Title: Predicting online buying behaviour - a comparative study using three classifying methods

Authors: Sanjeev Prashar; T. Sai Vijay; Chandan Parsad

Addresses: Indian Institute of Management Raipur (IIMR), Old Dhamtari Road, Sejbahar, Raipur-492015, Chhattisgarh, India ' Indian Institute of Management Raipur (IIMR), Old Dhamtari Road, Sejbahar, Raipur-492015, Chhattisgarh, India ' Indian Institute of Management Raipur (IIMR), Old Dhamtari Road, Sejbahar, Raipur-492015, Chhattisgarh, India

Abstract: Online retailing with its increasing foothold has made India one of the most anticipated destinations for both local and multinational retailers. The success of these online retailers will depend on their ability to attract more and more consumers to shop online. Therefore, it is pertinent to comprehend and understand consumers' attitude and behaviour towards online shopping, besides predicting online buying potential. This empirical study investigates the accuracy of prediction of different classifiers used in determining online buying. We empirically compared the forecasting ability of neural network (NN), linear discriminant analysis (LDA) and k-nearest neighbour (kNN) in the context of consumers' willingness to shop online. Statistical evidence has been provided that neural network significantly outperforms the other two models in terms of the predicting power. This study shall contribute to online retailers in reducing their vulnerability with respect to market demand and improve their preparedness to handle the market response.

Keywords: online buying; predicting buying behaviour; neural network; e-commerce; k-nearest neighbour; kNN; linear discriminant analysis; LDA.

DOI: 10.1504/IJBIR.2018.088468

International Journal of Business Innovation and Research, 2018 Vol.15 No.1, pp.62 - 78

Received: 30 Jul 2015
Accepted: 24 Apr 2016
Published online: 11 Dec 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article