AIRMS: A risk management tool using machine learning

作者：

Highlights：

• Development of two AI risk management systems based on ANNs and decision trees.

• Determine the most proper evaluation metric based on MRB channel trading strategy.

• Application of walk-forward test to define the models for each year/currency pair.

• Usage of the two developed AIRMSs to predict future trades.

• Performance comparison between produced via AIRMS portfolios to the initial ones.

摘要

•Development of two AI risk management systems based on ANNs and decision trees.•Determine the most proper evaluation metric based on MRB channel trading strategy.•Application of walk-forward test to define the models for each year/currency pair.•Usage of the two developed AIRMSs to predict future trades.•Performance comparison between produced via AIRMS portfolios to the initial ones.

论文关键词：Deep learning,Decision trees,Trading strategies,Risk management,Modified Renko bars,Profitable portfolio

论文评审过程：Received 19 July 2017, Revised 22 March 2018, Accepted 23 March 2018, Available online 27 March 2018, Version of Record 24 April 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.03.044