Prague Economic Papers 2025, 34(4):495-558 | DOI: 10.18267/j.pep.898

Do Machine Learning Techniques Outperform Autoregressive Distributed Lag Models in Inflation Forecasting?

Bogdan Oancea ORCID..., Mihaela Simionescu ORCID..., Richard Pospisil ORCID...
Bogdan Oancea, Department of Applied Economics and Quantitative Analysis, University of Bucharest, Bd. Regina Elisabeta no. 4-12, Sector 3, 030108 Bucharest, Romania, National Institute of Research and Development for Biological Sciences, Splaiul Independenței 296, 060031 Bucharest, Romania
Mihaela Simionescu, Department of Applied Economics and Quantitative Analysis, University of Bucharest, Bd. Regina Elisabeta no. 4-12, Sector 3, 030108 Bucharest, Romania, Institute for Economic Forecasting, Romanian Academy, Bucharest, Romania, Academy of Romanian Scientists, Ilfov 3, 050044 Bucharest, Romania
Richard Pospisil (Corresponding author), Tomas Bata University in Zlin, Faculty of Logistics & Crisis Management, Zlin, Czech Republic

Following the COVID-19 pandemic, Romania and other Central and Eastern European (CEE) countries faced some of the highest inflation rates in the European Union, creating a pressing need for accurate short-term forecasts to guide monetary policy. This study compares modern machine learning (ML) methods - Long Short-Term Memory (LSTM) neural networks, Random Forests (RF) and Support Vector Regression (SVR) - with traditional Autoregressive Distributed Lag (ARDL) models in forecasting Harmonised Index of Consumer Prices. Using quarterly data for Romania (2006Q1-2023Q4) and monthly data for nine CEE economies (2006M1-2025M3), we incorporate unemployment and sentiment indicators derived from the Romanian Central Bank reports and the European Commission's Economic Sentiment Indicator (ESI). We further evaluate model performance through simulation experiments that include high persistence, moving-average non-invertibility, nonlinear regimes, and structural breaks. Across both empirical and LSTM and SVR models - they frequently deliver lower forecast errors than ARDL, with LSTM achieving up to 53% reductions in mean squared error relative to naïve benchmarks. However, ARDL remains competitive when sentiment indices are the main predictor. These findings highlight that while advanced ML models can capture nonlinear dynamics and regime changes, traditional econometric tools still provide valuable robustness, particularly in sentiment-driven contexts. Overall, integrating ML, econometric approaches, and sentiment analysis offers a more reliable toolkit for short-horizon inflation forecasting under economic uncertainty.

Klíčová slova: Inflation, Long Short-Term Memory neural networks, Random Forests, Support Vector Regression, Autoregressive Distributed Lag models.
JEL classification: C51, C53, E31

Vloženo: 20. březen 2025; Revidováno: 11. září 2025; Přijato: 10. říjen 2025; Zveřejněno online: 19. prosinec 2025; Zveřejněno: 22. prosinec 2025  Zobrazit citaci

ACS AIP APA ASA Harvard Chicago Chicago Notes IEEE ISO690 MLA NLM Turabian Vancouver
Oancea, B., Simionescu, M., & Pospisil, R. (2025). Do Machine Learning Techniques Outperform Autoregressive Distributed Lag Models in Inflation Forecasting? Prague Economic Papers, 34(4), 495-558. doi: 10.18267/j.pep.898
Stáhnout citaci
  • BibTeX (.bib)
  • Bookends (.ris)
  • EasyBib (.ris)
  • EndNote (.enw)
  • EndNote 8 (.xml)
  • ISI WoS (.isi)
  • Medlars (.medlars)
  • Mendeley (.ris)
  • MODS (.xml)
  • Papers (.ris)
  • RefWorks (.txt)
  • RefManager (.ris)
  • RIS (.ris)
  • MS Word (.xml)
  • Zotero (.ris)
    • Zobrazit celý článek

    Reference

    1. Abadi, M.; et al. (2016). TensorFlow: A System for Large-Scale Machine Learning. In Proc. 12th USENIX Symp. Oper. Syst. Des. Implement.; pp 265-283. https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf
    2. Ahsan, M. D. Manjurul; Mahmud, M. A. Parvez; Saha, P. K.; Gupta, K. D.; Siddique, Z. (2021). Effect of Data Scaling Methods on Machine Learning Algorithms and Model Performance. Technologies, 9(3), 52. https://doi.org/10.3390/technologies9030052. Přejít k původnímu zdroji...
    3. Almosova, A., Andresen, N. (2023). Nonlinear inflation forecasting with recurrent neural networks. J. Forecasting, 42(3), 240-259. https://doi.org/10.1002/for.2901 Přejít k původnímu zdroji...
    4. Bahdanau, D.; Cho, K.; Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. In Proc. 3rd Int. Conf. Learn. Representations (ICLR). https://arxiv.org/pdf/1409.0473
    5. Bańbura, M., Bobeica, E. (2020). Does the Phillips curve help to forecast euro area inflation? ECB Working Paper Series, No 2471. European Central Bank. https://www.ecb.europa.eu/pub/pdf/scpwps/ecb.wp2471~fc87caada8.en.pdf
    6. Basak, D.; Pal, S.; Patranabis, D. C. (2007). Support Vector Regression. Neural Inf. Process. Lett. Rev., 11(10), 203-224. https://www.researchgate.net/publication/228537532_Support_Vector_Regression
    7. Beck, E., Wolf, M. (2025). Forecasting Inflation with the Hedged Random Forest. Policy Brief No. 1250, SUERF - The European Money and Finance Forum. https://www.suerf.org/wp-content/uploads/2025/09/SUERF-Policy-Brief-1250-_Beck.Wolf_.pdf Přejít k původnímu zdroji...
    8. Benett, J., Owyang, M. (2022). On the Relative Performance of Inflation Forecasts. Federal Reserve Bank of St. Louis. Staff Rep. No. 214/2022. https://doi.org/10.20955/r.104.131-48 Přejít k původnímu zdroji...
    9. Boaretto, G., Medeiros, M. C. (2023). Forecasting inflation using disaggregates and machine learning, arXiv preprint arXiv:2308.11173. https://doi.org/10.48550/arXiv.2308.11173. Přejít k původnímu zdroji...
    10. Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324 Přejít k původnímu zdroji...
    11. Biau, G., Scornet, E. (2016). Random Forest Guided Tour. TEST, 25, 197-227. https://doi.org/10.1007/s11749-016-0481-725 (2). Přejít k původnímu zdroji...
    12. Chalmovianský, J., Porqueddu, M., Sokol, A. (2020). Weigh(t)ing the basket: aggregate and component-based inflation forecasts for the euro area. ECB Working Paper Series, No 2501, European Central Bank. https://www.ecb.europa.eu/pub/pdf/scpwps/ecb.wp2501~8797484f4b.en.pdf
    13. Chollet, F. (2015). Keras: The Python Deep Learning Library. [Retrieved 2024-10-01]Available at: https://keras.io.
    14. Cissoko, M. B. H., Castelain, V., Lachiche, N. (2025). Multi-Way Adaptive Time Aware LSTM for Irregularly Collected Sequential ICU Data. Expert Syst. Appl. 261, 125548. https://doi.org/10.1016/j.eswa.2024.125548. Přejít k původnímu zdroji...
    15. Clements, M.P., Reade, J.J., 2020. Forecasting and forecast narratives: The Bank of England inflation reports. International Journal of Forecasting, 36(4), 1488-1500. https://doi.org/10.1016/j.ijforecast.2019.08.013 Přejít k původnímu zdroji...
    16. Cutler, D. R.; Edwards, T. C., Jr.; Beard, K. H.; Cutler, A.; Hess, K. T.; Gibson, J.; Lawler, J. J. (2007). Random Forests for Classification in Ecology. Ecology, 88(11), 2783-2792. Přejít k původnímu zdroji...
    17. https://doi.org/10.1890/07-0539.1 Přejít k původnímu zdroji...
    18. Dang, P. N., Dang, T. V. D., Nguyen, T. M. T., Vu, Q. K., Nguyen, A. H. (2025). Sentiment index as a predictor of CPI: A lexicon-based approach using economic news data in Vietnam. Journal of Open Innovation: Technology, Market, and Complexity, 11(3), 100620. https://doi.org/10.1016/j.joitmc.2025.100620. Přejít k původnímu zdroji...
    19. Drucker, H.; Burges, C. J. C.; Kaufman, L.; Smola, A.; Vapnik, V. (1997). Support Vector Regression Machines. In Adv. Neural Inf. Process. Syst., 9, 155-161. https://proceedings.neurips.cc/paper_files/paper/1996/file/d38901788c533e8286cb6400b40b386d-Paper.pdf
    20. Eugster, P., Uhl, M. (2024). Forecasting Inflation Using Sentiment. Economics Letters. Vol. 236(3), 111575. https://doi.org/10.1016/j.econlet.2024.111575 Přejít k původnímu zdroji...
    21. Faust, J., Wright, J. (2013). Forecasting Inflation. Handbook of Economic Forecasting. 1(2), p. 2-56. https://doi.org/10.1016/B978-0-444-53683-9.00001-3 Přejít k původnímu zdroji...
    22. Fulton, Ch., Hubrich, K. (2021). Forecasting Real Inflation in Real Time. Econometrics. 9 (4), 36. https://doi.org/10.3390/econometrics9040036 Přejít k původnímu zdroji...
    23. Gers, F. A., Schmidhuber, J., Cummins, F. (2000). Learning to Forget: Continual Prediction with LSTM. Neural Comput. 12(10), 2451-2471. https://doi.org/10.1162/089976600300015015. Přejít k původnímu zdroji...
    24. Graves, A., Liwicki, M., Fernandez, S., Bertolami, R., Bunke, H., Schmidhuber, J. (2009). A Novel Connectionist System for Unconstrained Handwriting Recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 855-868. https://doi.org/10.1109/TPAMI.2008.137. Přejít k původnímu zdroji...
    25. Groen, J., Paap, R., Ravazzolo, F. (2012). Real Time Inflation Forecasting in Changing World. Federal Reserve Bank of New York. Staff Rep. No. 388. https://resources.newyorkfed.org/medialibrary/media/research/staff_reports/sr388.pdf Přejít k původnímu zdroji...
    26. Grothe M., Meyler, A. (2015). Inflation Forecasts: Are Marked Based and Survey Based Measures Informative? ECB: Working Paper Series. 1865(11). https://www.ecb.europa.eu/pub/pdf/scpwps/ecbwp1865.en.pdf
    27. Han, J., Kamber, M., Pei, J. (2011). Data Mining: Concepts and Techniques, 3rd ed.; Morgan Kaufmann: Burlington, MA.
    28. Hochreiter, S., Schmidhuber, J. (1997). Long Short-Term Memory. Neural Comput. 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735 Přejít k původnímu zdroji...
    29. Hong, Y., Jiang, F., Meng, L., Xue, B. (2024). Forecasting Inflation Using Economic Narratives. Journal of Business and Economic Statistics. 43(1), 216-231. https://doi.org/10.1080/07350015.2024.2347619 Přejít k původnímu zdroji...
    30. Hoque, K. E., Aljamaan, H. (2021). Impact of Hyperparameter Tuning on Machine Learning Models in Stock Price Forecasting. IEEE Access, 9, 163815-163830. https://doi.org/10.1109/ACCESS.2021.3134138. Přejít k původnímu zdroji...
    31. Hyndman, R. J., Koehler, A. B. (2006). Another Look at Measures of Forecast Accuracy. Int. J. Forecast. 22(4), 679-688. https://doi.org/10.1016/j.ijforecast.2006.03.001 Přejít k původnímu zdroji...
    32. Hyndman, R. J., Athanasopoulos, G. (2018). Forecasting: Principles and Practice; OTexts.
    33. Ito, K.; Nakano, R. (2003). Optimizing Support Vector Regression Hyperparameters Based on Cross-Validation. In Proc. Int. Joint Conf. Neural Networks; Portland, OR, USA, Vol. 3, pp 2077-2082. https://doi.org/10.1109/IJCNN.2003.1223728. Přejít k původnímu zdroji...
    34. James, G., Witten, D., Hastie, T.; Tibshirani, R. (2013). An Introduction to Statistical Learning; Springer Science & Business Media: New York. Přejít k původnímu zdroji...
    35. Kumuda, A., Panigrahy, S. K. (2025). Design of an Efficient Model for Psychological Disease Analysis and Prediction Using Machine Learning and Genomic Data Samples. Big Data Cogn. Comput. 9(3), 49. https://doi.org/10.3390/bdcc9030049. Přejít k původnímu zdroji...
    36. Lenza, M., Moutachaker, I., Paredes, J. (2023). Density forecasts of inflation: A quantile regression forest approach. ECB Working Paper No. 2830. European Central Bank. https://www.ecb.europa.eu/pub/pdf/scpwps/ecb.wp2830~81049ee58f.en.pdf Přejít k původnímu zdroji...
    37. Lin, E., Kuo, P.-H., Lin, W.-Y., Liu, Y.-L., Yang, A. C.; Tsai, S. J. (2021). Prediction of Probable Major Depressive Disorder in the Taiwan Biobank: An Integrated Machine Learning and Genome-Wide Analysis Approach. J. Pers. Med. 11(7), 597. https://doi.org/10.3390/jpm11070597. Přejít k původnímu zdroji...
    38. Liu, Y., Pan, R., Xu, R. (2024). Mending the Crystal Ball: Enhanced Inflation Forecasts with Machine Learning. International Monetary Fund. WP/24/206, (9). Přejít k původnímu zdroji...
    39. https://doi.org/10.5089/9798400285387.001 Přejít k původnímu zdroji...
    40. Medeiros, M., Vasconcelos, G., Veiga, A., Zilberman, E. (2021). Forecasting Inflation in a Data Rich Environment: The Benefits of Machine Learning Methods. Journal of Business & Economic Statistics, 39(1), 98-119. https://doi.org/10.1080/07350015.2019.1637745 Přejít k původnímu zdroji...
    41. Mienye, I. D., Swart, T. G.; Obaido, G. (2024). Recurrent Neural Networks: A Comprehensive Review of Architectures, Variants, and Applications. Information 15(9), 517. https://doi.org/10.3390/info15090517. Přejít k původnímu zdroji...
    42. Ngwaba, C. A. (2025). Forecasting Covered Call Exchange-Traded Funds (ETFs) Using Time Series, Machine Learning, and Deep Learning Models. J. Risk Financ. Manag. 18(3), 120. https://doi.org/10.3390/jrfm18030120. Přejít k původnímu zdroji...
    43. Nitesh, K., Abhiram, Y., Teja, R. K., Kavitha, S. (2023). Weather Prediction Using Long Short Term Memory (LSTM) Model. In Proc. 2023 5th Int. Conf. Smart Syst. Invent. Technol. (ICSSIT); Tirunelveli, India, pp 1-6. https://doi.org/10.1109/ICSSIT55814.2023.10061039. Přejít k původnímu zdroji...
    44. Panzaru, C., Belea, S., & Jianu, L. (2025). Delayed Taxation and Macroeconomic Stability: A Dynamic IS-LM Model with Memory Effects. Economies, 13(7), 208. https://doi.org/10.3390/economies13070208. Přejít k původnímu zdroji...
    45. Paranhos, L. (2025). Predicting inflation with recurrent neural networks. Intl. J. of Economic Forecasting, in press. https://doi.org/10.1016/j.ijforecast.2024.07.010. Přejít k původnímu zdroji...
    46. Park, S., Yang, J. S. (2022). Interpretable Deep Learning LSTM Model for Intelligent Economic Decision-Making. Knowledge-Based Systems, 248, 108907. https://doi.org/10.1016/j.knosys.2022.108907. Přejít k původnímu zdroji...
    47. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E. (2011). Scikit-Learn: Machine Learning in Python. J. Mach. Learn. Res. 12, 2825-2830.
    48. https://www.jmlr.org/papers/volume12/pedregosa11a/pedregosa11a.pdfPetropoulos, F., Apiletti, D., Assimakopoulos, V., Babai, M. Z., Barrow, D. K., Taieb, S. B., Ziel, F. (2022). Forecasting: Theory and Practice. Int. J. Forecast. 38(3), 705-871. https://doi.org/10.1016/j.ijforecast.2021.11.001 Přejít k původnímu zdroji...
    49. Raza, A., Shahid, M. A., Zaman, M., Miao, Y., Huang, Y., Safdar, M., Maqbool, S., Muhammad, N. E. (2025). Improving Wheat Yield Prediction with Multi-Source Remote Sensing Data and Machine Learning in Arid Regions. Remote Sensing 17(5), 774. https://doi.org/10.3390/rs17050774. Přejít k původnímu zdroji...
    50. Rygh, T., Vaage, C., Westgaard, S., de Lange, P. E. (2025). Inflation Forecasting: LSTM Networks vs. Traditional Models for Accurate Predictions. J. Risk Financial Manag., 18(7), 365. https://doi.org/10.3390/jrfm18070365 Přejít k původnímu zdroji...
    51. Saâdaoui, F., Rabbouch, H. (2024). Financial Forecasting Improvement with LSTM-ARFIMA Hybrid Models and Non-Gaussian Distributions. Technol. Forecast. Soc. Change, 206, 123539. https://doi.org/10.1016/j.techfore.2024.123539. Přejít k původnímu zdroji...
    52. Salton, G. D.; Kelleher, J. D. (2019). Persistence Pays Off: Paying Attention to What the LSTM Gating Mechanism Persists. In Proc. Recent Adv. Nat. Lang. Process. (RANLP 2019); Varna, Bulgaria, pp 1052-1059. https://doi.org/10.26615/978-954-452-056-4_121. Přejít k původnímu zdroji...
    53. Sevgin, F. (2025). Machine Learning-Based Temperature Forecasting for Sustainable Climate Change Adaptation and Mitigation. Sustainability, 17(5), 1812. https://doi.org/10.3390/su17051812. Přejít k původnímu zdroji...
    54. Smola, A. J.; Schölkopf, B. (2004). A Tutorial on Support Vector Regression. Stat. Comput.,14, 199-222. https://doi.org/10.1023/B:STCO.0000035301.49549.88. Přejít k původnímu zdroji...
    55. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. (2014). Dropout: A Simple Way to Prevent Neural Networks from Overfitting. J. Mach. Learn. Res., 15(1), 1929-1958. http://jmlr.org/papers/v15/srivastava14a.html
    56. Stock, J., M. Watson. (1999). Forecasting Inflation. Journal of Monetary Economics. 44(2), p. 293-335. https://doi.org/10.1016/S0304-3932(99)00027-6 Přejít k původnímu zdroji...
    57. Stock, J., M. Watson. (2003). Forecasting Output and Inflation: the Role of Assets Prices. Journal of Economic Literature. 41(3), p. 788-829. https://www.aeaweb.org/articles/pdf/doi/10.1257/002205103322436197 Přejít k původnímu zdroji...
    58. Strobl, C., Boulesteix, A. L., Zeileis, A., Hothorn, T. (2009). Bias in Random Forest Variable Importance Measures: Illustrations, Sources and a Solution. BMC Bioinformatics, 10 (1), 213. https://doi.org/10.1186/1471-2105-8-25 Přejít k původnímu zdroji...
    59. Sutskever, I., Vinyals, O., Le, Q. V. (2014). Sequence to Sequence Learning with Neural Networks. In Proc. 27th Int. Conf. Neural Inf. Process. Syst.; MIT Press, pp. 3104-3112. https://proceedings.neurips.cc/paper_files/paper/2014/file/5a18e133cbf9f257297f410bb7eca942-Paper.pdf
    60. Svoboda, J., Štych, P., Laštovička, J., Paluba, D., Kobliuk, N. (2022). Random Forest Classification of Land Use, Land-Use Change and Forestry (LULUCF) Using Sentinel-2 Data-A Case Study of Czechia. Remote Sensing, 14(5), 1189. https://doi.org/10.3390/rs14051189. Přejít k původnímu zdroji...
    61. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J.; Wojna, Z. (2016). Rethinking the Inception Architecture for Computer Vision. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 2818-2826. https://doi.org/ 10.1109/CVPR.2016.308. Přejít k původnímu zdroji...
    62. Vapnik, V. (1995). The Nature of Statistical Learning Theory; Springer: New York. Přejít k původnímu zdroji...
    63. Vicente, J. (2005). Forecasting inflation through a bottom-up approach: The Portuguese case. Banco de Portugal Working Paper No. 5-05. https://www.bportugal.pt/sites/default/files/anexos/papers/wp200502.pdf
    64. Wang, H., Liu, M. (2025). Credit Risk Assessment of Green Supply Chain Finance for SMEs Based on Multi-Source Information Fusion. Sustainability, 17(4), 1590. https://doi.org/10.3390/su17041590. Přejít k původnímu zdroji...
    65. Zaremba, W., Sutskever, I., Vinyals, O. (2014). Recurrent Neural Network Regularization. In Proc. 2014 Conf. Empir. Methods Nat. Lang. Process. (EMNLP); Association for Computational Linguistics, pp 1524-1534. https://doi.org/10.48550/arXiv.1409.2329 Přejít k původnímu zdroji...
    66. Zhang, L., Li, J. (2012). Inflation Forecasting Using Support Vector Regression, Fourth International Symposium on Information Science and Engineering, Shanghai, China, 2012, pp. 136-140. https://doi.org/ 10.1109/ISISE.2012.37 Přejít k původnímu zdroji...
    67. Zhou, J.; Li, C.; Kim, Y. K.; Park, S. (2025). Bioinformatics and Deep Learning Approach to Discover Food-Derived Active Ingredients for Alzheimer's Disease Therapy. Foods, 14(1), 127. https://doi.org/10.3390/foods14010127. Přejít k původnímu zdroji...
    68. Zhu, P. Zhou, O., Zhang, Y. (2024). Investor Attention and Consumer Price Index Inflation rate: an Evidence from the United States. Human and Social Studies Communications, 11 (541). https://doi.org/10.1057/s41599-024-03036-y Přejít k původnímu zdroji...

    Tento článek je publikován v režimu tzv. otevřeného přístupu k vědeckým informacím (Open Access), který je distribuován pod licencí Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY NC ND 4.0), která umožňuje nekomerční distribuci, reprodukci a změny, pokud je původní dílo řádně ocitováno. Není povolena distribuce, reprodukce nebo změna, která není v souladu s podmínkami této licence.


    Zpět na obsah