Event-Driven LSTM For Forex Price Prediction

The majority of studies in the field of AI guided financial trading focus on applying machine learning algorithms to continuous historical price and technical analysis data. However, due to the non-stationary and highly volatile nature of Forex markets most algorithms fail in real practice. In this paper, we developed novel event-driven features which indicate a change of trend in direction. We then built long deep learning models to predict a retracement point providing a perfect entry point to gain maximum profit. We used a simple recurrent neural network (RNN) as our baseline model and compared that with short-term memory (LSTM), bidirectional long short-term memory (BiLSTM) and gated recurrent unit (GRU). Our experiment results show that the proposed event-driven feature selection together with the proposed models can form a robust prediction system which supports accurate trading strategies with minimal risk. Our best model on 15-minutes interval data for the EUR/GBP currency achieved RMSE 1.5×10^-3 with a MAPE 0.12% outperforming previous studies.