A Deep Learning Model for Classification of EEG Signals for Neuromarketing

Advertising campaigns for marketing and advertisement of different consumer items is a well-known strategy to boost sales and public awareness. It can lead towards greater profit margins for the factories or companies. Reproduction of products typically depends on numerous factors, such as market usage, reviewer comments, ratings, etc. In neuromarketing a person is examined with the help of EEG signals generated in his/her brain so that his emotions can be recognized for making certain decisions. Therefore, research in this area is in high demand but has not yet achieved an adequate standard. We provide a predictive modelling framework to interpret consumer preferences for e-commerce goods by analyzing EEG data. In this research study, volunteers of varying ages and genders were asked to visually feel the effect of different packaging of products and the corresponding EEG signals generated inside their brains were monitored. Several experiments by varying approaches were performed on the dataset that contain the EEG signals of consumers. Two machine learning and a deep learning classifier were employed to evaluate the accuracy of the model. After conducting different experiments, it was observed that the proposed approach performs superior, and the framework can be leveraged to create a more effective business model.