Machine Learning Techniques for Eeg-Based Neuromarketing: A Systematic Literature Review

Understanding consumer behavior has become important for companies as it can provide insights into consumer preferences and their future decisions, which can be useful in designing effective marketing strategies. Traditional data-gathering methods such as surveys, interviews, and focus groups have some limitations; so, neuromarketing-based approaches can be used to collect consumer brain data and reduce the biases of previous methods. Neuromarketing uses various techniques to measure brain activity, and one of them used in various research is EEG signals. Because of their characteristics, EEG signals have a significant application in neuromarketing. However, because these signals are often complex and analyzing them is time-consuming, machine learning and deep learning methods can be used to analyze user responses to stimuli in neuromarketing research more efficiently. This paper provides a systematic review of previous studies related to analyzing and processing EEG signals in neuromarketing using machine learning methods to have an overview of these methods, evaluate previous research, identify the gaps, and offer suggestions for future studies.