首页> 外文会议>International conference on omputational science and technology >Location Analytics for Churn Service Type Prediction
【24h】

Location Analytics for Churn Service Type Prediction

机译:Churn Service类型预测的位置分析

获取原文

摘要

Churn has always been a challenge for companies that trade products or services. Research work has been focusing on predicting customer churn, however, the relationship between churn and geospatial information have not been fully explored. In this work, it was hypothesized that geospatial information exhibits a correlation with churn pattern. Empirical study was conducted to employ five different similarity algorithms to investigate the similarity between one churn location to others. The findings suggested that location features do assert a positive effect on customer churn with the accuracy of 70.24% using Hamming algorithm based on top 31 rows of majority voting.
机译:流失一直是贸易产品或服务的公司挑战。研究工作一直专注于预测客户流失,然而,尚未完全探索流失与地理空间信息之间的关系。在这项工作中,假设地理空间信息表现出与流失模式相关的相关性。进行实证研究以雇用五种不同的相似性算法,以研究一个流失位置与他人的相似性。研究结果表明,使用基于大多数大多数投票的前31行的汉明算法,定位特征对客户流失的积极影响。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号