Forecasting Slovak GDP based on metal commodity prices as a tool for policymakers
Article Sidebar
Main Article Content
Abstract
The paper examines the development of selected metal commodity prices in the global market in the context of the development of Slovakia´s GDP as a macroeconomic indicator GDP and identify which of the analyzed metal commodities are most closely linked to the Slovak economy. Research data were obtained from website Investing and Eurostat and converted into time series. Metal commodity prices were expressed in US dollars per ton, while GDP values were expressed in millions of US dollars. The data were processed using artificial intelligence, specifically recurrent neural networks with a Long Short Term Memory layer, which have strong potential to predict such types of time series. The experiment included predictive models based on artificial neural networks. Metal commodities also play a crucial role in the Slovak economy, and the research confirms that the development of copper, zinc and aluminum prices is correlated with Slovakia´s economic performance. Therefore, the country´s GDP can be forecasted with high accuracy based on the price movements of these selected metal commodities. The findings may assist policymakers as well as top management in the manufacturing industry, where input prices can be compared with developments in the national economy.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authorship: The list of authors signing must include only those people who have contributed intellectually to the development of the work. Collaboration in the collection of data is not, by itself, a sufficient criterion of authorship. "Retos" declines any responsibility for possible conflicts arising from the authorship of the works that are published.
Copyright: The Salesian Polytechnic University preserves the copyrights of the published articles, and favors and allows their reuse under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Ecuador license. They may be copied, used, disseminated, transmitted and publicly displayed, provided that: i) the authorship and the original source of their publication (journal, editorial and work URL) are cited; (Ii) are not used for commercial purposes; Iii) mention the existence and specifications of this license.
References
Ab Khalil, M. R. y Abu Bakar, A. (2023). A Comparative Study of Deep Learning Algorithms in Univariate and Multivariate Forecasting of the Malaysian Stock Market. Sains Malaysiana, 52(3), 993-1009. https://doi.org/10.17576/jsm-2023-5203-22
Alkhareif, R. M. y Barnett, W. A. (2022). Nowcasting Real GDP for Saudi Arabia1*. Open Economies Review, 33(2), 333-345. https://doi.org/10.1007/s11079-021-09634-6
Aisy, R.R., Zulfa, L., Rahim, Y. y Ahsan, M. (2025). Residual XGBoost regression-Based individual moving range control chart for Gross Domestic Product growth monitoring. PLoS ONE 20, e0321660. https://doi.org/10.1371/journal.pone.0321660
Apanovych, Y., Rowland, Z., Borovkova, B. (2024). The impact of oil prices on the GDP of V4 Countries. ACTA Montan. Slovaca, 29, 1-12. https://doi.org/10.46544/AMS.v29i1.01
Cuaresma, J. C., Fortin, I., Hlouskova, J. y Obersteiner, M. (2024). Regime-dependent commodity price dynamics: A predictive analysis. J. Forecast., 43, 2822-2847. https://doi.org/10.1002/for.3152
Chang, A. C. y Levinson, T. J. (2023). Raiders of the lost high-frequency forecasts: New data and evidence on the efficiency of the Fed’s forecasting. J. Appl. Econom. 38, 88-104. https://doi.org/10.1002/jae.2938
Chen, J., Yi, J., Liu, K., Cheng, J., Feng, Y. y Fang, C. (2023). Copper price prediction using LSTM recurrent neural network integrated simulated annealing algorithm. PLoS ONE, 18(10), e0285631. https://doi.org/10.1371/journal.pone.0285631
Enilov, M. (2023). The predictive power of commodity prices for future economic growth: Evaluating the role of economic development. International Journal of Finance & Economics. https://doi.org/10.1002/ijfe.2821
Guo, Z., Chen, X., Li, M., Chi, Y. y Shi, D. (2024). Construction and Validation of Peanut Leaf Spot Disease Prediction Model Based on Long Time Series Data and Deep Learning. Agron.-BASEL 14, 294. https://doi.org/10.3390/agronomy14020294
Gupta, V. y Kumar, E. (2023). Hybrid Harris hawk optimization based light gradient boosting machine model for real-time trading. Artificial Intelligence Review, 56(8), 8697-8720. https://doi.org/10.1007/s10462-022-10323-0
Hájek, L. y Rezny, L. (2014). 20 years of Czech economy development-Comparison with Slovakia. E & M Ekonomie Management, 17. https://doi.org/10.15240/tul/001/2014-1-002
Jovanovic, A., Jovanovic, L., Zivkovic, M., Bacanin, N., Simic, V., Pamucar, D. y Antonijevic, M. (2025). Particle swarm optimization tuned multi-headed long short-term memory networks approach for fuel prices forecasting. J. Netw. Comput. Appl. 233, 104048. https://doi.org/10.1016/j.jnca.2024.104048
Kahraman, E. y Akay, O. (2023). Comparison of exponential smoothing methods in forecasting global prices of main metals. Mineral Economics, 36(3), 427-435. https://doi.org/10.1007/s13563-022-00354-y
Kara, A., Yildirim, D. y Tunc, G. I. (2023). Market efficiency in non-renewable resource markets: evidence from stationarity tests with structural changes. Miner. Econ. 36, 279-290. https://doi.org/10.1007/s13563-022-00312-8
Kim, G. I. y Jang, B. (2023). Petroleum Price Prediction with CNN-LSTM and CNN-GRU Using Skip-Connection. Mathematics, 11(3), 547. https://doi.org/10.3390/math11030547
Kumar, V.N., Sil, A. (2023). Five decades spatial hazard maps of atmospheric corrosion predict the rate of deterioration of steel beams in different environments of India. Corros. Rev. 41, 85-101. https://doi.org/10.1515/corrrev-2022-0028
Li, J. y Guo, Y. (2025). A hybrid model based on iTransformer for risk warning of crude oil price fluctuations. ENERGY, 314, 134199. https://doi.org/10.1016/j.energy.2024.134199
Li, Z., Yang, Y., Chen, Y. y Huang, J. (2023). A novel non-ferrous metals price forecast model based on LSTM and multivariate mode decomposition. Axioms, 12(7), Article 7. https://doi.org/10.3390/axioms12070670
Link, S., Peichl, A., Roth, C., y Wohlfart, J. (2023). Information frictions among firms and households. J. Monet. Econ. 135, 99-115. https://doi.org/10.1016/j.jmoneco.2023.01.005
Matsumoto, A., Pescatori, A. y Wang, X. (2023). Commodity prices and global economic activity. Japan and the World Economy, 66, 101177. https://doi.org/10.1016/j.japwor.2023.101177
Peersman, G., Rueth, S.K., Van der Veken, W. (2021). The interplay between oil and food commodity prices: Has it changed over time? J. Int. Econ. 133, 103540. https://doi.org/10.1016/j.jinteco.2021.103540
Rokicki, T. y Perkowska, A. (2021). Diversity and changes in the energy balance in EU Countries. Energies, 14(4), Article 4. https://doi.org/10.3390/en14041098
Santos, G. C., Barboza, F., Veiga, A. C. P. y Silva, M. F. (2021). Forecasting Brazilian Ethanol Spot Prices Using LSTM. Energies, 14(23), Article 23. https://doi.org/10.3390/en14237987
Sen, A., Akpolat, A. G. y Balkan, I. (2024). Commodity prices and economic growth: Empirical evidence from countries with different income groups. Heliyon 10, e34038. https://doi.org/10.1016/j.heliyon.2024.e34038
Shao, S.-F., Li, Y., Cheng, J. (2024). Non-fungible tokens and metal markets: time-varying spillovers and portfolio implications. Appl. Econ. Lett. https://doi.org/10.1080/13504851.2024.2363323
Song, H. y Choi, H. (2023). Forecasting stock market indices using the recurrent neural network based hybrid models: CNN-LSTM, GRU-CNN, and Ensemble Models. Appl. Sci.-BASEL, 13, 4644. https://doi.org/10.3390/app13074644
Szabo, M. (2024). Disciplining growth-at-risk models with survey of professional forecasters and Bayesian quantile regression. J. Forecast, 43, 1975-1981. https://doi.org/10.1002/for.3120
Urbina, D. A. y Rodriguez, G. (2023). Evolution of the effects of mineral commodity prices on fiscal fluctuations: empirical evidence from TVP-VAR-SV models for Peru. Rev. WORLD Econ., 159, 153-184. https://doi.org/10.1007/s10290-022-00460-7
Valásková, K. y Kramárová, K. (2015). A bootstrap analysis of macroeconomic aspects of the automotive industry in Slovakia, Transport Means 2015, PTS I AND II, ISSN 1822-296X
Wang, W. y Cheung, Y.-W. (2023). Commodity price effects on currencies. J. Int. Money Finance, 130, 102745. https://doi.org/10.1016/j.jimonfin.2022.102745
Wang, J. y Zhang, Y. (2025). A hybrid system with optimized decomposition on random deep learning model for crude oil futures forecasting. Expert Syst. Appl. 272, 126706. https://doi.org/10.1016/j.eswa.2025.126706
Wang, J., Zhang, T., Lu, T. y Xue, Z. (2023). A Hybrid Forecast Model of EEMD-CNN-ILSTM for Crude Oil Futures Price. Electronics 12, 2521. https://doi.org/10.3390/electronics12112521
Wanzala, R.W., Obokoh, L.O. (2024). Sustainability implications of commodity price shocks and commodity dependence in selected Sub-Saharan countries. Sustainability, 16, 8928. https://doi.org/10.3390/su16208928
Yasmeen, R., Huang, H., Shah, W.U.H. (2024). Assessing the significance of FinTech and mineral resource depletion in combating energy poverty: Empirical insights from BRICS economies. Resour. Policy, 89, 104691. https://doi.org/10.1016/j.resourpol.2024.104691
Ybrayev, Z., Kubenbayev, O., Baimagambetov, A. (2024). Macroeconomic effects of fiscal rules for a commodity-exporting economy: avoiding procyclical bias in Kazakhstan. Macroecon. Finance Emerg. Mark. Econ., 17, 271-294. https://doi.org/10.1080/17520843.2022.2043602
Zarkova, S., Kostov, D., Angelov, P., Pavlov, T. y Zahariev, A. (2023). Machine Learning Algorithm for Mid-Term Projection of the EU Member States’ Indebtedness. Risks, 11, 71. https://doi.org/10.3390/risks11040071
Zhang, Y., Shang, W., Zhang, N., Pan, X. y Huang, B. (2023). Quarterly GDP forecast based on coupled economic and energy feature WA-LSTM model. Frontiers in Energy Research, 11. https://doi.org/10.3389/fenrg.2023.1329376
Zhao, Y., Guo, Y. y Wang, X. (2025). Hybrid LSTM-Transformer Architecture with Multi-Scale Feature Fusion for High-Accuracy Gold Futures Price Forecasting. Mathematics, 13, 1551. https://doi.org/10.3390/math13101551