Forecasting USD/CNY Exchange Rates Using Machine Learning

Exchange rate prediction is important in global trade, investment, and financial decision-making. The USD/CNY exchange rate in particular has received much attention due to China’s growing role in the global economy. However, predicting exchange rates is difficult because the data is complex, nonlinear, and often influenced by many factors. This research focuses on predicting the USD/CNY exchange rate using machine learning-based approaches. Three models are evaluated and compared in this work: SVR, LSTM, and GRU. Historical exchange rate data is from January 1, 2015, to March 20, 2025. Model performance is evaluated by the R²score, MSE, MAE, and RMSE. The results show that all three models can capture exchange rate trends. GRU achieves the highest performance. It reaches an R²score of 0.9311 and the lowest error metric. LSTM reaches an R² of 0.9141.SVR reaches an R² of 0.9005 The findings suggest that deep learning approaches offer better results in financial time series forecasting and it can provide valuable insights for future applications in exchange rate prediction.