A Survey of Forex and Stock Price Prediction Using Deep Learning

Predictions of stock and foreign exchange (Forex) have always been a hot profitable area study. Deep learning applications proven to yield better accuracy return in the field financial prediction forecasting. In this survey, we selected papers from Digital Bibliography & Library Project (DBLP) database for comparison analysis. We classified according different deep methods, which included Convolutional neural network (CNN); Long Short-Term Memory (LSTM); (DNN); Recurrent Neural Network (RNN); Reinforcement Learning; other methods such as Hybrid Attention Networks (HAN), self-paced mechanism (NLP), Wavenet. Furthermore, paper reviews dataset, variable, model, results each article. The survey used presents through most performance metrics: Root Mean Square Error (RMSE), Absolute Percentage (MAPE), (MAE), (MSE), accuracy, Sharpe ratio, rate. identified that recent models combining LSTM with example, DNN, are widely researched. yielded great returns performances. conclude that, years, trend using deep-learning-based modeling is rising exponentially.