Combining NeuroEvolution and Principal Component Analysis to trade in the financial markets

作者：

Highlights：

• A system that uses PCA and NEAT to generate a lucrative trading signal is proposed.

• PCA is used to reduce the dimensionality of the input financial data.

• NEAT creates and evolves the neural network that generates the trading signal.

• The proposed system outperforms the B&H strategy in multiple markets.

• The PCA method has a big influence in the performance of the system.

摘要

•A system that uses PCA and NEAT to generate a lucrative trading signal is proposed.•PCA is used to reduce the dimensionality of the input financial data.•NEAT creates and evolves the neural network that generates the trading signal.•The proposed system outperforms the B&H strategy in multiple markets.•The PCA method has a big influence in the performance of the system.

论文关键词：Financial markets,Trading signal,Technical analysis,Principal Component Analysis (PCA),NeuroEvolution of Augmenting Topologies (NEAT)

论文评审过程：Received 10 November 2017, Revised 25 January 2018, Accepted 8 March 2018, Available online 9 March 2018, Version of Record 20 March 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.03.012