Foreign exchange prediction and trading using random forests

Abstract

The aim of the study is to predict foreign exchange prediction and trading strategies using Random Forests. The application of machine learning technology in market forecasting has been widely established in the scientific community. Developing high-precision techniques for predicting financial time series is critical for economists, researchers, and analysts. Complex machine learning techniques, such as artificial neural networks, support vector machines (SVMs) and random forests, provide sufficient learning capabilities and are more likely to capture complex nonlinear models that dominate the financial market. This paper discussed the application of random forests in predicting the exchange rate of the Euro against the US dollar. Taking the Long-Short-Term Memory Neural Network (LSTM) as a reference, compare the role of the two in this application, in order to promote the future development of machine learning technology in the scientific community.