A novel crude oil futures trading strategy based on volume-price time-frequency decomposition with ensemble deep reinforcement learning

Abstract

With the deepening financialization of crude oil, an increasing number of investors are becoming involved in trading crude oil futures. However, various factors influence crude oil futures price fluctuations, presenting complex characteristics. For this reason, a trading strategy plays a crucial role in investment. In this paper, we construct an ensemble trading strategy by combining time-frequency feature extraction of crude oil volume-price series with deep reinforcement learning. We decompose the original oil volume-price series by using the optimized variational mode decomposition. Additionally, taking into account the long memory characteristics of the crude oil time series, we employ the Sharpe ratio to filter the appropriate agents corresponding to market volatility. Moreover, the best features of the three agents are effectively combined and used in the next phase of trading, thus robustly adapting to different market volatility situations. Finally, we tested our strategy using Brent crude oil futures. Compared with other benchmark models, the proposed OVMD(V–P)-DRL-Ensemble strategy is suitable for the highly volatile crude oil market and performs well in terms of the corresponding performance evaluation metrics, showing excellent return performance and stability.