Machine Learning
The Case against Accuracy Estimation for Comparing Induction Algorithms
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Crafting Papers on Machine Learning
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Tree induction vs. logistic regression: a learning-curve analysis
The Journal of Machine Learning Research
Massively Categorical Variables: Revealing the Information in Zip Codes
Marketing Science
Random Forests for multiclass classification: Random MultiNomial Logit
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
Response modeling with support vector machines
Expert Systems with Applications: An International Journal
An empirical evaluation of rotation-based ensemble classifiers for customer churn prediction
Expert Systems with Applications: An International Journal
Data augmentation by predicting spending pleasure using commercially available external data
Journal of Intelligent Information Systems
Customer attrition in retailing: An application of Multivariate Adaptive Regression Splines
Expert Systems with Applications: An International Journal
| Hi-index | 12.05 |
The key question of this study is: How long should customer event history be for customer churn prediction? While most studies in predictive churn modeling aim to improve models by data augmentation or algorithm improvement, this study focuses on a another dimension: time window optimization with respect to predictive performance. This paper first presents a formalization of the time window selection strategy, along with a literature review. Next, using logistic regression, classification trees and bagging in combination with classification trees, this study analyzes the improvement in churn-model performance by extending customer event history from one to sixteen years. The results show that, after the fifth additional year, predictive performance is only marginally increased, meaning that the company in this study can discard 69% of its data with almost no decrease in predictive performance. The practical implication is that analysts can substantially decrease data-related burdens, such as data storage, preparation and analysis. This is particularly valuable in times of big data when decreasing computational complexity is paramount.