Cross-company customer churn prediction in telecommunication: A comparison of data transformation methods
作者：
Highlights：
• Devised a model for Cross-Company Churn Prediction (CCCP) in telecommunication sector.
• Comprehensively explored the impact of the data transformation methods (i.e., Log, Rank, Box-Cox, and Z-Score) on CCCP model performance.
• Investigated the performance of multiple state-of-the-art classifiers (i.e., Naïve Bayes, K-nearest neighbour, Gradient Boosted Tree, Single Rule Induction, and Deep Learner Neural Net).
• Empirically addressed the following research questions:
• RQ1: What is the effect of DT methods (i.e., log, Rank, Box-Cox and Z-Score) on data normality in CCCP?
• RQ2: What impact does the DT method has in the performance of different classifiers?
• RQ3: Do the application of different DT methods exhibits significant performance difference?
摘要
•Devised a model for Cross-Company Churn Prediction (CCCP) in telecommunication sector.•Comprehensively explored the impact of the data transformation methods (i.e., Log, Rank, Box-Cox, and Z-Score) on CCCP model performance.•Investigated the performance of multiple state-of-the-art classifiers (i.e., Naïve Bayes, K-nearest neighbour, Gradient Boosted Tree, Single Rule Induction, and Deep Learner Neural Net).•Empirically addressed the following research questions:•RQ1: What is the effect of DT methods (i.e., log, Rank, Box-Cox and Z-Score) on data normality in CCCP?•RQ2: What impact does the DT method has in the performance of different classifiers?•RQ3: Do the application of different DT methods exhibits significant performance difference?
论文关键词：Churn prediction,Cross-company,Data transformation,Box-cox,Rank,Log,Z-Score
论文评审过程：Received 4 June 2018, Revised 18 August 2018, Accepted 29 August 2018, Available online 27 September 2018, Version of Record 20 March 2019.
论文官网地址：https://doi.org/10.1016/j.ijinfomgt.2018.08.015
