Predicting Online Buying Behavior Among Indian Shoppers Using a Neural Network Technique

Predicting Online Buying Behavior Among Indian Shoppers Using a Neural Network Technique

The online retail store has emerged as a ubiquitous sales channel. As a medium of business that uses computer systems and internet technology to distribute goods and services, the online retailer must attract the maximum possible number of shoppers to buy online at its website, if it is to succeed. It is important, therefore, for the online retailer not only to understand consumers’ online shopping behavior and the factors influencing such behavior, but also to predict online buying potential. In this study, we investigated the contribution of various predictors (independent variables) of online buying behavior using a neural network model. This type of model is known for its competence in examining non-compensatory decision making. Our study is a pioneer in using such a model as a classifying method to predict and explain consumer behavior toward online shopping. An empirical survey was conducted in four Indian state capitals to collect data for our study, and various predictors were identified based on their relative importance to shoppers’ online buying. The results of our study indicate that the predictive model developed using the neural network technique has a prediction rate of 97.01%. In addition, we propose a number of suggestions for online retailers and marketers and address future research needs and managerial implications.