CFP last date
28 January 2026
Call for Paper
February Edition
CAE solicits high quality original research papers for the upcoming February edition of the journal. The last date of research paper submission is 28 January 2026

Submit your paper
Know more
The week's pick
Responsive image
Machine Learning Models, Data Preprocessing Techniques and Suite of Metrics for Assessing Solar Power Forecasting: A Comprehensive Review

Asma A.M. Nagaraja
Random Articles
Reseach Article

A Ridge-Regularized Deep Learning Stacking Ensemble for Multivariate Daily Exchange Rate Forecasting in Emerging Markets: Evidence from the Ghana Forex Market

by Ernest Kwame Ampomah, Ezekiel Mensah Martey, Emmanuel Asante
journal cover thumbnail

Communications on Applied Electronics
Foundation of Computer Science (FCS), NY, USA
Volume 8 - Number 1
Year of Publication: 2025
Authors: Ernest Kwame Ampomah, Ezekiel Mensah Martey, Emmanuel Asante
10.5120/cae2025652919

Ernest Kwame Ampomah, Ezekiel Mensah Martey, Emmanuel Asante . A Ridge-Regularized Deep Learning Stacking Ensemble for Multivariate Daily Exchange Rate Forecasting in Emerging Markets: Evidence from the Ghana Forex Market. Communications on Applied Electronics. 8, 1 ( Dec 2025), 61-72. DOI=10.5120/cae2025652919

@article{ 10.5120/cae2025652919,
author = { Ernest Kwame Ampomah, Ezekiel Mensah Martey, Emmanuel Asante },
title = { A Ridge-Regularized Deep Learning Stacking Ensemble for Multivariate Daily Exchange Rate Forecasting in Emerging Markets: Evidence from the Ghana Forex Market },
journal = { Communications on Applied Electronics },
issue_date = { Dec 2025 },
volume = { 8 },
number = { 1 },
month = { Dec },
year = { 2025 },
issn = { 2394-4714 },
pages = { 61-72 },
numpages = {9},
url = { https://www.caeaccess.org/archives/volume8/number1/a-ridge-regularized-deep-learning-stacking-ensemble-for-multivariate-daily-exchange-rate-forecasting-in-emerging-markets-evidence-from-the-ghana-forex-market/ },
doi = { 10.5120/cae2025652919 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2025-12-31T19:48:15.215627+05:30
%A Ernest Kwame Ampomah
%A Ezekiel Mensah Martey
%A Emmanuel Asante
%T A Ridge-Regularized Deep Learning Stacking Ensemble for Multivariate Daily Exchange Rate Forecasting in Emerging Markets: Evidence from the Ghana Forex Market
%J Communications on Applied Electronics
%@ 2394-4714
%V 8
%N 1
%P 61-72
%D 2025
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Forecasting exchange rate remains a major challenge due to nonlinear dynamics, structural volatility, and complex cross-currency interactions. Although deep learning models have demonstrated strong predictive capability, however, the individual architectures often specialize in limited temporal patterns and may overfit volatile financial series. This study proposes a hybrid multivariate stacking ensemble that integrates Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), and Multi-Task Learning (MTL) models with a ridge-regression meta-learner to enhance predictive accuracy and stability. Daily EUR/GHS, GBP/GHS, and USD/GHS exchange rates from January 2010 to September 2025 were modeled using a sliding-window, multi-input, multi-output configuration. Performance was benchmarked against standalone deep learning models and a Vector Auto-Regression (VAR) baseline. Results show that the proposed hybrid multivariate stacking ensemble (TCN+LSTM+MTL) model achieves the lowest mean RMSE (0.7488), MAE (0.5285), MAPE (3.75 percent), and SMAPE (3.64 percent), representing approximately 89.7 percent and 92.7 percent RMSE reduction compared to VAR and LSTM, respectively. The findings confirm that combining specialized deep architectures with regularized meta-learning significantly improves forecasting accuracy and robustness in volatile financial markets and offers insights for future research in cross-architecture fusion and meta-learning for financial econometrics.

References
  1. Liu, S., Huang, Q., Li, M., &Wei, Y. (2024). A new LASSO-BiLSTM-based ensemble learning approach for exchange rate forecasting. Engineering Applications of Artificial Intelligence, 127, 107305.
  2. Alexandridis, A. K., Panopoulou, E., & Souropanis, I. (2024). Forecasting exchange rate volatility: An amalgamation approach. Journal of International Financial Markets, Institutions and Money, 97, 102067.
  3. Liu, J. (2021). Impact of uncertainty on foreign exchange market stability: Based on the LT-TVP-VAR model. China Finance Review International, 11(1), 53-72.
  4. Mate, C., & Jimeńez, L. (2021). Forecasting exchange rates with the iMLP: New empirical insight on one multi-layer perceptron for interval time series (ITS). Engineering Applications of Artificial Intelligence, 104, 104358.
  5. Cao, H., Lin, F., Li, Y., & Wu, Y. (2021). Information flow network of international exchange rates and influence of currencies. Entropy, 23(12), 1696.
  6. Antwi, A., Kyei, K. A., & Gill, R. S. (2020). The use of mutual information to improve value-at-risk forecasts for exchange rates. IEEE Access, 8, 179881-179900.
  7. Gamaliy, V., Shalimova, N., Zhovnovach, R., Zahreba, M., & Levchenko, A. (2018). Exchange rates: The influence of political and economic events. A fundamental analysis approach. Banks and Bank Systems, 13(4), 131-142.
  8. Picasso, A., Merello, S., Ma, Y., Oneto, L., & Cambria, E. (2019). Technical analysis and sentiment embeddings for market trend prediction. Expert Systems with Applications, 135, 60-70.
  9. Rubio, L., Palacio Pinedo, A., Mejía Castaño, A., & Ramos, F. (2023). Forecasting volatility by using wavelet transform, ARIMA and GARCH models. Eurasian Economic Review, 13(3), 803-830.
  10. Beckmann, J., Czudaj, R., & Feess, E. (2020). Forecasting with VAR models under structural breaks and regime shifts. Journal of Applied Econometrics, 35(3), 333–356.
  11. Han, C., Wang, Y., & Xu, Y. (2020). Nonlinearity and efficiency dynamics of foreign exchange markets: evidence from multifractality and volatility of major exchange rates. Economic research-Ekonomska istraživanja, 33(1), 731-751.
  12. Rossi, B. (2013). Exchange rate predictability. Journal of economic literature, 51(4), 1063-1119.
  13. Hassani, H., & Silva, E. S. (2015). Forecasting with big data: A review. Annals of Data Science, 2(1), 5-19.
  14. Rodrigues, P. C., Awe, O. O., Pimentel, J. S., & Mahmoudvand, R. (2020). Modelling the behaviour of currency exchange rates with singular spectrum analysis and artificial neural networks. Stats, 3(2), 137-157.
  15. Liu, Yang. 2019. Novel volatility forecasting using deep learning—Long Short Term Memory Recurrent Neural Networks. Expert Systems with Applications 132: 99–109.
  16. Kim, J., Kim, H., Kim, H., Lee, D., & Yoon, S. (2025). A comprehensive survey of deep learning for time series forecasting: architectural diversity and open challenges. Artificial Intelligence Review, 58(7), 1-95
  17. Aydin, A. D., & Cavdar, S. C. (2015). Comparison of prediction performances of artificial neural network (ANN) and vector autoregressive (VAR) Models by using the macroeconomic variables of gold prices, Borsa Istanbul (BIST) 100 index and US Dollar-Turkish Lira (USD/TRY) exchange rates. Procedia Economics and Finance, 30, 3-14.
  18. Dautel, A. J. (2020). Forex exchange rate forecasting using deep recurrent neural networks. Computational Economics, 56(1), 1–22.
  19. García, F., Guijarro, F., Oliver, J., & Tamošiūnienė, R. (2023). Foreign exchange forecasting models: ARIMA and LSTM comparison. Engineering Proceedings, 39(1), 81.
  20. Zhao, L., Zhang, X., & Li, Y. (2024). Prediction of currency exchange rate based on ARIMA, LSTM, and GRU models. Journal of Risk and Financial Management, 17(8), 332.
  21. Bejani, M. M., & Ghatee, M. (2021). A systematic review on overfitting control in shallow and deep neural networks. Artificial Intelligence Review, 54(8), 6391-6438.
  22. Madhulatha, T. S., & Ghori, D. M. A. S. (2025). Deep neural network approach integrated with reinforcement learning for forecasting exchange rates using time series data and influential factors. Scientific Reports, 15(1), 29009
  23. Lara-Benítez, P., Carranza-García, M., Luna-Romera, J. M., & Riquelme, J. C. (2020). Temporal convolutional networks applied to energy-related time series forecasting. applied sciences, 10(7), 2322..
  24. Zhang, Y., & Yang, Q. (2021). A survey on multi-task learning. IEEE Transactions on Knowledge and Data Engineering, 34(12), 5586–5609.
  25. Mienye, I. D., & Swart, T. G. (2024). A comprehensive review of deep learning: Architectures, recent advances, and applications. Information, 15(12), 755.
  26. Lin, Hualing, Qiubi Sun, and Sheng-Qun Chen. 2020. Reducing Exchange Rate Risks in International Trade: A Hybrid Forecasting Approach of CEEMDAN and Multilayer LSTM. Sustainability 12: 2451.
  27. Islam, M. S., & Hossain, E. (2021). Foreign exchange currency rate prediction using a GRU-LSTM hybrid network. Soft Computing Letters, 3, 100009.
  28. He, K., Yang, Q., Ji, L., Pan, J., & Zou, Y. (2023). Financial time series forecasting with the deep learning ensemble model. Mathematics, 11(4), 1054.
  29. Sina, L. B., Secco, C. A., Blazevic, M., & Nazemi, K. (2023). Hybrid forecasting methods—a systematic review. Electronics, 12(9), 2019.
  30. Gu, J., Zhang, S., Yu, Y., & Liu, F. (2025). AB-LSTM-GRU: A novel ensemble composite deep neural network model for exchange rate forecasting. Computational Economics, 66(2), 1767-1791.
  31. Sims, C. A. (1980). Macroeconomics and Reality. Econometrica, 48(1), 1–48.
  32. Mienye, I. D., Swart, T. G., & Obaido, G. (2024). Recurrent neural networks: A comprehensive review of architectures, variants, and applications. Information, 15(9), 517.
  33. Fan, J., Zhang, K., Huang, Y., Zhu, Y., & Chen, B. (2023). Parallel spatio-temporal attention-based TCN for multivariate time series prediction. Neural Computing and Applications, 35(18), 13109-13118.
  34. Zhang, Y., & Yang, Q. (2021). A survey on multi-task learning. IEEE transactions on knowledge and data engineering, 34(12), 5586-5609.
  35. Ghasemieh, A., Lloyed, A., Bahrami, P., Vajar, P., & Kashef, R. (2023). A novel machine learning model with Stacking Ensemble Learner for predicting emergency readmission of heart-disease patients. Decision analytics journal, 7, 100242.
Index Terms

Computer Science
Information Sciences

Keywords

Exchange Rate Forecasting Multivariate Modeling Stacking Ensemble Long Short-Term Memory Temporal Convolutional Network Multi-Task Learning Ridge Regression Meta-Learning Deep Learning Financial Time Series

Powered by PhDFocusTM