The tree based linear regression model for hierarchical categorical variables
作者：
Highlights：
• We study linear regression models built on hierarchical categorical predictors.
• We aim to consolidate information, trading off the accuracy and the complexity.
• An optimization problem to obtain such reduced lineal regression model is solved.
摘要
•We study linear regression models built on hierarchical categorical predictors.•We aim to consolidate information, trading off the accuracy and the complexity.•An optimization problem to obtain such reduced lineal regression model is solved.
论文关键词：Hierarchical categorical variables,Linear regression models,Accuracy vs. model complexity,Mixed integer convex quadratic problem with linear constraints
论文评审过程：Received 11 June 2021, Revised 24 January 2022, Accepted 25 April 2022, Available online 4 May 2022, Version of Record 12 May 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117423
