Development and performance evaluation of neural network classifiers for Indian internet shoppers Ritanjali Majhi a , Babita Majhi b,⇑ , Ganapati Panda c a School of Management, National Institute of Technology, Warangal, India b Dept. of IT, Institute of Technical Education and Research, Siksha O Anusandhan University, Bhubaneswar, India c School of Electrical Sciences, Indian Institute of Technology, Bhubaneswar, India article info Keywords: Consumer classification Online shopping Factor analysis Hierarchical clustering Discriminant analysis Multilayer perceptron Functional link artificial neural network Radial basis function neural network abstract The rapid growth of usage of internet has paved the way towards the use of online shopping. Consumers’ behavior is one of the significant aspects that is considered by the service providers for the improvement of various services. Consumers are generally satisfied if their needs are fulfilled. In this paper an in depth investigation is made on the behavior of Indian consumers towards online shopping. Factor analysis is carried out to extract significant factors that affect online shopping of Indian consumers and these con- sumers are clustered based on their behavior, towards online shopping using hierarchical clustering. Employing the results of clustering in training of multilayer perceptron (MLP), functional link artificial neural network (FLANN) and radial basis function (RBF) networks efficient classifier models are devel- oped. The performance of these classifiers are evaluated and compared with those obtained by conven- tional statistical based discriminant analysis. The simulation study demonstrates that the RBF network provides best classification performance of internet shoppers compared to those given by the FLANN, MLP and discriminant analysis based methods. The simulation study on the impact of different combina- tion of inputs demonstrates that demographic input has least effect on classification performance. On the other hand the combination of psychological and cultural inputs play the most significant role in classi- fication followed by psychological and then cultural inputs alone. Ó 2011 Elsevier Ltd. All rights reserved. 1. Introduction and literature review During last decade the emergence of high speed internet con- nection and rapid development of internet usage have opened of a new channel for marketing. (Kim, Kim, & Lee, 2009). Convenient access of internet in personal computers, mobile phones and PDAs has made the online shopping a viable alternate shopping medium (Chuleeporn, 2006). Retailers have taken the advantage of these facilities and have introduced several online services which have increased the competition among themselves. The main advanta- ges with online shopping are shopping at any time around the clock, substantial saving of time, wider choice of selection of prod- ucts and services, peer competition to reduce price, easier means to launch new products and least botheration to select and buy a product. In spite of these advantages the consumers are still more concerned about the privacy and security involved in the transac- tion process of online shopping (Chuleeporn, 2006). Recently the craze among Indian shoppers towards online shopping has increased to a larger extent. They mostly prefer online services to purchase various air/railway tickets, movie tick- ets, consumer electronic goods, audio/video files, software pack- ages etc. But online shopping in India is carried out mostly by people living in cities. In rural areas and small towns availability of internet access is quite low. Further most of the rural people are not fully conversant with the usage of internet. Secondly many people having adequate internet exposure prefer buying goods in traditional offline stores as they are worried about the security of their online transactions. In addition there exists a difference in psychology among Indian consumers and consumers in the rest of part of the world. In many situations they discuss with their friends and relatives and take their opinion before buying a costly product. Consumers’ attitude also change within a short span of time (Muthitacharoen, 1999). Buying behavior of consumers de- pends on their characteristics like demography, psychology, cul- ture (Hasslinger, Hodzic, & Opazo, 2008). If the major factors responsible for online shopping are identified and the consumers are, judiciously classified, then the consumers’ needs are known which in turn facilitate the marketing strategy to be undertaken (Hsieh & Chu, 2009). In this paper, investigation is made on the on- line buying behavior of the consumers’ by employing tools such as factor analysis, discriminant analysis, clustering and various artifi- cial neural network based classifiers. 0957-4174/$ - see front matter Ó 2011 Elsevier Ltd. All rights reserved. doi:10.1016/j.eswa.2011.07.128 ⇑ Corresponding author. E-mail addresses: ritanjalimajhi@gmail.com (R. Majhi), babita.majhi@gmail.com (B. Majhi), ganapati.panda@gmail.com (G. Panda). Expert Systems with Applications 39 (2012) 2112–2118 Contents lists available at ScienceDirect Expert Systems with Applications journal homepage: www.elsevier.com/locate/eswa