Using EEG measurements to predict preferences and market success
A basic aim of marketing research is to predict consumers’ preferences and the success of marketing campaigns in the general population. However, traditional behavioral measurements have various limitations, calling for novel measures to improve predictive power. I will present three studies where we use neural signals measured with electroencephalography (EEG) in order to overcome these limitations. I will describe our prediction attempts that started in the first study with a regression analysis, advanced to machine learning algorithms in the second study, and finally evolved to a state-of-the-art deep neural network that we developed in order to generate predictions. I will show that we are able to use EEG measurements to predict participants subsequent choices, willingness to pay, and the success of commercials at the population level. Importantly, I will show that the EEG measurements increased the prediction accuracy of the marketing questionnaire. Lastly, I will discuss the advantages and disadvantages of each of the three prediction approaches and the challenges that the field of neuromarketing is facing.