A Comparative Study of ANN and ANFIS Models in Predicting USD to DZD Exchange Rates

This study compares the effectiveness of Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) models in predicting USD to DZD exchange rates using daily data from May 2010 to May 2024. The ANN models, especially those with two-layer configurations, consistently outperformed ANFIS models in terms of accuracy, demonstrating lower mean squared error and root mean squared error. The findings suggest that ANN is better suited for exchange rate prediction, offering superior accuracy and computational efficiency. This research highlights the potential for improving ANFIS models by optimizing fuzzy inference systems and integrating additional features. The findings of this study highlight the significance of choosing the right modeling techniques for financial forecasting to enhance predictive accuracy and decision-making.