Article ID: | iaor20134009 |
Volume: | 14 |
Issue: | 2 |
Start Page Number: | 91 |
End Page Number: | 104 |
Publication Date: | Jun 2013 |
Journal: | Information Technology and Management |
Authors: | Yang Jeongwon, Ha Sung |
Keywords: | neural networks, statistics: regression |
Recent years have witnessed the growing popularity of Internet telephony services (ITSs) in the telecommunications industry. However, most studies of ITSs have focused on technological trends, institutional policies, or advances in related technologies. Although there has been a sharp increase in demand for ITSs, which are increasingly likely to replace existing telephone services, few studies have provided a quantitative analysis of ITSs. This study develops some classification models for predicting consumers’ intentions to switch from traditional telephone services to ITSs by adopting data mining methods to analyze switching intentions and using discriminant analysis, logistic regression, classification tree, and neural network techniques to develop the classification models. This study compares these models to identify the superior one, and using the chosen model, the study suggests some customer relationship management strategies that can best address the transition from traditional telephone services to ITSs. The classification model has important practical implications for managers in the telecommunications industry.