The Science Behind Our Predictions
Built on the world's largest dataset of real eye-tracking data with industry-leading accuracy
Built on the world's largest dataset of real eye-tracking data with industry-leading accuracy
Dataset Foundation
Our model's accuracy stems from training on the most comprehensive real-world webcam eye-tracking dataset ever assembled from people viewing content on desktop and laptop screens
Our model's accuracy stems from training on the most comprehensive real-world webcam eye-tracking dataset ever assembled from people viewing content on desktop and laptop screens
Eye-Tracking Tests
Individual testing sessions from real webcam eye-tracking studies ensuring robust attention pattern recognition across diverse viewing scenarios
Individual testing sessions from real webcam eye-tracking studies ensuring robust attention pattern recognition across diverse viewing scenarios
Unique Items
Distinct designs analyzed including advertisements, websites, and packaging viewed on desktop and laptop screens in real-world studies
Distinct designs analyzed including advertisements, websites, and packaging viewed on desktop and laptop screens in real-world studies
Fixation Points
Over 33.9 million individual eye fixations captured via webcam eye-tracking on desktop and laptop devices, reflecting authentic visual behavior
Over 33.9 million individual eye fixations captured via webcam eye-tracking on desktop and laptop devices, reflecting authentic visual behavior
Exceptional Predictive Accuracy
We measure performance using Mean Absolute Error (MAE) against real webcam eye-tracking data from desktop and laptop viewing sessions - the lower the score, the closer our predictions match actual human gaze patterns.
Latest Model Performance (November 2025 - Epoch 70)
Overall Mean Absolute Error across all attention components
Component-Specific Accuracy (Validation MAE)
What Does ~6.1% Error Mean for Your Business?
In simple terms: When our AI predicts how much attention a specific area of your design will get, it's approximately 6.1% off from actual measurements.
Highly Accurate Predictions
If we predict 30% of people will notice your logo, the real number will be between 28.17% and 31.83% (±6.1%)
Confident Design Decisions
Make expensive design changes with confidence - our predictions are reliable enough for business decisions
Skip Costly Testing
Get research-grade accuracy without running expensive eye-tracking studies for every design iteration
Understanding the Accuracy Metrics
Hold Component (12.0% MAE): Predicts how long people fixate on areas with strong accuracy for sustained attention prediction. Time-range specific: 6.4% (3s), 6.1% (6s), 5.9% (10s).
Speed Component (11.6% MAE): Reliable accuracy in predicting time-to-first-fixation, determining which areas capture immediate attention. Time-range specific: 6.4% (3s), 6.0% (6s), 5.9% (10s).
Reach Component (10.8% MAE): Best component performance in forecasting what proportion of users will notice specific areas across different viewing durations. Time-range specific: 6.2% (3s), 5.8% (6s), 5.8% (10s).
Deep Learning Architecture
Technical Implementation
Deep Neural Networks
State-of-the-art convolutional neural networks trained specifically on webcam eye-tracking data from real desktop and laptop viewing sessions
Multi-Scale Analysis
Processes images at multiple resolutions to capture both fine-grained details and overall composition patterns that influence visual attention
Real-World Training
Trained exclusively on actual human viewing data from webcam eye-tracking studies, not synthetic or laboratory-controlled environments
Experience the Accuracy Yourself
See how our scientifically-validated predictions can enhance your design process