Evolutionary multi-objective optimization for multivariate pairs trading

作者：

Highlights：

• First large-scale framework to accommodate multivariate pair formation.

• Formulates pair formation as a Mixed Integer Programming model.

• NSGA-II simultaneously optimizes volatility and mean-reversion.

• Details genetic algorithm alterations for implementation.

• Significantly outperforms benchmark strategies.

摘要

•First large-scale framework to accommodate multivariate pair formation.•Formulates pair formation as a Mixed Integer Programming model.•NSGA-II simultaneously optimizes volatility and mean-reversion.•Details genetic algorithm alterations for implementation.•Significantly outperforms benchmark strategies.

论文关键词：Multi-objective optimization,Genetic algorithm,Mixed integer programming,Pairs trading,Portfolio optimization

论文评审过程：Received 14 July 2018, Revised 11 April 2019, Accepted 28 May 2019, Available online 29 May 2019, Version of Record 14 June 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.05.046