DDPG based on multi-scale strokes for financial time series trading strategy

TL;DR

This paper introduces a multi-scale stroke deep reinforcement learning model (MSSDDPG) that leverages multi-scale features based on financial theory to improve trading strategies in noisy, non-stationary financial time series.

Contribution

It proposes a novel multi-scale feature extraction method combined with DDPG for financial trading, demonstrating superior performance over existing strategies.

Findings

Outperforms turtle trading, DQN, and standard DDPG in experiments.

Achieves best results on China's CSI 300 and SSE Composite indices.

Shows outstanding performance on U.S. stock indices Dow Jones and S&P 500.

Abstract

With the development of artificial intelligence,more and more financial practitioners apply deep reinforcement learning to financial trading strategies.However,It is difficult to extract accurate features due to the characteristics of considerable noise,highly non-stationary,and non-linearity of single-scale time series,which makes it hard to obtain high returns.In this paper,we extract a multi-scale feature matrix on multiple time scales of financial time series,according to the classic financial theory-Chan Theory,and put forward to an approach of multi-scale stroke deep deterministic policy gradient reinforcement learning model(MSSDDPG)to search for the optimal trading strategy.We carried out experiments on the datasets of the Dow Jones,S&P 500 of U.S. stocks, and China's CSI 300,SSE Composite,evaluate the performance of our approach compared with turtle trading strategy, Deep Q-learning(DQN)reinforcement learning strategy,and deep deterministic policy gradient (DDPG) reinforcement learning strategy.The result shows that our approach gets the best performance in China CSI 300,SSE Composite,and get an outstanding result in Dow Jones,S&P 500 of U.S.