A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring
作者：
Highlights：
• A novel boosted tree model for credit scoring is proposed.
• A hyper-parameter optimization technique is developed based on TPE algorithm.
• The model is proved to outperform several baseline techniques.
• The model is validated on five datasets over five performance metrics.
• The feature importance scores and decision chart enhance model interpretation.
摘要
•A novel boosted tree model for credit scoring is proposed.•A hyper-parameter optimization technique is developed based on TPE algorithm.•The model is proved to outperform several baseline techniques.•The model is validated on five datasets over five performance metrics.•The feature importance scores and decision chart enhance model interpretation.
论文关键词：Credit scoring,Boosted decision tree,Bayesian hyper-parameter optimization
论文评审过程：Received 19 November 2016, Revised 8 February 2017, Accepted 9 February 2017, Available online 10 February 2017, Version of Record 21 February 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.02.017
