Stock price prediction for a trading strategy: embedding trading strategy into deep learning framework

This paper proposes a new approach to making stock price movement prediction better serve the trading strategy by embedding the strategy into deep learning. The trading strategy is incorporated into the model’s training loss function to obtain a higher return under the given trading strategy. To better embed the strategy into the learning model, we also adopt the data of the same day as a batch instead of fixed-size data as a batch. In other words, each parameter update is based on one day’s data. We used the data from the Chinese stock market for an empirical experiment, and according to the characteristics of the Chinese stock market, we made some special treatments. The empirical experiment results show that this method improves the trading strategy’s performance compared with the benchmark.