| Summary: | 碩士 === 輔仁大學 === 體育學系碩士班 === 93 === Abstract
The main purpose of this study included the understanding of customer constitutive structure in YMCA, the customer churn model of YMCA established by data mining classification technology (discriminant analysis, logistic regression, artificial neural networks, and multivariate adaptive regression splines), and the realization of significant characteristics of churn customer through the customer churn model. This study used the data provided by YMCA to perform the empirical research. The original data was 5,487 records, after deleting the missing data and unreasonable data, there were 4,733 records totally. The results were as followed:
1. The customer constitutive structure in YMCA was the majority of female members (61%), the average age of 29.49-year-old and the major concentration of 30-year-old below (61.37%), the 3,850 dollars of total fee at most (42.05%), and living in Taipe city mostly (53.56%).
2. The constructional process of churn model that this study proposed was by way of four classification methods to obtain the one best discriminating mode. Beside, in order to verify the effectivity of the discriminating mode, this study used the data provided by YMCA to perform the empirical research. The result found that whole correct classification rate was 88.49% in this churn model using the best way of multivariate adaptive regression splines.
3. By all accounts, the characteristics of churn customer through the customer churn model using the best way of multivariate adaptive regression were the members of the age 20-year-old below ,and the total fee of 3,850 dollars.
|
|---|
