Neuromarketing Study Using Machine Learning for Predicting Purchase Decision

Abstract

Neuromarketing research has evolved as a new and novel way of gathering reliable consumer data to understand consumer decisions better and increase marketing effectiveness. Physiological and neural signals are measured in neuromarketing to get insight into customers' motivations and preferences, which can help create new marketing materials, product development, pricing, and other marketing sectors. The most prevalent methods of measuring are brain scanning, which measures neural activity, and physiological tracking, which measures eye movement, heart rate, and skin conductivity. As part of this study, electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) are used together with galvanic skin response (GSR) and heart rate variability (HRV) to see how different colors of one product affects consumers' preferences. Machine learning algorithms such as the k-nearest neighbor (kNN) and support vector machine (SVM) are adopted to ascertain consumer preferences.