Deep neural networks in foreign exchange market: A predictive classification framework for real-time price movement”

The application of deep neural networks (DNNs) in foreign exchange (FX) markets introduces a novel methodology for predicting short-term price movements with greater accuracy. This study explores a classification-based approach, where market price direction is forecasted using a comprehensive model trained on high-frequency historical FX data. By employing advanced deep learning techniques and leveraging co-movement patterns between various currency pairs, the model classi- fies price changes into positive, negative, or neutral outcomes. Through a backtested strategy on multiple FX futures over 43 instruments, this method demonstrates improved decision-making accuracy and offers sig- nificant potential for enhancing algorithmic trading strategies. Our find- ings reveal that incorporating multiple hidden layers in neural networks significantly boosts predictive performance, positioning DNNs as a pow- erful tool for traders and financial analysts.