LAUSR

Price prediction using machine learning is a heated topic and an effective task in quantitative trading. However, the objectives that existing researches focus on are typically naive and can hardly express the diverse properties in real trading, by using which the results of price prediction cannot precisely reflect the returns in real trading. To alleviate this problem, we first formulate the characteristics of transactions and then propose a multi-objective method under a real-trading-oriented perspective, where a tree model inducing explainable trading characteristics is proposed. With lots of considerations of real trading characteristics, the results of price prediction can better obtain the properties in trading, and especially perform quite well in real trading. Multiple experiments on the Chinese Index Future Market display the effectiveness of the proposed model, where the performance of real trading has reached the industry-leading level. In particular, the difference between model prediction and returns in real trading can be diminished.