How Image Recognition Classification Method Can Help Lift Brand Creative Standards

Machine learning modelling is known for predicting performance of marketing activities, however, this is a story of how we developed an image classification model that predicts the performance of Instagram advertisements and provides an opportunity to uplift creative standards. “Will consumers engage with this creative element?”, “and to what extent is the emotional connect?” were the questions in the minds of our researchers?

We selected a tea brand's Instagram image adverts for this research. And we felt that there was scope for improving the engagement rate (viz. likes, comments and saves) of Insta adverts. We set three research objectives: 1) To identify high performing Insta adverts. 2) To build a profile of high performing campaign elements. 3) To explore building a database of creative campaigns, especially those that have an emotional content. This brand would execute different type of campaigns – festive, new product launch, new offer, sales offer etc. Our initial scan showed that the engagement rates varied significantly between different campaigns.

We developed a 3 Step C-P-M Framework or simply known as Classification-Prediction-Measurement Framework.

In the 1st stage of classification, historical Insta adverts dating back to 2018 and 2019 were classified using natural language processing methods and image recognition methods. Three classes viz. High Performers, Medium Performers & Negative Performers were formed based on factors like a presence of a primary image, headline text, number of likes, offer prominence etc.

In the 2nd stage, new Insta adverts were checked against i) the above classes and ii) automated eye tracking model. Prediction scores revealed the class to which the new Insta advert would be tagged. This framework allows creative time to revise the new adverts.

In the 3rd stage, upon release of Insta adverts, the performance key performance variables like no. of likes/shares are correlated with in-store KPI viz. average sales per square foot in order to understand the impact of lift on in-store KPI.

Also, due to application of automated eye tracking and machine learning models client teams are able to detect creative concepts that has maximum emotional impact on consumer emotions. This enables in lifting of creative standards in what we term it as ‘Creative Idea Leapfrogging’.

Traditional Research Methods and Neuromarketing – The Perfect Marriage Powered by Machine Learning

Most current articles relating to market research would highlight so much on behavioral insights with the thought that the use of traditional surveys and focus groups seem outdated. However, our view is that traditional research methodologies do have its own merit and when used correctly, provides a context to modern research methods like #neuromarketing.

The truth is, marrying traditional research and #neuromarketing delivers rich and actionable customer or business insights. This happens when there is merging of survey data with biometric data that is generated from neuromarketing. #machinelearning algorithms that drive neuromarketing can process millions of records and in this case algorithms can model small yet divergent data with ease. The net result is that models are robust and results are highly reliable.

Along with the robustness of the results, understanding the context surrounding the research findings is important. One of the often quoted limitation of #neuroscience research is finding answers to ‘why’. Measurement of brain waves doesn’t answer all questions pertaining to ‘why’ and is not a sufficient condition.

This is where traditional surveys and human analysis come in handy. Insight professionals can connect the dots of data that isn’t associated with emotions with those requiring explicit answers or those questions which requires human comments.

At the other end of the spectrum, results traditional surveys alone cannot be held as conclusive evidence due to the bias factor and usually entails depth analysis. When the usual questions of awareness, likes and dislikes come up, #neuroscience plays a crucial role.

Answers to #neuroscience questions are devoid of bias and is a great way to examine how a stimulus elicits emotions when being exposed. It can even tell exactly what kind of emotional response your subject has disclosed. This precision factor is an added value as it aids in the understanding of the impact consumer decision.

The point is there is a misconception that, with the advent of cutting-edge research methods, traditional survey methods should be disregarded. This need not be the case. Instead of substituting one research method over the other, both should be utilized hand-in-hand.

Researchers need to leverage the benefits of both methodologies and underlying #machinelearning models to complement each other’s setback. At Stratzie, we have noted the significance of both roles as a crucial necessity to having a holistic result, especially in today’s data rich world.

Adding 'E' Quotient to Brand Measurement

With the influx of brands kick-starting daily along with all the existing brands striving to remain relevant in their respective industry, marketing has never been more competitive than ever today.

The digital and technological world has advanced, so has the tools and methodologies of research, delving deeper into the consumers’ sub-conscious level. Stratzie has developed an innovative brand tracking measure, utilising #neuromarketing methods on top of traditional methods of research.

To clarify exactly what Stratzie DBE Index is, why it is needed and how it benefits brands in the market, our Master Storyteller Siti Wajihah has developed a concise Q&A. It's all about adding 'E' or 'Emotional' quotient to brand measurement.

Q: So, what exactly is #StratzieDBEIndex?

Waji:That’s a good question to begin with. It is a single measure that tracks consumers’ emotional impact on the brand. It stands for Stratzie Digital Brand Engagement Index. This measure is a combination of #neuromarketing (e.g. #facialcoding, #EEG, #fMRIetc.) and traditional survey KPIs.

Q: Why now the talk of consumers’ emotional connection with brands?

Waji:This is the digital and social age. And content is the key driver in customer communications. In that respect, how do you measure the depth of #customerliking With the advent of #neuromarketingmethods, there’s a big opportunity for the brands to measure the depth of customer emotion.

Q: How is it effective for different client brands?

Waji:The innovation is that you don’t need a large sample size to conduct brand measurement studies. Yet, the samples are sufficient enough for extrapolation of findings that in turn can be representative of the population at large. And this is due to the advancements in machine learning and #artificialintelligence algorithms.

Q: What kind of outputs can brand marketers expect?

Waji:Firstly, there’s a single measurement for brands as per category, country, region etc. It takes into account the data from #neuroscience and traditional surveys. In addition, there are biometric outputs like heatmaps, correlation maps etc.

Q: Who can participate in this tracking study?

Waji: Any brand, big or small, can participate in this study.

Q: Pricing-wise, what is the cost in order for a brand to participate in this study?

Waji: The study is customised for each participating brand and therefore the costs vary. Please send inquiries to info@stratzie.com and we will respond swiftly.