Genetic algorithms for credit scoring: Alternative fitness function performance comparison

作者：

Highlights：

• Performance of three different fitness functions in credit scoring is evaluated.

• A novel fitness function based on subsets of client characteristics is proposed.

• The proposed fitness function shows better accuracy and sensitivity.

摘要

•Performance of three different fitness functions in credit scoring is evaluated.•A novel fitness function based on subsets of client characteristics is proposed.•The proposed fitness function shows better accuracy and sensitivity.

论文关键词：Genetic algorithms,Credit scoring,Evolutionary techniques,Fitness function,Finance,Risk management

论文评审过程：Available online 26 November 2014.

论文官网地址：https://doi.org/10.1016/j.eswa.2014.11.028