In the last decade, High-Frequency Trading (HFT) has become a popular issue in the futures market, which has attracted much attention from numerous researchers. In this study, an intelligent decision support system is proposed for apple futures high-frequency trading. First, three eXtreme Gradient Boosting (XGBoost) based models use the feature inputs from multiple time scales for return and direction prediction. Then, based on a pre-designed trading rule, the signals of long and short-selling are determined, and corresponding transactions are executed. In order to retain considerable profits in time and to avoid serious losses possibly caused by sudden and huge price changes toward the opposite direction as predictions, a position closing function is implemented in the trading rule. Meanwhile, Particle Swarm Optimization (PSO) is employed to optimize the parameters of the trading rule as well as the XGBoost parameters. By evaluating the experimental results, we observed that the proposed approach successfully achieved the best performance in terms of direction prediction accuracy, transaction returns, as well as return/risk ratio. It could be inferred from the experimental results that the proposed approach could provide decision support and beneficial reference for market traders involved in high-frequency trading of the apple futures.
ASJC Scopus subject areas
- コンピュータ サイエンス（全般）