Application of LSTM Neural Network in Forecasting Foreign Exchange Price

Abstract

LSTM neural network and RNN neural network models in deep learning are used to forecast the price of foreign exchange financial time series. The existing foreign exchange price and technical analysis indexes are taken as input parameters. By comparing the evaluation indexes of two deep learning models, the optimal neural network model is selected. The experimental results show that the LSTM neural network model has smaller root mean square error (RMSE) and mean absolute error (MAE) than the RNN network model, and the predicted price is more accurate.