Customer relationship management (CRM) is crucial in today’s airline business because of globalization, increasing competition, market saturation and rapid advances in technology. The aim of CRM is to understand the profitability of their customers and to retain the profitable ones. Therefore, many firms need to be able to determine the value of their customers in order to retain or even cultivate the potential profit of customers (Hawkes, 2000). CRM is a dynamic process of managing a customer–company relationship such that customers elect to continue mutually beneficial commercial exchanges and at the same time are dissuaded from participating in exchanges that are unprofitable to the company (Bergeron, 2002). CRM is a key business strategy in which a firm needs to stay focused on the needs of its customers and must integrate a customer-oriented approach throughout the organization.
The trend of increasing competition and decreasing customer loyalty have led to the emergence of concepts that push from a product orientation to a customer orientation and that define their market strategy from the outside-in and not from the inside-out. The focus here is on customer needs rather than on product features (Ozgener & Iraz, 2006). This shift in organizational culture challenges airlines to revise their organizational system and processes, identify customer-related metrics, and identify areas of strategic advantage. To address this customer focus, discussion on data management, availability, data warehousing, and data mining are occurring at various levels within the airline companies, from booking, check-in, cabin service, customer complaint handling to frequent flyer incentives. An important driver of this change is the advent of CRM, which is underpinned by the information and communication technologies (Ryals & Knox, 2001). Thus, a clear shift toward data-based decision making, using so-called data mining or knowledge discovering techniques is evident.
Data mining – the extraction of hidden predictive information from a large database – is a useful tool for airlines that can identify valuable customers, predict future behaviors, and enables firms to make proactive, knowledge-driven decisions. The Variable Consistency Dominance-based Rough Set Approach (VC-DRSA) originally developed by Greco et al., 1998 and Greco et al., 2000 and extended by Blaszczynski, Greco, and Slowinski (2007) is a relatively new approach in data mining, and is very useful for data reduction in both quantitative and qualitative analysis. The decision rule preference model resulting from the VC-DSRA can even represent inconsistent preferences (Blaszczynski et al., 2007). Unlike conventional data analysis, which uses a statistical inferential technique, the rough set approach is based on data mining techniques for discovering knowledge (Goh & Law, 2003). According to Zhu, Premkumar, Zhang, and Chu (2001), the rough set method does not require additional information about the data; it can work with imprecise values or uncertain data, and is able to discover important facts hidden in that data and express them in natural language. The rough set theory has been successfully applied in a variety of fields, including: evaluation of bankruptcy risk (Slowinski & Zopounidis, 1995), business failure prediction (Beynon & Peel, 2001), travel demand analysis (Goh & Law, 2003), mining stock prices (Wang, 2003), insurance market (Shyng, Wang, Tzeng, & Wu, 2007), accident prevention (Wong & Chung, 2007), customers’ classification of telecommunication services (Blaszczynski et al., 2007) etc.
The objective of this research was to apply the VC-DRSA data mining technique to investigate the behaviors of customers in the airline market, and to develop an appropriate CRM strategy for personalized marketing that could contribute to the enhancement of the long-term relationships with exiting customers. The rest of this paper is structured as follows: In Section 2, some of the important previous researches regarding CRM are summarized, and in Section 3, the basic concept of the VC-DRSA is introduced. In Section 4, an empirical example is illustrated for use in the validation of the proposed model. The results and discussions of the empirical study are presented in Section 5. Finally, in Section 6 some conclusions are drawn.
