Neuromarketing Solutions based on EEG Signal Analysis using Machine Learning

Abstract

Marketing campaigns that promote and market various consumer products are a well-known strategy for increasing sales and market awareness. This simply means the profit of a manufacturing unit would increase. "Neuromarketing" refers to the use of unconscious mechanisms to determine customer preferences for decision-making and behavior prediction. In this work, a predictive modeling method is proposed for recognizing product consumer preferences to online (E-commerce) products as "Likes" and "Dislikes". Volunteers of various ages were exposed to a variety of consumer products, and their EEG signals and product preferences were recorded. Artificial Neural Networks and other classifiers such as Logistic Regression, Decision Tree Classifier, K-Nearest Neighbors, and Support Vector Machine were used to perform product-wise and subject-wise classification using a user-independent testing method. Though, the subject-wise classification results were relatively low with artificial neural networks (ANN) achieving 50.40 percent and k-Nearest Neighbors achieving 60.89 percent. Furthermore, the results of product-wise classification were relatively higher with 81.23 percent using Artificial Neural Networks and 80.38 percent using Support Vector Machine.

A systematic review of the prediction of consumer preference using EEG measures and machine-learning in neuromarketing research

“…In the literature reviewed presently, machine learning was used primarily to predict consumer self-reported preference or buying behaviour [ 1 – 4 , 6 , 23 , 24 , 31 , 85 , 87 , 96 , 98 , 101 – 103 , 139 , 151 , 178 , 185 , 185 , 186 , 186 , 206 , 210 , 223 , 254 , 262 , 263 , 287 , 294 , 307 , 308 , 314 ]. However, it has yet to be demonstrated how machine learning can be used to improve advertisement or product designs.…”

“…Literature searches using the six journal databases used in the primary literature search were conducted using the search terms “consumer neuroscience”, “neuromarketing”, and “machine learning”. From this literature search, an additional eighteen studies were identified which used machine learning to predict consumer preference or purchase intention using EEG signals [ 4 , 6 , 23 , 24 , 87 , 96 , 185 , 185 , 186 , 186 , 206 , 210 , 237 , 263 , 287 , 291 , 294 , 307 , 308 , 313 ]. These additional studies have been included in the systematic review section.…”

“…The subsequent use of machine-learning algorithms has been shown to improve the predictive accuracy of a model above the use of traditional logistic regressions [ 31 , 85 , 87 , 96 , 102 , 103 , 151 , 185 , 185 , 186 , 186 , 251 , 255 , 287 , 291 , 294 , 313 ]. Most studies reviewed employed the use of multiple machine-learning algorithms, allowing for the direct comparison of these methods [ 2 – 4 , 6 , 23 , 87 , 98 , 102 , 103 , 206 , 210 , 251 , 254 , 263 , 287 , 294 , 307 , 308 ] (see Table 4 ).…”

“…Across the reviewed literature, the most commonly used classification methods were DNN [ 2 , 3 , 6 , 313 ], KNN [ 2 , 3 , 6 , 98 , 102 , 103 , 206 , 210 , 263 , 308 ], SVM [ 1 – 3 , 6 , 87 , 98 , 102 , 103 , 185 , 185 , 186 , 186 , 210 , 263 , 291 , 307 , 308 , 314 ], RF [ 1 – 3 , 6 , 23 , 85 , 98 , 151 , 206 , 307 , 308 , 314 ], and regressions [ 1 , 24 , 85 , 102 , 103 , 138 , 237 , 251 ].…”