Using a genetic algorithm to optimize an expert credit rating model
作者：
Highlights：
• It is the first study to use a genetic algorithm to replicate credit ratings.
• We show how an “expert” rating model can be optimized with a genetic algorithm.
• The algorithm optimizes the combination of the weights of the variables.
• Our model complies with current and future European banking regulatory framework.
• It also complies with last EBA discussion paper on machine learning for IRB models.
摘要
•It is the first study to use a genetic algorithm to replicate credit ratings.•We show how an “expert” rating model can be optimized with a genetic algorithm.•The algorithm optimizes the combination of the weights of the variables.•Our model complies with current and future European banking regulatory framework.•It also complies with last EBA discussion paper on machine learning for IRB models.
论文关键词：Genetic algorithm,Credit rating,Expert judgment
论文评审过程：Received 13 May 2021, Revised 2 May 2022, Accepted 2 May 2022, Available online 6 May 2022, Version of Record 11 May 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117506
