کاربرد داده کاوی برای مدیریت تلاطم مخابراتی

Taiwan deregulated its wireless telecommunication services in 1997. Fierce competition followed, and churn management becomes a major focus of mobile operators to retain subscribers via satisfying their needs under resource constraints. One of the challenges is churner prediction. Through empirical evaluation, this study compares various data mining techniques that can assign a ‘propensity-to-churn’ score periodically to each subscriber of a mobile operator. The results indicate that both decision tree and neural network techniques can deliver accurate churn prediction models by using customer demographics, billing information, contract/service status, call detail records, and service change log.

Taiwan opened its wireless telecommunication services market in 1997, with licenses granted to six mobile operators. Competition has been fierce from this point. For any acquisition activity, mobile operators need to have significant network investment to provide ubiquitous access and quality communications. The market was saturated within 5 years, and mergers and acquisitions reduced the number of mobile operators from six to four by the end of 2003. When the market is saturated, the pool of ‘available customers’ is limited and an operator has to shift from its acquisition strategy to retention because the cost of acquisition is typically five times higher than retention. As Mattersion (2001) noted, ‘For many telecom executives, figuring out how to deal with Churn is turning out to be the key to very survival of their organizations’. Based on marketing research (Berson, Smith, & Thearling, 2000), the average churn of a wireless operator is about 2% per month. That is, a carrier lost about a quarter of its customer base each year. Furthermore, Fig. 1 suggests that Asian telecom providers face a more challenging customer churn than those in other parts of the world.From a business intelligence perspective, churn management process under the customer relationship management (CRM) framework consists of two major analytical modeling efforts: predicting those who are about to churn and assessing the most effective way that an operator can react (including ‘do nothing’) in terms of retention. This research focuses on the former. It intends to illustrate how to apply IT technology to facilitate telecom churn management. Specifically, this research uses data mining techniques to find a best model of predictive churn from data warehouse to prevent the customers turnover, further to enhance the competitive edge. The remainder of this paper is organized as follows. Section 2 defines some basic concepts (and rationale) that we use in the research, Section 3 describes our research methodology, and Section 4 presents the findings. Section 5 concludes this paper.

Churn prediction and management is critical in liberalized mobile telecom markets. In order to be competitive in this market, mobile service providers have to be able to predict possible churners and take proactive actions to retain valuable customers. In this research, we proposed different techniques to build predictive models for telecom churn prediction. We included customer service and customer complaint log for modeling, as suggestions from prior research of Wei and Chiu (2002). We examined the impact of inadequate data on model building. Our empirical evaluation shows that data mining techniques can effectively assist telecom service providers to make more accurate churner prediction. However, the effective churn prediction model only supports companies to know which customers are about to leave. Successful churn management must also include effective retention actions. Mobile service providers need to develop attractive retention programs to satisfy those customers. Furthermore, integrating churn score with customer segment and applying customer value also helps mobile service providers to design the right strategies to retain valuable customers. Data mining techniques can be applied in many CRM fields, such as credit card fraud detection, credit score, affinity between churners and retention programs, response modeling, and customer purchase decision modeling. We expect to see more data mining applications in business management, and more sophisticated data mining techniques will be developed as business complexity increases.