Predicted consumer buying behavior in neural marketing based on convolutional neural network and short-term long-term memory

Neuromarketing has received attention as a means to bridge the gap between conventional marketing studies and research on brain-computer interfaces based on electroencephalography (EEG). Through priority prediction, it aims to accurately determine customers' true desires. The performance of EEG-based priority detection systems relies on selecting appropriate feature extraction techniques and machine learning algorithms. Current methods do not focus on effective preprocessing techniques and the classification of EEG signals. In this study, preference detection of neuromarketing data is carried out using a combination of different EEG indicators and various algorithms for feature extraction and classification. EEG features are extracted using the discrete wavelet transform (DWT), which enhances the accuracy of priority detection for preference-based EEG indicators. Moreover, a one-dimensional convolutional neural network (CNN1D) in combination with a Long Short-Term Memory (LSTM) network is used. This study compares the proposed method with classifiers such as Support Vector Machines (SVM), Random Forest (RF) and CNN-Transformer. The results obtained demonstrate the high potential of the proposed model in the field of neuromarketing and its improvement over traditional marketing methods. This innovative approach allows us to more accurately identify unconscious consumer buying behaviors and gain a better understanding of their decision-making patterns in real purchasing situations. This study contributes to the field by demonstrating the effective use of EEG and machine learning to enhance neuromarketing strategies.