With Women’s history month coming to an end, let’s dive into the second installment of the Women that shape research (and us) series. This time around, our top experts and impressive women selected breakthroughs about buying behavior that define the current moment.
Instagram done right
Testing in replicated environments is becoming the new standard for breaking down authentic consumer behavior; especially the complex and often elusive link between scrolling and buying. A validation study that was just completed set out to compare how consumers act in recreated Instagram feeds and reels for testing versus the actual Instagram app – here’s what we found.
Here’s an overview of other top findings:
Positioning matters: Ads that show up in the first 12 posts on the feed have up to 50% more visibility.
Visibility is not the same as memorability: Lower brand recall (29%) occurs even with the visibility is as high as 70%
Long ads are not Insta-friendly: You can lose ~85% of your audience in less than 5s
Social buying pushes the market research to do better
The social apps in China evolved to encompass all aspects of the consumer journey, including services such as delivery & in-app supermarket services, and retail search engines; they are an integral part of not only every facet of shopping, but everyday life.
Given the proliferation of e/social commerce, clients are looking to test how their concepts fare in the context of very particular platforms. For example, assessing the specificity of TikTok formats and developing platform-specific best practice gives you a clear competitive edge.
How much freedom is too much?
The crisis of recent years really brought home how resilient, flexible, tough, and above all adaptive we all are – just look at the evolution of online services.
Research by Global Web Index reveals that 1 in 5 internet users across 20 markets will be looking for more flexible payment options in the coming months – everything from free cancelations to refundable options improves shopping experience and potentially increases turnover. The key challenge for brands now is to strike the right balance with flexibility, and not overwhelm consumers with choice in order to discourage final cart dropout.
Make sure to check out the first installment of the series where top talent from Mexico shared their insights!
By Milica Kovac, New Business Development Manager at EyeSee, Researcher and former Senior Product Manager
Facing high inflation, most decision makers in market research are trying to find alternatives for quick savings. For example, AI-based visual prediction models promise to eliminate the need for eye-trackers as they give faster and more affordable results; and supposedly – just as good.
Let’s examine if this is really the case.
BTS of human gaze analyses
While both AI predictive algorithms and eye trackers seek to provide human gaze estimations and help us understand attention and visibility KPIs, they operate fundamentally differently.
Regular eye trackers rely on the data obtained from mapping the respondents’ eye gaze, while saliency-based AI solutions predict behavior based on the audio-visual features of the stimuli gazed at, relying on insights from cognitive science – what we know about how humans usually perceive things. In essence, this means that regular eye trackers deliver an answer to what is seen, while AI models suggest what is probable to be seen.
Consequently, eye trackers can chart the variance in behavior of different target groups inspecting stimuli, while prediction algorithms showcase the probability of what is seen by an average human. This means that if your study is looking at an average population, or you are looking for a simple reality check of early development concepts – AI might be good enough for the job. For all other cases, validation or full application of eye trackers is still advised.
Scientific and practical gaps
When talking to an AI vendor, it’s important to ask about the timeframe for which their model predicts visibility. Does it predict what’s most likely to be seen on a product packaging or a webpage at first glance, or does it predict visibility after the user has browsed for some time? You may be surprised by the variety of answers aka absence of any standard in the AI field, as well as by the inconsistency of some models with what we know from cognitive psychology about human memory.
Some AI solutions predict intuitive attention and visibility in the first 150 – 250ms. According to the Atkinson-Shiffrin memory model, when we see something, the entire information registered by our eyes is first stored in our sensory memory. This is a very short-term storage that only lasts for about 250 milliseconds, during which time the information is not yet processed in any way. Only when the information passes into the working memory, under the effect of selective attention, is the limited information about the stimuli being processed but for no longer than 15 seconds (with the average human attention span tending to decrease towards 8 seconds). Eye-tracking devices usually capture attention ranging from 3 to 7 seconds, coinciding with the duration of information processing. Going beyond theory, even from a practical perspective, is it really useful to know what can be observed on a website within a duration of 150-250 milliseconds?
Saliency is (still) mostly context-unaware
To fully understand the power and limits of the AI approach, my team recently completed a validation study of saliency-based algorithm for predictive eye tracking. We selected a number of stimuli typically tested in consumer research studies across industries and channels: from vertical and horizontal packaging stimuli to shelf images and webpages. We compared the results obtained by two different AI models available and popular on the research market with the results obtained using eye-trackers on human respondents.
What we’ve found is that saliency models are consistently under-predicting semantically important image regions; in some cases, they failed to catch the importance of a brand name on a pack aka failed to determine that those are not just any letters written in certain color, font and size.
What’s more, different models tend to favor different properties such as text, colors, faces, and others. Knowing that helps identify a model’s deficiency and choose an appropriate model for a specific application. For example, some models are better at capturing text area, while in some others, the sound is not considered. Further, different algorithms might not be trained on a certain type of stimuli, which could undermine findings for an entire category.
While this might get better with time, the overall conclusion is that more complex (full shelves, e-commerce websites) and dynamic (video ads) stimuli prove to be way too challenging for AI predictive algorithms as they are still incapable of contextual interpretation. They inspect the size and contrast, not the content; and in doing so, they often fail to capture the meaning. Knowing just how much meaning we attach to brands, letting AI conclude that it is looking at a purple cow feels stripped of all the meaning we attach to a brand like Milka.
An excerpt from a recent study published by the Institute of Electrical and Electronics Engineers provides an additional point of comparison between prediction algorithms and real eye-tracking.
Three different algorithms were used to predict what humans would look at while watching soccer players in colorful jerseys practicing with a football. The first algorithm picked up the colored regions as the most significant points, while the other two algorithms were concentrating on the players’ faces. Both underlying assumptions are justified from a cognitive science point of view: colors (especially red), and faces do grab people’s attention. However, true eye-tracking data showed that people were looking at the ball during soccer match, because they understand the meaning behind this game.
Conclusion
So, what’s the verdict on AI in this case? We’ve previously established that not all AI predictive models are created equal; they process and favor different properties. Keep this in mind, when selecting for a solution – you might find yourself short of one single perfect algorithm; in reality, you’ll have to choose every time you conduct a study.
However, this does not erase the fact that predictive algorithms are more scalable than full eye trackers. It is possible to imagine a scenario where a single application gathers data about both the user and the stimuli. By leveraging the complementary nature of subjective human eye-tracking and objective graph-based visual saliency modelling data, such solution would ultimately lead to a more reliable and efficient output. Until then – real eye tracking is still supreme when faced with complex questions that require nuanced insights.
Interested in application of behavioral methods? Check out our previous blog on measuring attention!
At EyeSee, women add up to 71% of all insights and data researchers; roughly 8out of 12 Directors are in fact women who define every facet of our agency. It is not an exaggeration to say that having this perspective uniquely influences how we tackle clients’ needs, deliver results and lead in consumer behavior insights. Therefore, we take Women’s month (as well as any opportunity) to reflect, acknowledge and celebrate women who shaped research and us.
First off, we checked in with our team based in Mexico City regarding their thoughts on consumer insights and the state of market research industry.
Are we doing femvertising right?
When asked what sort of patterns distinguish advertising of today, Daniela Blanco, Senior Insights manager at EyeSee had this to say:
Daniela observed that women aged 25 to 50 in Mexico do not feel represented in advertising, and they consider that brands do not represent gender equality. With femvertising, brands can better connect with female consumers, but above all, empowering, encouraging and strengthening women; which also benefits men and society in general.
In the same way, it was shown that there is a positive influence on the perception of Corporate Social Responsibility (CSR) of brands that use messages of empowerment of women, several studies have shown that this type of advertising improves the self-esteem of girls and adolescents, even in patriarchal and collectivist cultures.
What is the key challenge with consumers of today?
The consumer insight that is key to understand the behavior of the new generations is Average Attention Time, argues Yael Moctezuma, EyeSee’s Junior Data Analyst. She explained:
Environments such as social media pose additional challenges when it comes to creating a successful video ad. Ferociously fast-moving timelines have brought on the need for marketers to become excellent managers of attention. Consequently, attention metrics come into play as the strongest indicator of success: being three times more predictive than viewability, attention metrics inform marketers about how much of the video content will actually be seen.
Is the future female?
As you might have discerned by now, Mexican team is comprised of outstanding female influences that inspire us daily. One of which is Alexandra Mar, EyeSee’s Insights manager whose previous experiences cover health, finance, and EdTech sectors. She took this opportunity to reflected on employment gaps and imbalances, and outline reasons to curb optimism:
The impact is felt across industries including market research, claims Alexandra. If the future were indeed to include a more balanced female presence in the industry, the first step is to ensure empowerment through knowledge and training.
Incidentally, our Mexico Country Lead & Insights Director Diego Adolfo Chávez Terrazas just joined the impressive list of Women in research mentors, organization that works tirelessly to advance position and amplify voices of women in the industry. He echoed Alexandra’s concerns and added a very personal take:
Interested in this topic? Check out our #FollowInsight article inspired by Women’s month.
2023 is around the corner and the pressure is tangible: so, how do you best adjust for the recession? While predicting the future is never an easy task, we’re firm believers that there’s no better way to brace yourself than to turn to behavioral know-how. Some of our top experts across departments and regions gathered to share:
Insights, trends, and opportunities in shifting consumer behavior
How to prioritize initiatives and what to avoid as a competitive brand
Ways the MR industry is adapting to be more predictive and meet the needs of clients
We hope these perspectives serve as an inspiration to think beyond obvious challenges.
1. Drive actions with insight, not fear
During a crisis, when trends form and change much faster than usual, it is even more critical to both measure and launch new products that fit the needs of the consumer. With a steeper trend growth, it is essential to try harder to understand the current trends as the client’s needs are also developing faster. This means that the delta between the client’s requirement and the product offering is becoming even more significant – thus, the chance of switching brands grows higher if these needs are not fulfilled. Highly volatile environments (such as the recession) have much steeper trend curves – when that is taking place, it is imperative to monitor them with more research rather than stepping back until things settle.
2. Get to know the new kid on the block: 2023 Consumer
All the new pressures of this crisis have led to similar challenges brands had to make two years ago – shortages, supply chain issues, and, consequently, prioritization of product distribution. Due to this, brands had to make complex decisions in terms of trimming their portfolio, reducing pack sizes and counts, or shifting pricing at the same time. Relying on past data is simply not an option now when pricing sensitivity is fluctuating and consumer confidence is unstable. Although previous experiences with different recession periods showed us the various consumer reactions across categories – it is brands’ reactions and choices that are also changing the market landscape.
3. Avert switching through quality and exclusivity
Even when high inflationary pressures do not affect the everyday life of consumers, the biggest challenge brands must deal with is remaining competitive – especially with the growing penetration of private label brands. With the appealing prices combined with the on-par quality of shopper-favorite products, private label packs have been making their way into consumer carts more and more over the last years.
4. Consumers seek to treat themselves under pressure
But, do consumers recognize your product as indulging? Your pack and claims need to be tested on their shelf performance as 9 out of 10 packs are ineffective and don’t produce sales impact.
5. Blur the lines between online and brick-to-mortar
As gas prices reach record highs, so do the concerns about the cost of daily lives. The complex global environment is bound to have major effects on established shopping practices and the functions of touchpoints.
6. Tune your omnichannel voice
A smooth and seamless experience across touchpoints is now fully expected by consumers. Their standards are changing – and brands must keep in mind the hyper-sensitivity of their customers. Research shows that brand loyalties are the first to go as we adjust to the mounting pressures of the global recession.
7. Ride the wave of cashless payment and delivery alternatives
Driving value and meaningful connections across the Customer Experience is the top priority for many brands going into every new year – but what to expect in 2023? The key challenge will be finding just the right balance between the overall (and optimized) consumer journey and areas where you should step up on personalization to really bring that added value home. The truth is that the perception of what is valuable goes beyond price and is massively influenced by context; therefore, rethink and treat all in-store touchpoints as an opportunity.
8. Use videos… responsibly
Further, a clear-cut way to gain these learnings is by testing the video content in the right environment – be it YouTube, Meta, TikTok or any other platform.
Tools such as simulated social media feeds allow complete control over the testing environment and allow you to get more in-depth data on both engagement and brand impact.
9. Rethink research processes and data collection
The MR industry has massively transformed over the last 10-20 years in a way that alternatives are available at every turn – our team, for example, always finds ways to mix and match new methods and frameworks to meet the research questions and challenges.
10. Team up in crisis
The journey of successful co-branding begins with understanding the intersection of consumers and their behaviors. Pre-testing your advertising materials (online videos, TVC, social media posts, etc.) and packs can give you crucial insight into how consumers will see, react, evaluate, and if they would ultimately be inspired to purchase your co-branded product.
A mixed-method approach, where behavioral methods of eye tracking, facial coding and virtual shopping are combined with surveys, can measure such preferences with as much as an 80% correlation with actual shopping behavior.
Interested in more resources to help you navigate 2023? We’ve got you! Check out this selection of 10 recent behavioral studies.
Amongst the many disruptors the markets across the world have felt over the last few years, the UK government introduced new measures on food High in Fat, Salt, and Sugar (HFSS food) – putting in place restrictions and rules on the placement and promotion in both in-store and online ‘impulse’ locations.
What will this change for FMCG brands going forward? And more importantly, how can you not only prepare for but operate within this shift? To help brands brace and adapt to the various adjustments in their business, we tackled how brands can:
Purchase trigger points can be in unexpected places
In an effort to fight unhealthy dietary habits, HFSS food has been restricted from aisle ends, store entrances, and checkouts in brick and mortar across the UK. While these locations may be prominent – they are not the end-all-be-all for product placement. Since 80% of shopper purchase decisions are made subconsciously, understanding their decision-making process is an intricate science. Placing items in highly visible areas to trigger that impulse urge was the obvious go-to – but what can your brand do now when these trusty locations are no longer an option?
For one, have more faith (but also reliable insights) in shoppers’ intuition and logic – employ a flexible and agile research approach that allows you to test in virtual yet realistic shopping environments. Then, by leveraging them, you can map out the entire consumer decision-making process and the locations shoppers naturally gravitate toward to find your category/product with Behavioral Decision Trees.
They pinpoint the reasons behind particular product selections, behavior switches, trade-offs, and sources of loyalty, all while evaluating the overall shopping experiences – and ultimately help you understand how to assist their journey in the changed store landscape. The same Decision Tree tech can be used for testing in digital environments by recreating e-commerce shopping platforms and assessing the online consumer journey – as the placement restrictions will also apply to online equivalents of in-store spots and anything from entry and payment pages, landing pages for other categories, shopping baskets, and pop-ups will be off-limits for HFSS food products. Ultimately, by using Decision trees that leverage virtual shopping, you boost the chances of not missing out on the crucial triggers and touchpoints by 40%.
It’s time to go beyond product-based advertising
Come January, further restrictions will be in force – bans for HFSS food advertising on TV and restrictions on paid-for online advertising before a 9pm watershed. The advertising landscape is already highly competitive, especially in the social media domain, as we know that consumers scroll through their feeds at the rapid speed of 1-3 posts per second. So, a change like this means that marketers now have to consider a different approach to creating campaigns – perhaps indicating that re-adjusting the focus on the brand itself instead of the product and translating it into engaging ads is one such strategy.
Past data taught us that one of the most effective ways to boost purchase intent is to show both brand and product in an ad – so, making the transition to reduce or put a halt on product-centric marketing seems tricky if not executed correctly. A safe way to make sure consumers still resonate with your social media ads and TV commercials and opt for your products (even without showing them) is to test them in a controlled environment that feels as close to the real thing as possible.
With a proprietary testing solution and research methods, we have replicated feeds of all major social media platforms to test any ad type and format in the space it would naturally be seen in – and tap into the actual performance and sales potential.
Methods like Facial Coding are 2x better at predicting the viral potential of videos than any combination of survey questions – enabling a full-scope understanding of what works and what doesn’t, what can be tweaked and what about your brand grasps viewers’ attention – which in turn, will help you gain a competitive edge and fuel further differentiation between your brand and others.
For some categories, HFSS bans are a game-changer
While HFSS bans impose challenges on many categories and brands, we have seen that they simultaneously open up new possibilities for others. For example, when it comes to the store environments, the once HFSS-designated in-store spots and displays have now been filling up with other products like alcoholic beverages, cleaning products, and soft drinks.
Then there are brands like PepsiCo’s Quaker Oats, Pringles, and Mondelēz International, who saw this as an opportunity to embrace innovation and create a new and HFSS-compliant range of products that would still satisfy the same consumer need as its HFSS predecessors.
Inflation has already caused major shifts in how consumers choose to spend their money – and even without the new restrictions, many brands have embraced new product development and opted to rethink their portfolios. However, as a rule, innovation can be risky (more than +80% of new products fail), but volumetrics and market share projection can empower your NPD process by estimating the success of any new product launch. In fact, there are a few levels of studies that utilize the virtual shopping solution (that shares a 0.8 correlation with real shopping behavior) and behavioral methods to ensure the risk of an unsuccessful launch is significantly minimized by:
Screening product concepts to identify the most promising ones
Gaining the learnings to optimize the concepts for further development
Validating the optimal concepts and evaluating their future sales potential
Summary
As with any change that comes, there are those who embrace it and adapt – and those who fall short. The HFSS restrictions in the UK are no different – they present a sea of opportunities and possibilities to rethink and develop innovation and rekindle the relationship with your consumers for those who are interested in winning.
Relying on a behavioral research approach to guide you during these transforming times will equip you with the predictive learnings needed to make these sound decisions – and reduce the risks that come with the inevitable shifts in the market.
By 
