Stock market prediction and portfolio composition using a hybrid approach combined with self-adaptive evolutionary algorithm

作者：

Highlights：

• Evolutionary Algorithms with self-adaptive capabilities show improved returns.

• The technical case study is able to diminish accentuated market declines.

• The fundamental case study shows the ability to climb the markets at a fast pace.

• The Sliding windows scheme shows the best way to train/test trading algorithms.

• The portfolio composition system created shows ability ranking companies to invest.

摘要

•Evolutionary Algorithms with self-adaptive capabilities show improved returns.•The technical case study is able to diminish accentuated market declines.•The fundamental case study shows the ability to climb the markets at a fast pace.•The Sliding windows scheme shows the best way to train/test trading algorithms.•The portfolio composition system created shows ability ranking companies to invest.

论文关键词：Evolutionary algorithms,Self-adaptive evolutionary algorithms,Technical analysis,Fundamental analysis,Technical indicators,F-score,S&P500

论文评审过程：Received 26 May 2020, Revised 14 April 2022, Accepted 29 April 2022, Available online 17 May 2022, Version of Record 23 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117478