https://doi.org/10.30585/irabml.v1i1.53 © 2018 the Authors. Production and hosting by Avicenna FZ LLC. on behalf of Dubai Business School, University of Dubai – United Arab Emirates. This is an open access article under the CC BY-NC license. Page | 13 International Review of Advances in Business, Management and Law IRAMBL, Vol 1., No. 1, ISSN: 2616-4272 Available online at: http://publications.ud.ac.ae/index.php/IRBML Predicting Users’ Responses of Public Utility Services - Multivariate and Neural Network Analysis - A Case Study S. Sreedharan a , Poornima G.R b , Meena Nair c , Genanew B.Worku d , Ananth Rao e* , Wathiq Mansoor f a Public Affairs Centre (PAC), Bangalore-India, sreedhar@pacindia.org b Programme Officer, PAC, Bangalore – India, poornima.gr@pacindia.org c Participatory Governance Research Group, PAC, Bangalore – India, meena@pacindia.org d Dubai Business School, University of Dubai, Dubai, United Arab Emirates, gbekele@ud.ac.ae e Dubai Business School, University of Dubai, Dubai, United Arab Emirates, arao@ud.ac.ae f College of Engineering and IT, University of Dubai, Dubai, wmansoor@ud.ac.ae *Corresponding author. Received: 16 June 2017, revised: 4 September 2017, accepted: 7 September 2017, published: 9 April 2018 ABSTRACT This research addresses the problem of predicting the user’s responses through multivariate choice (MVC) and neural network (NN) frameworks for predicting quality, quantity and overall User satisfaction of public water supply organization, BWSSB (Bangalore Water Supply and Sewerage Board) in Bangalore - India for policy initiatives. The MVC study identifies statistically significant factors that explain users’ loyalty to express satisfaction and voice to express dissatisfaction. The MVC model correctly predicts 85% of satisfied customers across satisfaction dimensions. Wald test on 1940 responses confirms that there exits cross equation correlation across quality, quantity and overall Users’ satisfaction dimensions and thus appropriateness of MVC framework over traditional logit for predicting the user responses. NN framework outperforms the econometric model with 94% correct classification of user responses. The study opens up potential research opportunities for applying the advanced analytical frameworks for predicting user responses in various public and private settings for Policy initiatives so that the service providers could improve their service delivery. Key Words: Multivariate Choice Model, Neural Networks, Public Utility Service Provider, Econometric Model, Behavioural Responses, Big Data Analytics. JEL Codes: H41, H44, O18, Q25 1. INTRODUCTION Until recently, less interest has been shown to customer satisfaction by public administrations, especially in the case of public services, even though it is precisely in this sector that investigations on customer responses should be more useful. While private companies can be aware of customers’ dissatisfaction with a product, because its purchasing decreases, a public enterprise providing a service and operating as a monopoly might well be unaware of the lack of satisfaction among its Users if these Users cannot switch to other providers, refuse or reduce the service, since Hirschman’s “exit” becomes difficult or impossible (Hirschman 1970). Furthermore, a good knowledge of satisfaction for different aspects of a service in connection with the characteristics of its Users can suggest a multiple and more satisfactory provision of that service. In the absence of the market mechanisms of private ownership and competition, Brudney and England (1982) argue that satisfaction with the ‘impacts’ of services is significant in itself but also provides important information to policy makers. Therefore, a careful evaluation and monitoring of User satisfaction through survey responses using appropriate analytical tools could be useful in the public sector. 1.1. Research problem and questions