An Automated Portfolio Trading System with Feature Preprocessing and Recurrent Reinforcement Learning

TL;DR

This paper introduces an automated portfolio trading system that combines feature preprocessing with recurrent reinforcement learning, effectively reducing noise and improving profit while maintaining low drawdowns.

Contribution

The paper presents a novel integrated trading system with feature preprocessing and reinforcement learning, tailored for individual investors with small stock portfolios.

Findings

High profit generation demonstrated in empirical tests

System maintains low drawdown levels

Outperforms existing portfolio strategies

Abstract

We propose a novel portfolio trading system, which contains a feature preprocessing module and a trading module. The feature preprocessing module consists of various data processing operations, while in the trading part, we integrate the portfolio weight rebalance function with the trading algorithm and make the trading system fully automated and suitable for individual investors, holding a handful of stocks. The data preprocessing procedures are applied to remove the white noise in the raw data set and uncover the general pattern underlying the data set before the processed feature set is inputted into the trading algorithm. Our empirical results reveal that the proposed portfolio trading system can efficiently earn high profit and maintain a relatively low drawdown, which clearly outperforms other portfolio trading strategies.