An investor sentiment reward-based trading system using Gaussian inverse reinforcement learning algorithm

作者：

Highlights：

• Model investor sentiment and return interaction with inverse reinforcement learning.

• Use a preference graph to fit market change in response to sentiment shocks.

• Show superior performance over other news sentiment signal based strategies.

• Propose an adaptive sentiment reward trading system with SVM and retraining.

摘要

•Model investor sentiment and return interaction with inverse reinforcement learning.•Use a preference graph to fit market change in response to sentiment shocks.•Show superior performance over other news sentiment signal based strategies.•Propose an adaptive sentiment reward trading system with SVM and retraining.

论文关键词：Investor sentiment,Inverse reinforcement learning,Support vector machine learning,Sentiment reward

论文评审过程：Received 12 February 2018, Revised 29 May 2018, Accepted 27 July 2018, Available online 29 July 2018, Version of Record 4 August 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.07.056