Estimation of brand extension evaluation from the brain activity using a convolutional neural network

Abstract

The present neuromarketing study aims to predict how consumers evaluate brand extension from their brain activity. Brand extension refers to the use of well-established brand name to new goods or service. In our experiment, participants evaluated whether a given brand extension sample was acceptable during functional magnetic resonance imaging (fMRI) scanning. Brand extension samples included parent beverage brand name and extended goods name from beverage or household appliance categories. We pre-processed 3-D fMRI image data and extracted 2-D feature images based on a preliminary study. To overcome the limited number of fMRI samples, we conducted image augmentation for the training dataset. A deep neural network model with the convolutional neural network (CNN) architecture was used to classify fMRI images in response to visual presentation of each brand extension sample into one of the two classes: acceptable vs. non-acceptable. The train classifier was tested using 10-fold cross validation. Our model estimated the evaluation of brand extension with high accuracy (90.4%). This result indicates that one can predict how a consumer evaluates a new brand extension proposal only by their brain activity.