2692-2967ISSN (Online)
2770-0216ISSN (Print)
Volume 13 , Issue 1 , PP: 42-64, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
El-Sayed M. El-kenawy 1 *
Doi: https://doi.org/10.54216/AJBOR.130103
Accurate exchange rate prediction is a critical challenge in financial forecasting, as fluctuations in exchange rates directly impact trade balances, investment strategies, and monetary policy decisions. Motivated by the need for robust and precise forecasting models, this study presents a novel framework that integrates deep learning (DL) methodologies with advanced metaheuristic optimization. At the core of this framework is the Continuous-Time Sequence Model (CTSM), complemented by the binary Ninja Optimization Algorithm (bNiOA) for feature selection and the Ninja Optimization Algorithm (NiOA) for hyperparameter tuning. Experimental results demonstrate substantial improvements in predictive performance. The baseline CTSM model achieved an accuracy of 0.8168 with a mean squared error (MSE) of 0.0718. After applying the bNiOA-driven feature selection, accuracy increased markedly to 0.9576, while the MSE was reduced to0.00067. Further optimization of hyperparameters through NiOA elevated the model’s accuracy to 0.9963, with an MSE of 0.00088. These results validate that the proposed optimization-enhanced deep learning pipeline effectively reduces feature redundancy and dimensionality, while finely tuning model parameters to achieve superior accuracy and generalization. The implications of this study are significant, providing policymakers, investors, and businesses with a powerful tool for risk management, strategic planning, and informed decision-making in volatile currency markets.
Ninja Optimization Algorithm (NiOA) , Feature Selection-Hyperparameter Tuning , USD&ndash , PKR Time Series Prediction , Hybrid Deep Learning&ndash , Metaheuristic Models , Financial Time Series Forecasting
[1] Sahar Afshan, Ken Yien Leong, Arsalan Najmi, Ummara Razi, Bawani Lelchumanan, and Calvin Wing Hoh Cheong. Fintech advancements for financial resilience: Analysing exchange rates and digital currencies during oil and financial risk. Resources Policy, 88:104432, 2024.
[2] Faroque Ahmed, Kazi Sohag, Oleg Mariev, Rakibul Islam, Md Ariful Alam, and Mahfuzur Rahman Shuvo. Spillover effects of global, local, and mutual risks on financial stress: How do superpowers react? Chinese Political Science Review, pages 1–36, 2025.
[3] Muhammad Jawad, Sidra Nazir, and Md Saiful Islam. Examining exchange rate bubbles in pakistan: application of sequential adf tests. SN Business & Economics, 5(9):128, 2025.
[4] Mervan Selcuk and Mehmet Asutay. Assessing financial convergence in developing countries: The case of d-8 countries. Borsa Istanbul Review, 25(4):709–721, 2025.
[5] Toufic Sarieddine. A tale of rice and copper: The china-pakistan economic-corridor. In A Tale of Rice and Copper: A World-Systems Analysis of Chinese Hegemony in Pakistan, pages 81–171. Springer, 2024.
[6] Atoosa Rezaei, Iheb Abdellatif, and Amjad Umar. Towards economic sustainability: A comprehensive review of artificial intelligence and machine learning techniques in improving the accuracy of stock market movements. International Journal of Financial Studies, 13(1), 2025.
[7] Elysee Nsengiyumva, Joseph K. Mung’atu, and Charles Ruranga. Hybrid garch-lstm forecasting for foreign exchange risk. FinTech, 4(2), 2025.
[8] Xi Tang and Yumei Xie. Exchange rate forecasting: A deep learning framework combining adaptive signal decomposition and dynamic weight optimization. International Journal of Financial Studies, 13(3), 2025.
[9] Mohamed Elhoseny, Noura Metawa, Gabor Sztano, and Ibrahim M El-Hasnony. Deep learning-based model for financial distress prediction. Annals of operations research, 345(2):885–907, 2025.
[10] Md Yeasin Rahat, Rajan Das Gupta, Nur Raisa Rahman, Sudipto Roy Pritom, Samiur Rahman Shakir, Md Imrul Hasan Showmick, and Md Jakir Hossen. Advancing exchange rate forecasting: Leveraging machine learning and ai for enhanced accuracy in global financial markets. arXiv preprint arXiv:2506.09851, 2025.
[11] Pedro Reis, Ana Paula Serra, and Jo˜ao Gama. The role of deep learning in financial asset management: A systematic review. arXiv preprint arXiv:2503.01591, 2025.
[12] Samreen Naeem, Wali Khan Mashwani, Aqib Ali, M Irfan Uddin, Marwan Mahmoud, Farrukh Jamal, and Christophe Chesneau. Machine learning-based usd/pkr exchange rate forecasting using sentiment analysis of twitter data. Computers, Materials & Continua, 67(3):3451–3461, 2021.
[13] Muhammad Yasir, Mehr Yahya Durrani, Sitara Afzal, Muazzam Maqsood, Farhan Aadil, Irfan Mehmood, and Seungmin Rho. An intelligent event-sentiment-based daily foreign exchange rate forecasting system. Applied Sciences, 9(15), 2019.
[14] Osama Wagdi, Eman Salman, and Hatem Albanna. Integration between technical indicators and artificial neural networks for the prediction of the exchange rate: Evidence from emerging economies. Cogent Economics & Finance, 11(2):2255049, 2023.
[15] Mira Tamer Shaker, Hadeer El-Batanouny, Mohamed Abdelsalam, and Yehia Helmy. Systematic re- view of machine learning approaches in forecasting economic growth and enhancing decent work opportunities: A comprehensive analysis. In 2024 6th International Conference on Computing and Informatics (ICCI), pages 377–392, 2024.
[16] Mohamed El Mahjouby, Mohamed Taj Bennani, Mohamed Lamrini, Badre Bossoufi, Thamer A. H. Alghamdi, and Mohamed El Far. Machine learning algorithms for forecasting and categorizing euro- to-dollar exchange rates. IEEE Access, 12:74211–74217, 2024.
[17] Francisco L´opez-Herrera, Jaime Gonz´alez Maiz Jim´enez, and Ad´an Reyes Santiago. Directional fore- casting for eight forex pairs against the us dollar using machine learning techniques. Discover Artificial Intelligence, 5(1):1–32, 2025.
[18] Pradeepta Kumar Sarangi, Muskaan Chawla, Pinaki Ghosh, Sunny Singh, and P.K. Singh. Forex trend analysis using machine learning techniques: Inr vs usd currency exchange rate using ann-ga hybrid approach. Materials Today: Proceedings, 49:3170–3176, 2022. National Conference on Functional Materials: Emerging Technologies and Applications in Materials Science.
[19] Elia Yathie Matsumoto, Emilio Del-Moral-Hernandez, Claudia Emiko Yoshinaga, and Afonso de Campos Pinto. Forecasting us dollar exchange rate movement with computational models and human behavior. Expert Systems with Applications, 194:116521, 2022.
[20] Jingyang Wang, Xiaoxiao Wang, Jiazheng Li, and Haiyao Wang. A prediction model of cnn-tlstm for usd/cny exchange rate prediction. IEEE Access, 9:73346–73354, 2021.
[21] Gurpreet Singh, Pradeepta Kumar Sarangi, Lekha Rani, Kapil Sharma, Sachin Sinha, Ashok KumarSahoo, and Bishnu Prasad Rath. Cnn-rnn based hybrid machine learning model to predict the currency exchange rate: Usd to inr. In 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), pages 1668–1672, 2022.
[22] Muhammad Atif Saeed and Akhtar Jamil. Stock price prediction in response to us dollar exchange rate using machine learning techniques. In International Conference on Computing, Intelligence and Data Analytics, pages 281–290. Springer, 2022.
[23] Sohail Akhtar, Maham Ramzan, Sajid Shah, Iftikhar Ahmad, Muhammad Imran Khan, Sadique Ah- mad, Mohammed A El-Affendi, and Humera Qureshi. Forecasting exchange rate of pakistan using time series analysis. Mathematical Problems in Engineering, 2022(1):9108580, 2022.
[24] Rabia Sabri, Abdul Aziz Abdul Rahman, Abdelrhman Meero, Liaqat Ali Abro, and Muhammad AsadUllah. Forecasting turkish lira against the us dollars via forecasting approaches. Cogent Eco- nomics & Finance, 10(1):2049478, 2022.
[25] Hafiz Muhammad Naveed, Pan Yanchun, Bilal Ahmed Memon, Shoaib Ali, and Jan Muhammad Sohu. Financial modelling system using deep neural networks (dnns) for financial risk assessments. International Social Science Journal, 75(255):137–154, 2025.
[26] Fernando Garc´ıa, Francisco Guijarro, Javier Oliver, and Rima Tamoˇsi¯unien˙e. Foreign exchange fore- casting models: Lstm and bilstm comparison. Engineering Proceedings, 68(1), 2024.
[27] Kinza Yousfani, Hasnain Iftikhar, Paulo Canas Rodrigues, El´ıas A. Torres Armas, and Javier Linkolk L´opez-Gonzales. Global shocks and local fragilities: A financial stress index approach to pakistan’s monetary and asset market dynamics. Economies, 13(8), 2025.
[28] El-Sayed M El-Kenawy, Faris H Rizk, Ahmed Mohamed Zaki, Mahmoud Elshabrawy, Abdelhameed Ibrahim, Abdelaziz A Abdelhamid, Nima Khodadadi, Ehab M ALmetwally, and Marwa M Eid. Nioa: A novel metaheuristic algorithm modeled on the stealth and precision of japanese ninjas. Journal of Artificial Intelligence in Engineering Practice, 1(2):17–35, 2024.
