Consumer behavior analysis using EEG signals for neuromarketing application

Abstract

Neuromarketing is applying neuropsychology in marketing research studying consumer sensory-motor actions such as cognitive and affective responses to marketing stimuli with the help of modern technologies. It is one of the most recent marketing research strategies and may become the future of marketing research. Many research works have been carried out in this area to obtain better outcomes. However, literature shows that there is an opportunity for further improvement. Hence, in this study, a model is presented using data mining and machine learning algorithms for consumer behavior analysis from EEG signals. Time-frequency distribution features are extracted from EEG signals on which different classification algorithms are applied. Consumer's responses toward marketing strategies and their behavior towards purchasing or selecting goods can be studied and analyzed to understand the producer-consumer relationship. EEG signals from 25 people are collected where the participants varied in age and gender for a better understanding of consumer behavior towards a marketing policy. By analyzing the data, the reason behind how and why they like certain marketing policies was uncovered. The performance of our proposed model with an existing technique is compared. The accuracy of our model on the dataset is 95%, whereas the accuracy of the existing technique on the same dataset is 70%. We also evaluated whether neuropsychological measures can capture differences in consumer's actions according to different marketing stimuli. The experimental results on our model indicate that studies in this field can bring a change and improve marketing strategies for the betterment of both the producer and the consumer, resulting in an eventual mutual benefit.