvin (Google Ads liaison) announced that first-click, linear, position-based and time decay attribution models are being removed from Google Ads and GA4.

Unsurprisingly, this set off a fresh wave of consternation from marketers about having to rely on GA4 come July (seriously, if you haven’t got it set up by now, you need to get cracking).

It’s worth bearing in mind a couple things about this.

GA4 comes with auto BigQuery exports

You would have had to pay hundreds of thousands of pounds for this with UA. If you want, you can use that granular data to recreate your favourite attribution models for comparison.

I strongly recommend switching on the BigQuery exports if you haven’t already, if only because it’ll give you ongoing granular data access stretching back more than the 14 month limit that GA4 imposes. Even if you don’t think you’ll personally be digging into historic data that much, if you’re thinking of doing any impact modelling or forecasting in the future using tools like Prophet or Causal Impact, you’ll want 24 months worth of data at least.

As Google’s Ads Liaison points out, you can also use explorations to investigate user journeys

This isn’t quite the same as having a model baked in from the start that you can easily flick to and see how different channels are performing. You’ll have to dig to get your answers and, to be honest, I think that’s part of the point.

Google can’t have their free analytics tool eagerly disagreeing with their own ads

As we’re all keenly aware, attribution is almost never a straightforward conversation. For something so ‘mathsy’ there are a lot of opinions that fly around - and it’s only getting harder with cookie changes. On the one hand, cutting down support for models probably makes life easier for Google engineers/processing costs. On the other hand, it almost definitely reduces the scenarios where PPC teams are having their impact questioned by other teams or senior stakeholders who have been flicking between the models available in GA.

I don’t think it’s a coincidence that these models are being removed from Google Ads and GA4 at the same time. I also don’t think we need to be wearing too big a tinfoil hat to remark on the fact that the three models that are sticking around (Last Click, Ads-Preferred Last Click, and Data Driven) are either the easiest to measure, the most likely to make ads look good, or the hardest to pick apart.

So, maybe you’re thinking: ‘What should I do about attribution now?’

It may well not be the first time you’ve thought this, what with the aforementioned cookie stuff, Safari’s ever-tightening grip on tracking, growing ad blocker usage, GDPR etc. etc.

There’s also companies like Uber saying they turned off 80% of their ads and saw no impact, articles suggesting that attribution-based analytics is a scam, and a growing buzz from big tech companies like Facebook about how we need to stop “attributing” and start “modelling”.

As you can imagine, these questions and answers are very important to us at Aira. We’re not interested in how to make analytics numbers look good - our focus is business impact. So doing a bunch of activity that just takes credit for conversions that would have happened anyway is not the one.

The problem with user-tracking approaches

If you’re using tools like GA or ad pixels; click tracking, cookies, and fingerprinting all rely on following people every step of the way.

They assume that every conversion is due to something they have recorded (or some combination of things). Because they are so myopically focused on individual user journeys they are naturally bad at spotting broader patterns. They are less likely to pick up when conversions would happen anyway. So, they can split the numbers up for you and give you an idea of what’s working, but they can’t really give you an answer to the question “what did this get me that I wouldn’t have got anyway?”

The problem with maths-based approaches

Tools like Causal Impact, Robyn, and Uber Orbit look at historic data to try to gauge what the actual impact of activity is. Essentially - they try to understand the patterns of your business so well that they can say “when you changed x, shortly afterwards sales were higher than we’d expect, so we think x is responsible”. As a result - they need lots of data because of how well they need to understand those patterns to spot when something is unusual.

That means it can take a while to see what the true results of activity are. It’s pretty time-intensive to pull the data and it’s almost impossible to use these tools to inform granular decision making (like whether a headline is a good one to use).

The trick is to use both user-tracking and maths-based approaches, but for different things

Understandably, no one wants to run the risk of investing heavily in something that actually doesn’t have any impact, but at the same time we can’t spend all our time trying in vain to measure the value of small pieces of activity which we’re pretty sure are a good idea anyway.

Often the right answer with small-scale tactical stuff is relatively easy to spot. If we optimise a page and we start ranking better for our target keywords, that’s probably a good thing. If we start getting more traffic and that traffic is converting, that’s probably a good thing.

It’s usually the larger-scale decisions that are harder to validate. Should we be spending on brand advertising? Is top-of-funnel activity bringing us revenue further down the line?

We probably won’t change our attitude to top-of-funnel each week, but we could well be changing our headlines that fast. So, standard user-tracking probably gives us most of what we need for the small scale optimisations. Maybe we don’t have easy access to first-click models in GA any more, but we can probably use things like user signals to get an idea of if the traffic we’re bringing onto the site seems engaged. At the same time - we can try to measure our bigger investments, and strategies with some of the more maths-based approaches. When it comes to making decisions about bigger investments - we’re more likely to have long-term data, and more likely to have the time to do this kind of analysis. Aside from anything else, we’d be talking about a quarterly commitment rather than a daily one!

As ever, the last piece of the puzzle is for us all to accept that whatever measurement we choose it will almost always be wrong. While we can try our best to make it as accurate as possible, the goal is not to understand the ultimate ROI of every single small thing we do. We can put sensible measurements in place to avoid making silly decisions, but we’re always going to be doing a whole bunch of things at the same time anyway. If our whole plan relies on us just finding the one perfect change that will bring us business success, we’re already in trouble!

Thanks for reading

I hope you enjoyed this combined reading-list-and-ramble! We’re going to try to do more of these in future so if you particularly liked (or loathed) any parts of this please do let us know!

tl;dr: from June onwards, Aira will no longer be offering digital PR services to our clients and instead, will shift our value proposition closer to being a performance marketing agency. Unfortunately, this means that some of our amazing creative and digital PR team will be looking for new roles - please drop me an email if you are hiring and would like to chat with them.

What got us here, won’t get us there

Ever since hearing this phrase back in 2018 at a founders dinner, it’s really stuck with me. It made me understand that the journey a company takes will naturally evolve and change over time. The way you do things and what works at one point in time, may not work at another point in time. Sometimes, change is easy and sometimes, change is really, really hard.

Right now, it’s the latter. The core services that have gotten Aira to this point are not the ones that will get us to the next stage of our journey.

Our creative and digital PR services have been a core service of Aira since day one. We’ve delivered amazing campaigns for clients, grown their businesses as a result and shared our experience with the industry.

It’s now time for the next phase of Aira’s journey and unfortunately, that means that I’ve made the hard decision to remove our creative and digital PR services as of 1st June 2023. This means that five of our team will be leaving us and looking for new opportunities. 

We’ve done our best to look after them financially, emotionally and in finding new opportunities. But there is no getting away from the fact that people who have worked hard for us and delivered great work are now losing their jobs. 

If you are hiring creative and digital PR roles, please drop me an email and I’d be happy to introduce the team and open up conversations. 

Does this mean that you don’t believe in links and digital PR anymore?

No, it doesn’t mean that. We’ve been delivering digital PR services and building links for clients since 2015 and I’ve been doing it since 2010. I still see a lot of value in it and would recommend companies such as Builtvisible and NeoMam who do a very good job of it. If I didn’t believe in it, we’d have stopped it long ago and I wouldn’t recommend it to businesses at all. 

It just doesn’t fit with the direction that I now want to take Aira in. I’ll share more on what this direction looks like shortly.

Whilst very different services, we made similar decisions with web development and organic social media over the years when they didn't fit with the direction we wanted to go in. 

Links can still drive rankings in competitive search results and we’re not blind to that. For Aira moving forward, links are almost certainly going to be built (either via outreach or naturally), but they won’t be the primary reason the content that we create exists. Because of this change of focus, we’ll be approaching the work in a different, more holistic way, one that we feel is a much better fit for Aira and our clients. 

Did finances play a part in this decision?

Yes, it did. I won’t try to hide that. 

Whilst Aira is financially sound, we had a tough end to 2022 and a slower start in 2023, particularly in the creative and digital PR team. We lost some clients for a variety of reasons and didn’t have the sales pipeline to replace them.

This led to some financial losses within the creative and digital PR team that we were prepared to carry, but looking ahead into the rest of 2023, these losses would mount up and given the current economic climate, we’re not able to confidently predict when those losses may turn around. We are fortunate to be in a strong enough financial position to carry losses in one team for a period of time, but it would be irresponsible of me to do that when we don’t know how long that period will last.

I’ve spoken with some close friends and colleagues who run other agencies and technology businesses, nearly all of them are finding things hard right now. If you are an agency founder, CEO or director and would like to talk about things, I can’t promise answers but I’m more than happy to listen because things are hard right now, so please get in touch. 

Whilst finances did play a part, the change in direction is something that has been on my mind for a while now and this change has probably been accelerated as a result. At the same time, I’d rather this change have not come about in this way.

The direction we’re taking

The direction we’re taking isn’t completely new to us, but when you remove a service as big as creative and digital PR, it’s going to feel very different. Aira will feel different moving forward and I’m looking forward to that journey and seeing where our team can take us. 

In summary, our core services will span:

• SEO
• Paid Media
• Content Marketing
• Marketing Automation

These services will be underpinned by our Client Services team. 

We’ve created content for clients for many years and will continue to.

The key change we’ve made when it comes to content is that we’ll no longer be producing content primarily for the purpose of generating links. Our services have evolved over the years and we’ve been able to produce content that serves multiple purposes, but the focus and expectation from clients was nearly always the same - generate links. If a content piece generates lots of great traffic or even some conversions, but didn’t hit a link target, some clients wouldn’t have seen this as a win. 

In some situations, we’d struggle to even get access to Google Analytics or Search Console to allow us to assess the impact of the links we’ve built. This doesn’t fit with the world that I want Aira to operate within which is neatly summarised by this snippet from our homepage:

“Aira grows your businesses with multi-channel digital marketing that's measured in sales and revenue.”

Instead of a focus on content that only generates links, we’re flipping things around and the focus of any content that we create moving forward will be to generate:

• Traffic
• Leads
• Revenue

Yes, links are almost certainly going to be built (either via outreach or naturally), but they won’t be the primary reason that the content was created. 

The reason we’re doing this is because we want to focus our efforts on producing content that does two core things:

• It sits far closer to the bottom line commercial metrics of our clients. 
• It sits on the buyer’s journey of our clients' target audience.

This isn’t new for Aira. We’ve actually been quietly doing this for the last couple of years and our copywriting team works incredibly closely with our SEO team to produce content that drives traffic, leads and revenue. 

We are going to do more of this. The results for clients are clear and we’re able to demonstrate our impact on their top and bottom line. 

I’ll be writing and sharing more about this in the coming weeks and months. Right now, my focus is on supporting the team at Aira and making their transition to new roles as smooth as possible.

Why write about this?

Writing a blog post about removing a whole team and telling people that they no longer have jobs isn’t something that I’ve ever wanted to do.

I’ll be honest: a big part of me didn’t want to write this post. Agencies (and companies generally) make these types of changes all the time but don’t necessarily write about it.

But taking ownership of decisions is really, really important to me. Even more so since I became CEO of Aira last year and whilst this decision was discussed and debated within the board and leadership teams, it’s ultimately my call and I’m accountable for it.

Even more important to me is looking after our team and doing our best by them, even when this means making hard decisions that affect them. By writing about this openly, it’s far easier to help them find new roles and if this post can help just one of them find a dream role, it’s worth it.

Finally, to our team who are reading this and have been impacted - thank you for the great work you've done for clients and for understanding the new journey that we're embarking on. We wouldn't have gotten here without you and wish each of you the best for the future. For the rest of the Aira team, thank you for the support that you’ve shown over the last couple of weeks whilst we’re going through these changes and move forward in a new, exciting direction.