摘要
为提高客户流失预测的精度,构建了基于自组织模糊规则归纳算法FRI(Fuzzy Rule Induction)的电子商务客户流失预测模型。该模型利用数据分组处理技术GMDH(Group method data handling)从训练样本中自动地提取接近于人类自然语言描述的电子商务客户流失模糊规则,进而对测试样本客户流失状态进行判别。采用某网上商场的1500名客户样本进行电子商务客户流失预测实证研究,结果表明,该方法对测试样本预测精度达到了90%以上,是一种有效和实用的电子商务客户流失预测工具。
To improve the accuracy of customer churn prediction, Fuzzy Rule Induction (FRI) was applied to E-business customer churn prediction. FRI uses group method of data handling (GMDH) to extract the fuzzy rules from customer data autonomously described in a more natural language to identify customer churn status. Taking 1500 customers in an e-shop as samples, empirical results showed that the forecast accuracy was over 90% on testing samples, proving FRI to be an efficient and practical tool for E-business customer churn prediction.
出处
《计算机应用与软件》
CSCD
2010年第12期44-47,共4页
Computer Applications and Software
基金
国家自然科学基金项目(70471074)
广东省自然科学基金项目(9452902001004060)
国家博士后科学基金一等项目(20100470008)
关键词
自组织模糊规则归纳
数据分组处理
客户流失预测
电子商务
Fuzzy rule induction Group method of data handling(GMDH) Customer churn prediction E-business