Tax payment default prediction using genetic algorithm-based variable selection

作者：

Highlights：

• Solvency, liquidity and payment period of trade payables are central variables.

• The best performing model comprises three non-linearly transformed variables.

• The best performing model has a predictive accuracy of 73.8%.

摘要

•Solvency, liquidity and payment period of trade payables are central variables.•The best performing model comprises three non-linearly transformed variables.•The best performing model has a predictive accuracy of 73.8%.

论文关键词：Tax default,Discriminant analysis,Genetic algorithms,Variable selection

论文评审过程：Received 23 April 2017, Revised 15 July 2017, Accepted 15 July 2017, Available online 17 July 2017, Version of Record 19 July 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.07.027