Event-Driven LSTM For Forex Price Prediction

Abstract

The majority of studies in the field of AI guided financial trading focus on purely applying machine learning algorithms to continuous historical price and technical analysis data. However, due to non-stationary and high volatile nature of Forex market most algorithm fail when put into real practice. We developed novel event-driven features which indicate a change of trend in direction. We then build long deep learning models to predict a retracement point providing a perfect entry point to gain maximum profit. We use a simple recurrent neural network (RNN) as our baseline model and compared with shortterm 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 RME 0.006x 𝟏𝟏𝟏𝟏 −𝟑𝟑 , RMSE 2.407x𝟏𝟏𝟏𝟏 −𝟑𝟑 , MAE 1.708x𝟏𝟏𝟏𝟏 −𝟑𝟑 , MAPE 0.194% outperforming previous studies.

A Survey of Forex and Stock Price Prediction Using Deep Learning

“…7. As for MAE, paper [75], [31], [27] and [29] had the lowest order of magnitude MAE with paper [75] having the best performance; paper [26] and [21] were in the second-lowest order of magnitude while paper [30] was in the third lowest order of magnitude. Paper [24] had the highest order of magnitude.…”

“…The model used technical indicators to calculate events then LSTM is used to make the prediction based on the events. [75] Pang, Xiong Wen propsed two improved deep LSTM model with embedded layers. The results showed its improvement over the benchmark.…”

“…6. As for MAPE, paper [75] had the lowest order of magnitude followed by the paper [30] , [24], [82], [84], [91], [95] and [27]. And paper [29] had the highest order of magnitude of MAPE.…”

“…In this table, paper [8], [9], [71] used CNN based model; paper [21], [24], [25], [26], [27], [28], [34], [35], [36], [75], [94] used LSTM based model; paper [50], [51], [52] used DNN based model; paper [53], [55], [73] used RNN based model and paper [67] used other deep learning method. [8], [9], [21], [24], [25], [26], [27], [28], [34], [35], [36], [50], [51], [52], [53], [55], [67], [71], [75], [94] [71], [75] 0.001-0.01 [52], [73] 0.01-0.1 [8], [21], [25], [27], [50],…”

Text Mining of Stocktwits Data for Predicting Stock Prices

“…al. [18], Zhao and Khushi [19] and Kim and Khushi [20] argue that it is best to predict the price of a financial instruct, and hence they propose to deal with this as a regression problem.…”