Multi-Source Financial Data Integration via LSTM-GRU-Attention Models for Robust Forex Predictions

Previous studies have shown that utilizing data sources such as historical or technical data along with deep learning approaches can increase the accuracy of forex price prediction. However, relying on a single data source, such as historical data alone, limits predictive performance as it fails to capture the entire complexity of the market. This study aims to demonstrate that merging financial data from four different sources can significantly improve prediction accuracy. This study proposes a hybrid LSTM-GRU-Attention deep learning model, leveraging historical, fundamental, technical, and sentiment data, to predict the closing price of the GBP/USD currency pair, which is actively traded on a global scale. QuantManager, Forexfactory, and DailyFX data were collected over three timeframes: 30-minute, 1-hour, and 1-day, from January 1, 2013 to December 31, 2023, respectively. The model’s performance was evaluated using MSE, RMSE, and MAE metrics. The proposed model with multi-source data demonstrated substantial error reductions compared to historical data only models from previous studies, achieving RMSE decreases from 17% to 89% and MAE reductions from 22% to 94% across 30-minute, 1-hour, and 1-day timeframes. The integrated multi-source data model outperformed models that integrated only historical data, across all timeframes, highlighting the benefits of improved forex prediction accuracy.