Research On Customer Churn's Prewarning Of Kunming Telecom

The choices for customers to use different telecom products or operators' services become wider, and the contest to attract customers is more competitive between telecom competitors, as the further reform and division in telecommunication industry. Major telecom competitors have to face serious churn problems, while the telecom market is saturating. Various sales promotions are implemented to attract new customers in order to maintain market occupation. Investigation shows that the cost to attract a new customer is 5 to 10 times more expensive than to maintain a current customer, so a long-time loyal customer is more profitable than a new customer. In this case, how to maintain current customers and predict churn so as to adopt suitable marketing measures to prevent loss becomes a urgent problem for telecom operators.The focus of data mining technology has turned to various application domains after several years' development. Telecom is typical industry with dense data, which hides a great deal of valuable information for enterprise. This paper, which studies the more and more serious customer churn problems in the telecom industry, discovers the characteristic of churned customers using the data mining technology, builds the forecast model of customer churn, and applies the model to forecast the churning customers, then builds the early warning model to prevent the customer churning.One side, in the aspect of technology, the paper analyses systemically several data mining technologies used for solving the PAS customer churn problems. After comparing, the paper applies decision tree algorithm in classification technology to analyze the churn problems, and builds model with it.Another side, in telecom industry, when implementing data mining process, analyses should fully understand business and process of the domain, so in the aspect of business, the paper analyses the causes and factors of customer churn in telecom industry, transforming the problems from business to technology.Based on these, the paper combines the characteristic of business data and sequential pattern technology, the paper emphasizes on the data mining methodology of customer churn in telecom industry, puts forward the specific and effective resolving solutions for the problems involved in business understanding, data understanding, data preparation, modeling, evaluation and deployment.Finally ,on the basis of theoretical research, we gain the churning customer listing through the model, realizes and validates the above research fruit.