A comparative analysis of GDP determinants in Germany and Poland: Integrating econometric and machine learning perspectives

Turgud Valiyev; Larissa M. Batrancea; Tunahan Aslan; Ulviyya Abasova; Turgud Valiyev; Larissa M. Batrancea; Tunahan Aslan; Ulviyya Abasova

doi:10.3934/NAR.2025021

National Accounting Review

2025, Volume 7, Issue 4: 501-521. doi: 10.3934/NAR.2025021

Previous Article Next Article

Research article

A comparative analysis of GDP determinants in Germany and Poland: Integrating econometric and machine learning perspectives

1.
Department of Computer Science, University of Innsbruck, Innsbruck, Austria
2.
Department of Business, Babes-Bolyai University, Cluj-Napoca, Romania
3.
Department of Economics, Van Yuzuncu Yıl University, Van, Türkiye
4.
Department of Economic Sciences, University of Warsaw, Warsaw, Poland

Received: 03 June 2025 Revised: 16 September 2025 Accepted: 14 October 2025 Published: 30 October 2025
JEL Codes: C53, C55, O33, O41, O47

This study analyzed the determinants of gross domestic product (GDP) for Germany and Poland using both linear econometric models and nonlinear machine learning models (decision trees, random forests, XGBoost) on data from 1991 to 2023. By comparing the model outcomes for Germany and Poland, we identified structural differences and uncovered key predictors of economic growth, measured by gross domestic product, over 33 years. Empirical results showed that nonlinear models significantly outperformed linear ones, with XGBoost achieving the best results in Germany, while the decision tree performed best in Poland. We also conducted feature importance analysis to reveal key factors. For Germany, factors such as life expectancy, net migration, and foreign direct investment were the strongest predictors of GDP. In Poland, production volume, life expectancy, urban population, internet usage, foreign direct investment, and unemployment rate emerged as the key drivers of GDP. Our insights highlight the need for specific economic modeling strategies and show how different development paths shape national growth dynamics.
- machine learning approach,
- GDP,
- econometric approach,
- economic growth
Citation: Turgud Valiyev, Larissa M. Batrancea, Tunahan Aslan, Ulviyya Abasova. A comparative analysis of GDP determinants in Germany and Poland: Integrating econometric and machine learning perspectives[J]. National Accounting Review, 2025, 7(4): 501-521. doi: 10.3934/NAR.2025021

Related Papers:

Abstract

This study analyzed the determinants of gross domestic product (GDP) for Germany and Poland using both linear econometric models and nonlinear machine learning models (decision trees, random forests, XGBoost) on data from 1991 to 2023. By comparing the model outcomes for Germany and Poland, we identified structural differences and uncovered key predictors of economic growth, measured by gross domestic product, over 33 years. Empirical results showed that nonlinear models significantly outperformed linear ones, with XGBoost achieving the best results in Germany, while the decision tree performed best in Poland. We also conducted feature importance analysis to reveal key factors. For Germany, factors such as life expectancy, net migration, and foreign direct investment were the strongest predictors of GDP. In Poland, production volume, life expectancy, urban population, internet usage, foreign direct investment, and unemployment rate emerged as the key drivers of GDP. Our insights highlight the need for specific economic modeling strategies and show how different development paths shape national growth dynamics.

References

[1]	Berg KA, Curtis CC, Mark NC (2024) GDP and temperature: Evidence on cross-country response heterogeneity. Eur Econ Rev 169: 104833. https://doi.org/10.1016/j.euroecorev.2024.104833 doi: 10.1016/j.euroecorev.2024.104833
[2]	Bhardwaj V, Bhavsar P, Patnaik D (2022) Forecasting GDP per capita of OECD countries using machine learning and deep learning models. In 2022 Interdisciplinary Research in Technology and Management (IRTM), 1–6. https://doi.org/10.1109/IRTM54583.2022.9791714
[3]	Boikova T, Zeverte-Rivza S, Rivza P, et al. (2021) The determinants and effects of competitiveness: The role of digitalization in the European economies. Sustainability 13: 11689. https://doi.org/10.3390/su132111689 doi: 10.3390/su132111689
[4]	Chu B, Qureshi S (2023) Comparing out-of-sample performance of machine learning methods to forecast US GDP growth. Computational Economics 62: 1567-1609. https://doi.org/10.1007/s10614-022-10312-z doi: 10.1007/s10614-022-10312-z
[5]	Cyrus N, Vogel D (2006) Managing access to the German labour market: How Polish (im)mmigrants relate to German opportunities and restrictions, In: Düvell, F. (Ed.), Illegal immigration in Europe, London: Palgrave Macmillan, 75-105. https://doi.org/10.1057/9780230555020_5
[6]	Dorn D, Zweimüller J (2021) Migration and labor market integration in Europe. J Econ Perspect 35: 49-76. https://doi.org/10.1257/jep.35.2.49 doi: 10.1257/jep.35.2.49
[7]	Ekinci R, Tüzün O, Ceylan F (2020) The relationship between inflation and economic growth: Experiences of some inflation targeting countries. Financial Studies 24: 6-20.
[8]	European Commission (2019) 15 years of Poland in the European Union: Benefits and challenges. Available from: https://ec.europa.eu/(Accessed May 2024).
[9]	Federal Reserve Bank of St. Louis (2024) Data retrieved from FRED, Federal Reserve Economic Data. Available from: https://fred.stlouisfed.org/(Accessed May 2024).
[10]	Feurer M, Hutter F (2019) Hyperparameter optimization, In: Hutter, F., Kotthoff, L., Vanschoren. J. (Eds.), Automated machine learning, Cham: Springer, 3-33. https://doi.org/10.1007/978-3-030-05318-5_1
[11]	Fihel A, Okólski M (2016) Dimensions and effects of labour migration to EU countries: the case of Poland, In: Galgóczi, B., Leschke, J. (Eds.), EU labour migration since enlargement, Abingdon: Routledge, 185-210.
[12]	Genuer R, Poggi JM, Tuleau-Malot C (2010) Variable selection using random forests. Pattern Recognit Lett 31: 2225-2236. https://doi.org/10.1016/j.patrec.2010.03.014 doi: 10.1016/j.patrec.2010.03.014
[13]	Georgarakos D, Kim KH, Coibion O, et al. (2025) How costly are business cycle volatility and inflation? A vox populi approach. NBER Working Paper Series, Working Paper 33476. Available from: https://www.nber.org/system/files/working_papers/w33476/w33476.pdf (Accessed July 2025).
[14]	Ghosh S, Ranjan A (2023) A machine learning approach to GDP nowcasting: An emerging market experience. Bull Monetary Econ Bank 26: 33-54. https://doi.org/10.59091/1410-8046.2055 doi: 10.59091/1410-8046.2055
[15]	Gogas P, Papadimitriou T, Matthaiou M, et al. (2015) Yield curve and recession forecasting in a machine learning framework. Comput Econ 45: 635-645. https://doi.org/10.1007/s10614-014-9432-0 doi: 10.1007/s10614-014-9432-0
[16]	Heinisch K, Scheufele R (2019) Should forecasters use real-time data to evaluate leading indicator models for GDP prediction? German evidence. Ger Econ Rev 20: 1-26. https://doi.org/10.1111/geer.12163 doi: 10.1111/geer.12163
[17]	Hsu MW, Lessmann S, Sung MC, et al. (2016) Bridging the divide in financial market forecasting: Machine learners vs. financial economists. Expert Syst Appl 61: 215-234. https://doi.org/10.1016/j.eswa.2016.05.033 doi: 10.1016/j.eswa.2016.05.033
[18]	International Trade Administration (2024) Poland country commercial guide. Available from: https://www.trade.gov/country-commercial-guides/poland-advanced-manufacturing (Accessed July 2025).
[19]	Kant D, Pick A, Winter JD (2025) Nowcasting GDP using machine learning methods. AStA Adv Stat Anal 109: 1-24. https://doi.org/10.1007/s10182-024-00515-0 doi: 10.1007/s10182-024-00515-0
[20]	Klasen S, Lawson D (2007) The impact of population growth on economic growth and poverty reduction in Uganda. Diskussionsbeiträge No. 133.
[21]	Kolodziejczyk K (2016) Poland in the European Union. Ten years of membership. UNISCI 40: 9-26. https://doi.org/10.5209/rev_RUNI.2016.n40.51803 doi: 10.5209/rev_RUNI.2016.n40.51803
[22]	KPMG (2025) Economic key facts Germany. Available from: https://kpmg.com/de/en/home/insights/overview/economic-key-facts-germany.html (Accessed July 2025).
[23]	Kreuter H, Riccaboni M (2023) The impact of import tariffs on GDP and consumer welfare: A production network approach. Econ Model 126: 106374. https://doi.org/10.1016/j.patrec.2010.03.014 doi: 10.1016/j.patrec.2010.03.014
[24]	Kumar A, Mallick S, Sinha A (2021) Policy errors and business cycle fluctuations: Evidence from an emerging economy. J Econ Behav Organ 192: 176-198. https://doi.org/10.1016/j.jebo.2021.10.004 doi: 10.1016/j.jebo.2021.10.004
[25]	Lianos TP, Pseiridis A. Tsounis N (2023) Declining population and GDP growth. Humanit Soc Sci Commun 10: 725. https://doi.org/10.1057/s41599-023-02223-7 doi: 10.1057/s41599-023-02223-7
[26]	Longo L, Riccaboni M, Rungi A (2022) A neural network ensemble approach for GDP forecasting. J Econ Dyn Control 134: 104278. https://doi.org/10.1016/j.jedc.2021.104278 doi: 10.1016/j.jedc.2021.104278
[27]	Maccarrone G, Morelli G, Spadaccini S (2021) GDP forecasting: Machine learning, linear or autoregression? Front Artif Intell 4: 757864. https://doi.org/10.3389/frai.2021.757864 doi: 10.3389/frai.2021.757864
[28]	Magazzino C, Mele M (2025) A new machine learning algorithm to explore the CO₂ emissions-energy use-economic growth trilemma. Ann Oper Res 345: 665-683. https://doi.org/10.1007/s10479-022-04787-0 doi: 10.1007/s10479-022-04787-0
[29]	Martin LC (2019) Machine learning vs traditional forecasting methods: An application to South African GDP. Stellenbosch Economic Working Papers: WP12/2019.
[30]	Mohamud MH, Mohamud FA, Gul A, et al. (2024) Unemployment rate and the gross domestic product in Somalia: Using frequentist and Bayesian approach. Cogent Econ Financ 12: 2388234. https://doi.org/10.1080/23322039.2024.2388234 doi: 10.1080/23322039.2024.2388234
[31]	Moroz M (2017) The level of development of the digital economy in Poland and selected European countries: A comparative analysis. Found Manag 9: 17-190. https://doi.org/10.1515/fman-2017-0014 doi: 10.1515/fman-2017-0014
[32]	Newell RG, Prest BC, Sexton SE (2021) The GDP-temperature relationship: Implications for climate changes damages. J Environ Econ Manag 108: 102445. https://doi.org/10.1016/j.jeem.2021.102445 doi: 10.1016/j.jeem.2021.102445
[33]	Nosratabadi S, Mosavi A, Duan P, et al. (2020) Data science in economics: comprehensive review of advanced machine learning and deep learning methods. Mathematics 8: 1799. https://doi.org/10.3390/math8101799 doi: 10.3390/math8101799
[34]	Pappas A, Boukas N (2025) Examining impact of inflation and inflation volatility on economic growth: Evidence from European Union economies. Economies 13: 31. https://doi.org/10.3390/economies13020031 doi: 10.3390/economies13020031
[35]	Peterson EWF (2017) The role of population in economic growth. Sage Open 7. https://doi.org/10.1177/2158244017736094 doi: 10.1177/2158244017736094
[36]	Richardson A, van Florenstein Mulder T, Vehbi T (2021) Nowcasting GDP using machine-learning algorithms: A real-time assessment. Int J Forecast 37: 941-948. https://doi.org/10.1016/j.ijforecast.2020.10.005 doi: 10.1016/j.ijforecast.2020.10.005
[37]	Robotko S, Topalov A, Lukashova V, et al. (2023) A machine learning study on world economic impact of intellectual property rights on GDP growth with a focus on Poland. 13th International Conference on Advanced Computer Information Technologies (ACIT), 261-264. https://doi.org/10.1109/ACIT58437.2023.10275475
[38]	Shiferaw YA (2023) An understanding of how GDP, unemployment and inflation interact and change across time and frequency. Economies 11: 131. https://doi.org/10.3390/economies11050131 doi: 10.3390/economies11050131
[39]	Sijabat R (2023) The association between foreign investment and gross domestic product in ten ASEAN countries. Economies 11: 188. https://doi.org/10.3390/economies11070188 doi: 10.3390/economies11070188
[40]	Sofianos E, Gogas P, Papadimitriou T (2022) Mind the gap: Forecasting euro-area output gaps with machine learning. Appl Econ Lett 29: 1824-1828. https://doi.org/10.1080/13504851.2021.1963403 doi: 10.1080/13504851.2021.1963403
[41]	Srinivasan N, Krishna M, Naveen V, et al. (2023) Predicting Indian GDP with machine learning: a comparison of regression models, In: 9th International Conference on Advanced Computing and Communication Systems (ICACCS), 1: 1855-1858. https://doi.org/10.1109/ICACCS57279.2023.10113035
[42]	Surwillo I, Slakaityte V (2024) Power moves East: Poland's rise as a strategic European player. Available from: https://www.diis.dk/en/research/power-moves-east-polands-rise-as-a-strategic-european-player (Accessed July 2025).
[43]	Tay R (2017) Correlation, variance inflation and multicollinearity in regression model. J East Asia Soc Transp Stud 12: 2006-2015. https://doi.org/10.11175/easts.12.2006 doi: 10.11175/easts.12.2006
[44]	Wettengel J (2024) Green technology Germany's best bet to remain industrial leader – industry association. Available from: https://www.cleanenergywire.org/news/green-technology-germanys- best-bet-remain-industrial-leader-industry-association (Accessed July 2025).
[45]	Wondimu M (2023) An empirical investigation of the impact of foreign direct investment on economic growth in Ethiopia. Cogent Econ Financ 11: 2281176. https://doi.org/10.1080/23322039.2023.2281176 doi: 10.1080/23322039.2023.2281176
[46]	World Bank (2024) Data retrieved from the World Bank database. Available from: https://data.worldbank.org/(Accessed May 2024).
[47]	Yoon J (2021) Forecasting of real GDP growth using machine learning models: Gradient boosting and random forest approach. Comput Econ 57: 247-265. https://doi.org/10.1007/s10614-020-10054-w doi: 10.1007/s10614-020-10054-w
[48]	Zarkova S, Kostov D, Angelov P, et al. (2023) Machine learning algorithm for mid-term projection of the EU member states' indebtedness. Risks 11: 71. https://doi.org/10.3390/risks11040071 doi: 10.3390/risks11040071

Reader Comments

Your name:*

Email:*
© 2025 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)