Consumer Decision Recognition Based on EEG Signals for Neuromarketing Applications

Neuromarketing is a blooming interdisciplinary field that tries to understand the biology of consumer behavior by combining neuroscience with marketing. This technique can be used to grasp consumers’ hidden choices, intentions and decisions by analyzing their physiological and brain signals. Electroencephalography (EEG) is one of the popular neuroimaging techniques to capture and record the neural activity of the brain. Numerous research projections have been made in this field to achieve better results. Earlier approaches did not prioritize effective EEG signal preprocessing and classification methods. This paper presents a model to recognize consumer preferences by analyzing and classifying EEG signals. In this model, EEG signals are decomposed into many subbands using wavelet transform. An enhanced wavelet thresholding method is proposed to eliminate noise from subbands. Several wavelet features are computed from each subband and then fed as input to classifiers. Finally, three different machine learning classifiers are used to classify the signal between like and dislike. The classifiers are K-Nearest Neighbor (KNN), Multilayer Perceptron (MLP) and Support Vector Machine (SVM). EEG signals from 25 people are collected to verify the developed system’s performance. The effectiveness of the developed method with different classifiers is validated by varying brain lobe features and band features. In comparison to other classifiers like KNN and MLP, the designed system with the SVM classifier performs better and achieves an accuracy of 98.21%. The experimental findings for the developed system suggest that research in this area has the potential to alter and enhance marketing tactics for the benefit of both manufacturers and consumers, ultimately leading to a mutually beneficial outcome.