Biometrically Trained AI Framework for PL Packaging Optimisation

This presentation was delivered at the International Cairo Congress on Scientific Research and Innovation, held online on April 17, 2026. This study introduces a biometrically trained artificial intelligence (AI) framework for optimizing private label (PL) packaging design, with a specific focus on the halo effect as a key cognitive mechanism shaping consumer perception. Grounded in dual-process theory and cognitive bias literature, the research examines how visually optimized packaging can influence perceived product quality and purchase intent independent of brand equity. Methodologically, the study employs a sequential multimodal mixed-method design integrating biometric data (eye-tracking), quantitative experimental testing, and qualitative inquiry through focus groups (N=43). The AI model is trained using real consumer attention data to generate neuro-optimized packaging alternatives, which are then evaluated under blind and branded conditions to measure perception shifts. Findings demonstrate that AI-optimized packaging can significantly neutralize private label stigma by leveraging the halo effect, enabling consumers to infer premium quality even in the absence of strong brand associations. Notably, in the Karmen case, the optimized design achieved 100% preference in blind conditions, indicating the dominant role of visual cues in early-stage decision-making . However, results also reveal boundary conditions: semantic mismatches in design elements (e.g., color-category incongruence) can lead to cognitive dissonance and rejection, as observed in the Vince case . The study contributes to the literature by bridging neuromarketing, AI-driven design, and consumer psychology, offering a novel framework for data-driven packaging optimization. Managerially, it positions packaging as a “silent communicator” capable of shaping perceived quality and overcoming structural disadvantages of private labels in competitive retail environments.