Forecasting foreign exchange rate volatility using deep learning: Case of US dollar/Algerian dinar during the COVID-19 pandemic
Forecasting foreign exchange rate volatility using deep learning: Case of US dollar/Algerian dinar during the COVID-19 pandemic

Summary/Abstract: This study explores the application of deep learning techniques in forecasting foreign exchange rate volatility, leveraging the ca-pabilities of neural networks to capture complex patterns and non-linear relationships within financial data. The volatility of ex-change rates is a critical factor influencing investment decisions, risk management and financial market stability. Traditional mod-els often struggle to capture the dynamic nature of market condi-tions, leading to increased interest in advanced machine learning methodologies. We applied the auto regressive integrated moving average (ARIMA) and machine learning linear regression (LR) mod-el, deep learning models, i.e. recurrent neural networks (RNN), bidirectional LSTM (BiLSTM), long short-term memory (LSTM) and gated recurrent unit (GRU). In terms of forecasting errors, Python routines were used for such a purpose. Furthermore, in order to investigate the quality of the models used, we compared the performances of these algorithms in US dollar/Algerian dinar exchange rate forecasting through the application of significance statistical tests (R-squared, MSE, RMSE, MAE, MAPE).The results clearly depict that contemporary techniques have been shown to produce more accurate results than conventional regression-based modelling. The machine learning linear regression (LR) model provides the maximum accuracy rate (99.83%), followed by the RNN models, with the GRU model (92.27%), BiLSTM mod-el (87.34%), LSTM model (74.68%) and ARIMA model (32.29%).

• Details
• Contents