计算机工程2011，Vol.37Issue(9)：12-15,4.DOI:10.3969/j.issn.1000-3428.2011.09.005
基于逻辑回归的客户稳定度建模
Customer Stability Modeling Based on Logistic Regression
摘要
Abstract
Aiming at the problem how to find a scientific method for assessing customer, based on data base of a western communications company, there are 1.2 million experimental data being selected through the expert methods and data extraction, transformation and loading processes.It uses attribute reduction algorithm based on mutual-information simplifies redundant attributes in order to enhance the efficiency and quality of the model construction, and through the Logistic regression algorithm the customer stability prediction model is constructed.The results show the model predicts more than 3 times to enhance hitting rate, so it can meet actual commercial applications.关键词
客户稳定度/Logistic回归/似然比检验/收益分析/每用户平均收入Key words
customer stability/ Logistic regression/ likelihood ratio test/ benefit analysis/ Average Revenue Per User(ARPU)分类
自科综合引用本文复制引用
彭凯,秦永彬,许道云..基于逻辑回归的客户稳定度建模[J].计算机工程,2011,37(9):12-15,4.基金项目
国家自然科学基金资助项目(60863005,61011130038) （60863005,61011130038）
贵州省省长基金资助项目(200404) （200404）
