Decoding currency dynamics: A multiscale machine learning approach integrating economic indicators, ESG, and investor sentiment
-
Received December 1, 2024;Accepted June 23, 2025;Published July 4, 2025
-
Author(s)Link to ORCID Index: https://orcid.org/0000-0001-9820-3655
-
DOIhttp://dx.doi.org/10.21511/imfi.22(3).2025.03
-
Article InfoVolume 22 2025, Issue #3, pp. 27-48
- TO CITE АНОТАЦІЯ
- 5 Views
-
2 Downloads
This work is licensed under a
Creative Commons Attribution 4.0 International License
The foreign exchange market, characterized by high volatility and economic significance, requires accurate predictive models. This study investigates the application of the Temporal Fusion Transformer (TFT), enhanced with Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), for forecasting major foreign exchange (forex) currency pairs: USD/EUR, USD/JPY, USD/CNY, USD/AUD, and USD/INR. The proposed framework integrates a wide range of economic indicators, which include interest rate differentials, GDP growth, and trade balances, alongside investor sentiment derived from Twitter and ESG-related news sentiment. By addressing the non-linear, multiscale nature of forex time series, the CEEMDAN-TFT model facilitates improved signal decomposition and interpretability. Empirical results indicate that the model demonstrates competitive performance across all five currency pairs, with the USD/EUR pair exhibiting the highest predictive accuracy. Other pairs, exhibiting good predictive accuracy, include USD/JPY and USD/CNY, underscoring the model’s adaptability to varying economic contexts. Performance is assessed using multiple error metrics, and the model is benchmarked against standard neural network approaches (MLP, RNN, LSTM, CNN). Variable importance analysis highlights the dynamic influence of interest rates, investor sentiment, and ESG factors across different market regimes. This study provides empirical evidence that including ESG and investor sentiment can improve the accuracy of currency forecasting models. This study provides guidance and a framework for informed decision-making for traders, analysts, and policymakers.
- Keywords
-
JEL Classification (Paper profile tab)C53, F31, G17, Q56
-
References44
-
Tables5
-
Figures17
-
- Figure 1. Daily rate movements of the USD and EUR pair
- Figure 2. Daily rate movements of the USD and JPY pair
- Figure 3. Daily rate movements of the USD and CNY pair
- Figure 4. Daily rate movements of the USD and AUD pair
- Figure 5. Daily rate movements of the USD and INR pair
- Figure 6. CEEMDAN decomposition of the USD/EUR exchange rate into Intrinsic Mode Functions (IMFs) and a residual trend
- Figure 7. CEEMDAN decomposition of the USD/JPY exchange rate
- Figure 8. CEEMDAN decomposition of the USD/CNY exchange rate
- Figure 9. CEEMDAN decomposition of the USD/AUD exchange rate
- Figure 10. CEEMDAN decomposition of the USD/INR exchange rate
- Figure 11. Model performance across time horizons
- Figure 12. Model forecast for USD/EUR
- Figure 13. Model forecast for USD/JPY
- Figure 14. Model forecast for USD/CNY
- Figure 15. Model forecast for USD/AUD
- Figure 16. Model forecast for USD/INR
- Figure 17. Attention weights of key variables across currency pairs
-
- Table 1. Variables employed in the forecasting model
- Table 2. Descriptive statistics
- Table 3. ADF, PP, and KPSS tests for a random walk
- Table 4. CEEMDAN-TFT and other models in-sample results
- Table 5. CEEMDAN-TFT and other model out-of-sample results
-
- Abdel Magid, A., Hussainey, K., De Andrés, J., & Lorca, P. (2023). The moderating role of online social media in the relationship between corporate social responsibility disclosure and investment decisions: evidence from Egypt. International Journal of Financial Studies, 11(2), 60.
- Abraham, B. (1982). Temporal Aggregation and Time Series. International Statistical Review / Revue Internationale de Statistique, 50(3), 285.
- Alexander, D., & Thomas, L. R. (1987). Monetary/asset models of exchange rate determination. How well have they performed in the 1980’s? International Journal of Forecasting, 3(1), 53-64.
- Bekiros, S., & Marcellino, M. (2013). The multiscale causal dynamics of foreign exchange markets. Journal of International Money and Finance, 33, 282-305.
- Bhattacharya, B. (2012). Causal relationship between stock market and exchange rate, foreign exchange reserves and value of trade balance in India: An Empirical analysis.
- Bose, D., Aithal, P., & Roy, S. (2021). Survey of Twitter Viewpoint on Application of Drugs by VADER Sentiment Analysis among Distinct Countries. International Journal of Management.
- Cao, J., Li, Z., & Li, J. (2019). Financial time series forecasting model based on CEEMDAN and LSTM. Physica A: Statistical Mechanics and Its Applications, 519, 127-139.
- Chen, Y. C., Rogoff, K. S., & Rossi, B. (2010). Can exchange rates forecast commodity prices? Quarterly Journal of Economics, 125(3), 1145-1194.
- Chen, Y., Zheng, Y., Lv, G., Gu, Y., & Zhang, W. (2024). Quantifying the effect of ESG-related news on Chinese stock movements. Journal of Environmental Management, 354, 120301.
- De Myttenaere, A., Golden, B., Le Grand, B., & Rossi, F. (2016). Mean absolute percentage error for regression models. Neurocomputing, 192, 38-48.
- Embrechts, M. J. (1995). Forecasting foreign exchange rates with artificial neural networks. Intelligent Engineering Systems Through Artificial Neural Networks, 5(1), 771-778.
- Engle, R. (2001). GARCH 101: The Use of ARCH/GARCH Models in Applied Econometrics. Journal of Economic Perspectives, 15(4), 157-168.
- Fama, E. F. (1970). Efficient Capital Markets. The Journal of Finance, 25(2), 383-417.
- Fratzscher, M., Gloede, O., Menkhoff, L., Sarno, L., & Stöhr, T. (2019). When is Foreign exchange intervention effective? Evidence from 33 countries. American Economic Journal: Macroeconomics, 11(1), 132-156.
- Guo, W., & Chen, Z. (2023). China–US economic and trade relations, trade news, and short-term fluctuation of the RMB exchange rate. Review of International Economics, 31(1), 180-203.
- Heiden, S., Klein, C., & Zwergel, B. (2013). Beyond fundamentals: Investor sentiment and exchange rate forecasting. European Financial Management, 19(3), 558-578.
- Hong, C., & Zu, W. (2024). A Twofold Model for Exchange Rate Forecasting: Combining Fundamentals and Market Dynamics. Journal of Business and Economic Options, 7(4), 42-52.
- Hornik, K. (1991). Approximation capabilities of multilayer feedforward networks. Neural Networks, 4(2), 251-257.
- Huang, X., Wang, Y., & Li, H. (2024). Exploring the asymmetric influence of economic policy uncertainty on the nonlinear relationship between exchange rate and carbon prices in China. North American Journal of Economics and Finance, 73.
- Huy, P. C., Minh, N. Q., Tien, N. D., & Anh, T. T. Q. (2022). Short-Term Electricity Load Forecasting Based on Temporal Fusion Transformer Model. IEEE Access, 10, 106296-106304.
- Ito, T., & Sato, K. (2008). Exchange rate changes and inflation in post-crisis Asian economies: Vector autoregression analysis of the exchange rate pass-through. Journal of Money, Credit and Banking, 40(7), 1407-1438.
- Jan, J. H., & Gopalaswamy, A. K. (2019). Identifying factors in currency exchange rate estimation: a study on AUD against USD. Journal of Advances in Management Research, 16(4), 436-452.
- Kourentzes, N., Petropoulos, F., & Trapero, J. R. (2014). Improving forecasting by estimating time series structural components across multiple frequencies. International Journal of Forecasting, 30(2), 291-302.
- Kumar, J. S., & Aluvala, R. (2020). Impact of selected economic variables on the USD/INR exchange rate. International Journal of Management (IJM), 11(7).
- Lim, B., Arık, S., Loeff, N., & Pfister, T. (2021). Temporal Fusion Transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting, 37(4), 1748-1764.
- MacDonald, R. (2007). Exchange rate economics: Theories and evidence. In Exchange Rate Economics: Theories and Evidence. Routledge Taylor & Francis Group.
- Meese, R. A., & Rogoff, K. (1983). Empirical exchange rate models of the seventies. Do they fit out of sample? Journal of International Economics, 14(1-2), 3-24.
- Mehta, P., Pandya, S., & Kotecha, K. (2021). Harvesting social media sentiment analysis to enhance stock market prediction using deep learning. PeerJ Computer Science, 7, 1-21.
- Menkhoff, L., & Taylor, M. P. (2007). The obstinate passion of foreign exchange professionals: Technical analysis. Journal of Economic Literature, 45(4), 936-972.
- Mohammadipour, M., & Boylan, J. E. (2012). Forecast horizon aggregation in integer autoregressive moving average (INARMA) models. Omega, 40(6), 703-712.
- Panda, M. M., Panda, S. N., & Pattnaik, P. K. (2022). Forecasting foreign currency exchange rate using convolutional neural network. International Journal of Advanced Computer Science and Applications, 13(2), 607-616.
- Plakandaras, V., Papadimitriou, T., & Gogas, P. (2015). Forecasting daily and monthly exchange rates with machine learning techniques. Journal of Forecasting, 34(7), 560-573.
- Safari Bideskan, S., Mehrazeen, A. R., Shorvarzi, M., & Masihabadi, A. (2022). Have hashtags and cashtags caused a slight reaction to stock returns in financial statements? Has the information content of the financial statements been lost? Case study: S & P500 companies. International Journal of Nonlinear Analysis and Applications, 13(1), 3029-3057.
- Sharma, S., Aggarwal, V., & Yadav, M. P. (2021). Comparison of linear and non-linear GARCH models for forecasting volatility of select emerging countries. Journal of Advances in Management Research, 18(4), 526-547.
- Simpson, J. L. (2002). The relationship between commodity prices and the Australian dollar. SSRN Electronic Journal.
- Steuer, S., & Tröger, T. H. (2022). The role of disclosure in green finance. Journal of Financial Regulation, 8(1), 1-50.
- Suman, S., & Raju, G. (2024). Dynamic Interaction Between the Nifty Index and Exchange Rate: Evidence from VAR Analysis. Educational Administration: Theory and Practice, 30(5), 5479-5487.
- Tang, T. C. (2005). Does exchange rate volatility matter for the balancing item of balance of payments accounts in Japan? An empirical note. International Review of Economics and Business, 52(4), 581-590.
- Torres, M. E., Colominas, M. A., Schlotthauer, G., & Flandrin, P. (2011). A complete ensemble empirical mode decomposition with adaptive noise. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4144-4147.
- Weigend, A. S., Huberman, B. A., & Rumelhart, D. E. (1992). Predicting Sunspots and Exchange Rates with Connectionist Networks. In Nonlinear modeling and forecasting, 12(1991), 395-432).
- Yilmaz, F. M., & Arabaci, O. (2021). Should deep learning models be in high demand, or should they simply be a very hot topic? A comprehensive study for exchange rate forecasting. Computational Economics, 57(1), 217-245.
- Zhang, H., Zou, Y., Yang, X., & Yang, H. (2022). A temporal fusion transformer for short-term freeway traffic speed multistep prediction. Neurocomputing, 500, 329-340.
- Zhang, W., Qu, Z., Zhang, K., Mao, W., Ma, Y., & Fan, X. (2017). A combined model based on CEEMDAN and modified flower pollination algorithm for wind speed forecasting. Energy Conversion and Management, 136, 439-451.
- Zhao, L., Yao, D., Yang, B., & Zhu, K. (2024). The Impact of China-United States Trade War on the Relationship Among the Exchange Rates: The Case of China, Korea, and Japan. Machine Learning for Econometrics and Related Topics, 489-499.
-
-
Conceptualization
Sougata Banerjee
-
Data curation
Sougata Banerjee
-
Formal Analysis
Sougata Banerjee
-
Investigation
Sougata Banerjee
-
Methodology
Sougata Banerjee
-
Project administration
Sougata Banerjee
-
Resources
Sougata Banerjee
-
Software
Sougata Banerjee
-
Supervision
Sougata Banerjee
-
Validation
Sougata Banerjee
-
Visualization
Sougata Banerjee
-
Writing – original draft
Sougata Banerjee
-
Writing – review & editing
Sougata Banerjee
-
Conceptualization
-
Machine learning for robo-advisors: testing for neurons specialization
Investment Management and Financial Innovations Volume 16, 2019 Issue #4 pp. 205-214 Views: 3253 Downloads: 586 TO CITE АНОТАЦІЯThe rise of robo-advisor wealth management services, which constitute a key element of fintech revolution, unveils the question whether they can dominate human-based advice, namely how to address the client’s behavioral biases in an automated way. One approach to it would be the application of machine learning tools during client profiling. However, trained neural network is often considered as a black box, which may raise concerns from the customers and regulators in terms of model validity, transparency, and related risks. In order to address these issues and shed more light on how neurons work, especially to figure out how they perform computation at intermediate layers, this paper visualizes and estimates the neurons’ sensitivity to different input parameters. Before it, the comprehensive review of the most popular optimization algorithms is presented and based on them respective data set is generated to train convolutional neural network. It was found that selected hidden units to some extent are not only specializing in the reaction to such features as, for example, risk, return or risk-aversion level but also they are learning more complex concepts like Sharpe ratio. These findings should help to understand robo-advisor mechanics deeper, which finally will provide more room to improve and significantly innovate the automated wealth management process and make it more transparent.
-
The effect of investor sentiment on the means of earnings management
Investment Management and Financial Innovations Volume 15, 2018 Issue #1 pp. 10-17 Views: 1645 Downloads: 576 TO CITE АНОТАЦІЯPrior research has shown that a firm’s tendency to meet or beat earning targets is greater during bad economic times than good times. The paper extends this line of research by investigating which means of earnings management is used in different states of economy. A sample of non-financial companies listed on Korea Securities Market from 2003 to 2011 is used for empirical tests. The findings of this study are summarized as follows. The magnitude of discretionary accruals is negatively related to investment sentiment, indicating that firms tend to use positive discretionary accruals to manipulate reported income upward when the sentiment is pessimistic. However, the real activity based earnings management is not significantly associated with the state of economy. Collectively, this study contributes to behavioral finance and accounting literature by suggesting that managers use discretionary portion of accruals, but do not change their real operating activities, in order to meet or beat earnings targets in economic downturn.
-
Modeling and predicting earnings per share via regression tree approaches in banking sector: Middle East and North African countries case
Investment Management and Financial Innovations Volume 17, 2020 Issue #2 pp. 51-68 Views: 1637 Downloads: 586 TO CITE АНОТАЦІЯThe regression tree approach is an effective and easy to interpret technique where it utilizes a recursive binary partitioning algorithm that divides the sample into partitioning variables with the strongest correlation to the response variable. Earnings per share can be considered as one of the main factors in making the investment decision. This study aims to build a predictive model for earnings per share in the context of the Middle East and North African countries (MENA) . The sample of the study consists of sixty-three banks, which were chosen from eight countries, with a total of six-hundred thirty observations. The simple regression, regression tree, and its pruned regression tree, conditional inference tree, and cubist regression are used to build the predictive model for earnings per share that depends on total assets, total liability, bank book value, stock volatility, age of the bank, and net cash. The results show that the cubist regression is outperforming other approaches where it improves root mean square error for the predictive model by approximately double in comparison with other methods. More interesting results are obtained from the important scores, where it shows that the total assets of the bank, bank book value, and total liability have the biggest impact on the prediction of earnings per share. Also, the cubist regression gives an improvement in R-squared over other methods by at least 30% and 23% using training and testing data, respectively.