Due to the interest of companies in scalable techniques, we decided to further focus the research project on testing AI models for eye tracking. This was done in two steps to answer two questions:

Is predictive eye tracking comparable to eye tracking with real participants?

What is the evaluation of predictive eye tracking in A/B testing?
1. Is predictive eye tracking comparable to eye tracking in which real participants participate?
In the first step, we analyzed the eye tracking responses to the videos from the previous study. Using two country wise email marketing list providers of predictive AI models: Neurons and Brainsight. Although these providers use different metrics, they both have algorithms trained on a large and specific dataset to predict what people might be looking at.

Also read: Eye tracking, EEG & more: 4 neuromarketing methods to apply

For example, they offer heat maps and other metrics, such as ‘ Clarity ‘. This indicates how easy it is for viewers to scan the most important information in an image. The goal was to compare the results of these providers with those of traditional eye tracking with real participants. This to antarctica business directory whether the use of AI models performs just as well.

When comparing the results, it appears that they are in line with the data collected by traditional eye analysis of competitors on marketplaces with real participants. However, biases do occur when using AI models. Below we discuss the three most important biases that we have encountered.

First, the AI ​​models predict that attention will be drawn more to the brand logo or name, while real participants would also notice other elements.Heatmap comparison AI model and real participants

There is also a bias towards faces. As can be seen in the following photos, the heatmap of AI models is focused on the faces of the people in the video. But real people also notice other elements.heatmap comparison looking at faces AI model and participants.