This study investigates the use of machine learning algorithms and EEG data to predict consumer purchasing decisions in online shopping. A field experiment with 66 participants yielded 328 decision-making instances. Analysis of EEG features (power spectral density (PSD) and prefrontal asymmetry index (PAI)) using various classifiers (KNN, RF, SVM, shallow neural network) and feature selection methods revealed that SVM with a Gaussian kernel achieved the highest accuracy (87.1%). Frontal and occipital regions played significant roles, with PAI indicating the prefrontal cortex's involvement in cognitive and emotional processing, and occipital PSD features highlighting visual processing and attention. The findings suggest the potential of EEG features in consumer behavior analysis and the importance of advanced machine learning for interpreting neural decision-making.

Zhiwei Xu, Siqi Liu