Genetic algorithm-based heuristic for feature selection in credit risk assessment

作者：

Highlights：

• This study shows the hybrid genetic algorithm (HGA) with the neural network (NN) in credit risk assessment.

• The HGA improves the GA performance by search space boundary restriction and the creation of the initial population.

• The HGA operates incrementally, tests new hypotheses while steadily improving its own performance.

• The HGA-NN classifier is a promising addition to existing data mining techniques.

摘要

•This study shows the hybrid genetic algorithm (HGA) with the neural network (NN) in credit risk assessment.•The HGA improves the GA performance by search space boundary restriction and the creation of the initial population.•The HGA operates incrementally, tests new hypotheses while steadily improving its own performance.•The HGA-NN classifier is a promising addition to existing data mining techniques.

论文关键词：Artificial intelligence,Genetic algorithms,Classification,Credit risk assessment,Incremental feature selection,Neural network

论文评审过程：Available online 13 September 2013.

论文官网地址：https://doi.org/10.1016/j.eswa.2013.09.004