Comprehensive study of feature selection methods to solve multicollinearity problem according to evaluation criteria

作者：

Highlights：

• Complete study of feature selection methods in multicollinearity case was performed.

• The quadratic programming approach to treat multicollinearity problem was proposed.

• Test data sets representing diverse multicollinearity cases were used in experiments.

• The proposed approach outperforms other feature selection methods on data sets.

摘要

•Complete study of feature selection methods in multicollinearity case was performed.•The quadratic programming approach to treat multicollinearity problem was proposed.•Test data sets representing diverse multicollinearity cases were used in experiments.•The proposed approach outperforms other feature selection methods on data sets.

论文关键词：Data fitting,Feature selection,Multicollinearity,Quadratic programming,Evaluation criteria,Test data sets

论文评审过程：Received 14 August 2016, Revised 25 January 2017, Accepted 26 January 2017, Available online 26 January 2017, Version of Record 5 February 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.01.048