Global Economic Cycles Unveiled: A Hybrid TCN-HMM Approach for Regime Dynamics Across Eight Nations

Bahaa Aly, Tarek (2026): Global Economic Cycles Unveiled: A Hybrid TCN-HMM Approach for Regime Dynamics Across Eight Nations.

Abstract

This study developed a hybrid Temporal Convolutional Network and Hidden Markov Model (TCN-HMM) framework to identify economic regimes across eight nations: Brazil, China, Egypt, Indonesia, Mexico, South Africa, United Kingdom, and United States, using GDP, inflation, policy rates, equity indices, exchange rates, and yield curve factors. The method integrated MSSA-smoothed data with a TCN autoencoder to extract multi-scale temporal features, optimized through sensitivity analysis, followed by an HMM to classify three regimes: Natural State, Substantial Growth, and Restrictive Policy. The TCN-HMM outperformed standalone HMMs in capturing non-linear dynamics and temporal dependencies. Key findings highlighted several insights. Twelve extracted features were optimal, outperforming eight features (the number of original variables), implying that the TCN enhanced regime differentiation through a richer feature representation. Furthermore, the framework demonstrated generalizability across the panel, as developing markets like Brazil and Egypt exhibited volatile inflation, while developed economies showed stable policy transmission. Finally, CHI maintained very high growth rates across all regimes, and currencies across the panel showed a high correlation with real interest rates rather than with overall economic conditions, reflecting their sensitivity to capital-flow dynamics.

• Item Type: MPRA Paper
• Language: English
• Keywords: TCN, HMM, Economic Regime, Temporal Dependencies, Non-linear dynamics
• Subjects: C - Mathematical and Quantitative Methods > C3 - Multiple or Simultaneous Equation Models ; Multiple Variables > C32 - Time-Series Models ; Dynamic Quantile Regressions ; Dynamic Treatment Effect Models ; Diffusion Processes ; State Space Models; C - Mathematical and Quantitative Methods > C4 - Econometric and Statistical Methods: Special Topics > C45 - Neural Networks and Related Topics; C - Mathematical and Quantitative Methods > C5 - Econometric Modeling > C53 - Forecasting and Prediction Methods ; Simulation Methods; E - Macroeconomics and Monetary Economics > E3 - Prices, Business Fluctuations, and Cycles > E37 - Forecasting and Simulation: Models and Applications

References

Ahmed, R., Vveinhardt, J., Streimikiene, D., & Fayyaz, M. (2017). Multivariate Granger Causality Between Macro Variables and KSE 100 Index: Evidence from Johansen cointegration and Toda & Yamamoto Causality. Economic Research, 30(1), 1497–1521. Retrieved from https://www.tandfonline.com/doi/full/10.1080/1331677X.2017.1340176

Ang, A., & Bekaert, G. (2002). International asset allocation with regime shifts. The Review of Financial Studies, 15(4), 1137–1187. Retrieved from https://business.columbia.edu/sites/default/files-efs/pubfiles/1971/1137.pdf

Atif, D. (2024). Enhancing long-term GDP forecasting with advanced hybrid models: A comparative study of ARIMA-LSTM and ARIMA-TCN with dense regression. Computational Economics, 65, 3447–3473. Retrieved from https://www.researchgate.net/publication/382301074_Enhancing_Long-Term_GDP_Forecasting_with_Advanced_Hybrid_Models_A_Comparative_Study_of_ARIMA-LSTM_and_ARIMA-TCN_with_Dense_Regression

Bagliano, F., & Morana, C. (2010). Business cycle comovement in the G-7: Common shocks or common transmission mechanisms? Applied Economics, 42(18), 2327–2345. Retrieved from https://www.tandfonline.com/doi/epdf/10.1080/00036840701858067?needAccess=true

Bagliano, F., & Morana, C. (2010). The Great Recession: US dynamics and spillovers to the world economy (Working Paper No. 103). Carlo Alberto Notebooks. Retrieved from https://www.cerp.carloalberto.org/wp-content/uploads/2010/11/wp_103.pdf

Bahaa Ali, T. (2023). Yield Curves and Macro Variables: Interactions and Predictions (Doctoral dissertation, University of Plymouth). University of Plymouth. Retrieved from https://pearl.plymouth.ac.uk/pbs-theses/1/

Bahaa Aly, T. (2025). Nonlinear Macroeconomic Granger Causality: An ANN Input Occlusion Approach on MSSA-Denoised Data (MPRA Paper No. 125453). Munich Personal RePEc Archive. Retrieved from https://mpra.ub.uni-muenchen.de/125453/

Bai, S., Kolter, J., & Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271. Retrieved from https://arxiv.org/abs/1803.01271

Chauvet, M., & Hamilton, J. (2005). Dating business cycle turning points (NBER Working Paper No. 11422). National Bureau of Economic Research. Retrieved from https://www.nber.org/system/files/working_papers/w11422/w11422.pdf

Chauvet, M., & Piger, J. (2003). Identifying business cycle turning points in real time. Federal Reserve Bank of St. Louis Review, 85(2), 47–61. Retrieved from https://jeremypiger.com/assets/files/Chauvet_Piger_2003_FRBSTLReview.pdf

Danaa, A., Yakubu, A., Abukari, A., & Mumin, D. (2024). Hidden Markov Model and Deep Neural Network hybrid model for enhanced speech recognition. Journal of Modern Science and Computational Methods. Retrieved from https://www.researchgate.net/publication/382694587_Hidden_Markov_Model_and_Deep_Neural_Network_Hybrid_Model_for_Enhanced_Speech_Recognition

Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.

Guidolin, M. (2011). Markov switching models in empirical finance (IGIER Working Paper No. 415). Bocconi University. Retrieved from https://repec.unibocconi.it/igier/igi/wp/2011/415.pdf

Guidolin, M., & Timmermann, A. (2007). Asset allocation under multivariate. Journal of Economic Dynamics and Control, 31(11). Retrieved from https://www.sciencedirect.com/science/article/pii/S0165188906002272

Hamilton, J. (1989). A new approach to the economic analysis of nonstationary time series and the business cycle. Econometrica, 57(2), 357–384. Retrieved from https://www.jstor.org/stable/pdf/1912559.pdf?refreqid=fastly-default%3A181fa8feea3546dec9d8598297f294a0&ab_segments=&initiator=&acceptTC=1

Kaya, H. (2013). The yield curve and macroeconomic variables in the presence of policy change: Evidence from Turkey. Economic Modelling, 32, 100-107. Retrieved from https://www.sciencedirect.com/science/article/pii/S026499931300045X

Kearns, J., & Manners, P. (2005). The Impact Of Monetary Policy On The Exchange Rate: A Study Using Intraday Data. Discussion Paper. Retrieved from https://www.rba.gov.au/publications/rdp/2005/pdf/rdp2005-02.pdf

Kim, C.-J., & Nelson, C. (1998). Business cycle turning points, a new coincident index, and tests of duration dependence based on a dynamic factor model with regime switching. The Review of Economics and Statistics, 80(2), 188–201. Retrieved from https://www.jstor.org/stable/2646631?if_data=e30%3D

Kritzman, M., Page, S., & Turkington, D. (2012). Regime shifts: Implications for dynamic strategies. Financial Analysts Journal, 68(3), 22–39. Retrieved from https://www.tandfonline.com/doi/epdf/10.2469/faj.v68.n3.3?needAccess=true

Krolzig, H. (2001). Business cycle measurement in the presence of structural change: International evidence. International Journal of Forecasting, 17(3), 349–368. Retrieved from https://ideas.repec.org/a/eee/intfor/v17y2001i3p349-368.html

Laopodis, N. (2013). Monetary Policy And Stock Market Dynamics Across Monetary Regimes. Journal of International Money and Finance, 33, 381-406. Retrieved from https://www.sciencedirect.com/science/article/abs/pii/S0261560612001635

Lea, C., Flynn, M., Vidal, R., Reiter, A., & Hager, G. (2016). Temporal convolutional networks for action segmentation and detection. arXiv preprint arXiv:1611.05267. Retrieved from https://arxiv.org/abs/1611.05267#

Liu, D., Honoré, A., Chatterjee, S., & Rasmussen, L. (2020). Powering hidden Markov model by neural network based generative models. arXiv preprint arXiv:1910.05744. Retrieved from https://arxiv.org/abs/1910.05744

Rimella, L., & Whiteley, N. (2025). Hidden Markov neural networks. Entropy, 27(2), 168. Retrieved from https://www.mdpi.com/1099-4300/27/2/168

Rundle, R., & Medda, F. (2019). Macroeconomic regime identification using a two-step approach with Independent Component Analysis and Hidden Markov Models. SSRN Electronic Journal. Retrieved from https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3391292

Wang, M., Lin, Y.-H., & Mikhelson, I. (2020). Regime-switching factor investing with hidden Markov models. Journal of Risk and Financial Management, 13(12), 311. Retrieved from https://www.mdpi.com/1911-8074/13/12/311

Yang, Y. (2025). TCN-QV: An attention-based deep learning method for long sequence time-series forecasting of gold prices. PLOS ONE, 20(5). Retrieved from https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0319776