Artificial intelligence
A system based on deep learning and trained with eye tracking studies data.
0 sec
To get a result
0
Aggregate eye tracking studies data
0 %
Accuracy of prediction for websites and 94% for general AI model.
0
Designs analysed
The technology

Data

Our algorithm is trained on approximately 30300 images from real eye tracking studies. The image datasets we use are both open-source and proprietary.
Dataset statistics:
  • Participant attention duration: 4 seconds
  • Average gender distribution: 58 % women and 42 % of men
  • Average participant age distribution: varies from 7 years old to about 60+ years old, however, most participants fall into the 21–30 age bracket

Accuracy

Attention Insight visual attention predictions are ~90% accurate for web images, and ~94% accurate for all other images.
The accuracy of our algorithm compared to real eye-tracking studies on average for MIT general images dataset. Area under the curve (AUC Judd) metric was used, currently the main metric in MIT saliency benchmark, to compare eye tracking results with predictions.

Algorithm

Attention Insight attention prediction model is based on deep learning and can automatically detect visual attention shifts that can be used as a substitution for eye tracking studies.

Real eye-tracking studies vs our predictions

Real eye-tracking study
Our prediction
Real eye-tracking study
Our prediction
Real eye-tracking study
Our prediction
Real eye-tracking study
Our prediction
Let’s grab and keep your customer’s attention. 

If you want to test your website design and get RECOMMENDATIONS from our team, send us a message right now:

Or just sign up for a free trial.

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

GET HEATMAP