Predicting product choice by customers based on neuromarketing with Chaotic salp swarm algorithm

Understanding how consumers make decisions is one of the important things in customer behavior that is addressed by neuromarketing. The purpose of this article is to present a new solution in neuromarketing by receiving brain signals and extracting and selecting important features and classification to increase the prediction of product selection by customers. In this article, brain signals from twenty-five participants who have seen the products have been received and characterized by the high-order spectrum method. In order to select the best features, in this article, the swarm algorithm of salp chaos has been presented, which can identify the effective features with high search power, and for the final prediction, different classifications have been used in the form of multiple learning. In the proposed model, the high-order spectra method was applied in extracting the phase information of the electroencephalogram signal in order to investigate the relationship between liking and disliking the product, which included more than seven hundred features. Then feature selection was used with the improved Salp swarm algorithm with logistic chaos mapping and the features were reduced from 742 to 198 features. The results showed that the proposed model was able to have an average accuracy of 75.99% in detecting the choice of users in all products, which shows a 3.75% improvement in the results compared to similar researches.