High-frequency direction forecasting and simulation trading of the crude oil futures using Ichimoku KinkoHyo and Fuzzy Rough Set

Abstract

With the rapid development of the Chinese economy in the last thirty years, crude oil has become an essential commodity and a strategic resource for China. Thus, the topic of crude oil price prediction has drawn significant attention from market participants and researchers. In this study, we propose an intelligent trading decision support system called FRS-NSGA-II-SW, which integrates the Fuzzy Rough Set (FRS), Non-dominated Sorting Genetic Algorithm-II (NSGA-II), and Sliding Window (SW), for high-frequency price direction prediction and simulated trading of the crude oil futures in the Chinese market. Additionally, a Japanese technical indicator Ichimoku KinkoHyo is employed to extract features of high-frequency movement for the proposed model. To assess the performance comprehensively, four evaluation measures, including hit ratio, accumulated return, maximum drawdown, and Sharpe ratio, are employed to investigate the performances of the proposed method and benchmark methods. As a result, the proposed approach produced an average hit ratio of 66.84%, an average accumulated return of 20.39%, an average maximum drawdown of 8.38%, and a Sharpe ratio of 1.22, which outperformed all the benchmark methods. Additionally, Friedman test results indicate that the proposed method significantly outperformed the benchmark methods in terms of prediction accuracy and profit-making ability. Furthermore, experimental results show that integrating the Multi-objective optimization algorithm NSGA-II and the dynamic learning method SW successfully enhanced the performance of the proposed method. The excellent performance of the proposed method demonstrates that it could be applied as an intelligent trading decision support system for market investors and regulators in the Chinese crude oil futures market.