Windowing improvements towards more comprehensible models
作者：
Highlights：
• We propose several improvements for the windowing algorithm.
• We evaluated model performance, interpretability, and stability.
• Our methodology focuses on the interpretability of the model.
• Our approach shows differences in terms of interpretability, without harming performance.
• Our approach may yield better classification models.
摘要
•We propose several improvements for the windowing algorithm.•We evaluated model performance, interpretability, and stability.•Our methodology focuses on the interpretability of the model.•Our approach shows differences in terms of interpretability, without harming performance.•Our approach may yield better classification models.
论文关键词：Windowing,Decision tree metrics,High dimensional data
论文评审过程：Received 24 July 2015, Revised 11 September 2015, Accepted 4 October 2015, Available online 22 October 2015, Version of Record 11 December 2015.
论文官网地址：https://doi.org/10.1016/j.knosys.2015.10.011
