Advanced Consumer Behaviour Analysis: Integrating Eye Tracking, Machine Learning, and Facial Recognition.

Area of Science:

• Human-Computer Interaction
• Consumer Psychology
• Computer Vision

Background:

• Traditional consumer behavior analysis relies on self-reported data, which is susceptible to biases like recall errors and social desirability.
• Objective behavioral measurements are needed to overcome the limitations of subjective survey methods.

Purpose of the Study:

• To introduce DeepVisionAnalytics, an integrated framework for objective consumer behavior analysis in visually driven tasks.
• To demonstrate the efficacy of combining eye tracking, computer vision (CV), and machine learning (ML) for behavioral insights.

Main Methods:

• The system integrates eye tracking to capture gaze distribution and fixation dynamics.
• OpenCV and ML are employed for facial analysis to estimate demographic attributes (age, gender, ethnicity).
• AOI-level eye tracking metrics are used as the primary signal for choice inference, with demographics as post hoc contextual metadata.

Main Results:

• Gaze-based inference accurately reproduced observed choice distributions in visually driven tasks.
• Demographic estimates facilitated meaningful post hoc segmentation without influencing the decision mechanism.
• The multimodal integration produced reproducible decision-support artifacts like AOI rankings and heatmaps.

Conclusions:

• DeepVisionAnalytics offers a reusable platform for marketing and UX research, generating objective behavioral data.
• The framework enables choice inference under constrained conditions and segment-level interpretation without demographic priors.
• This approach moves beyond descriptive heatmaps to provide actionable, data-driven insights into consumer behavior.