Exchange Rate Forecasting: A Deep Learning Framework Combining Adaptive Signal Decomposition and Dynamic Weight Optimization

Abstract

Accurate exchange rate forecasting is crucial for investment decisions, multinational corporations, and national policies. The nonlinear nature and volatility of the foreign exchange market hinder traditional forecasting methods in capturing exchange rate fluctuations. Despite advancements in machine learning and signal decomposition, challenges remain in high-dimensional data handling and parameter optimization. This study mitigates these constraints by introducing an innovative enhanced prediction framework that integrates the optimal complete ensemble empirical mode decomposition with adaptive noise (OCEEMDAN) method and a strategically optimized combination weight prediction model. The grey wolf optimizer (GWO) is employed to autonomously modify the noise parameters of OCEEMDAN, while the zebra optimization algorithm (ZOA) dynamically fine-tunes the weights of predictive models—Bi-LSTM, GRU, and FNN. The proposed methodology exhibits enhanced prediction accuracy and robustness through simulation experiments on exchange rate data (EUR/USD, GBP/USD, and USD/JPY). This research improves the precision of exchange rate forecasts and introduces an innovative approach to enhancing model efficacy in volatile financial markets.