Forecasting The Economic Growth of Sverdlovsk Region: A Comparative Analysis of Machine Learning, Linear Regression and Autoregressive Models

Daniel Musafiri Balungu, Avinash Kumar

Ural Federal University named after the First President of Russia B.N. Yeltsin, Yekaterinburg, Russia

Abstract

The relevance of accurate economic forecasting cannot be overstated in today's rapidly changing global economy. Decision-makers in both the public and private sectors rely heavily on reliable forecasts to make informed decisions about resource allocation, investment strategies, and policy development. In this context, the importance of leveraging advanced analytical techniques, such as machine learning, to improve the accuracy of economic forecasts has become increasingly apparent. The purpose of this study is to explore the use of different forecasting models in predicting the dynamics of the GRP of the Sverdlovsk region in Russia, with a focus on the potential benefits of integrating machine learning techniques. The central hypothesis underlying this study is that machine learning models have the potential to outperform traditional autoregressive models in predicting economic growth. By leveraging a rich dataset that includes yearly GRP data and macroeconomic indicators from 2005 to 2022, the research procedure involved a comprehensive comparative analysis of different modeling approaches. The main findings of this study highlight the superior performance of the random forest model in forecasting GRP growth compared to the traditional SARIMAX model. These results not only provide valuable insights into the predictive power of machine learning algorithms in economic forecasting but also underscore the potential benefits of adopting advanced analytical techniques in decision-making processes. By demonstrating the superiority of machine learning models in predicting economic indicators like GRP, this study contributes to the growing body of literature on the application of data-driven approaches in economic analysis. Ultimately, the theoretical and practical significance of these findings lies in their implications for improving the accuracy and reliability of economic forecasts, thereby enabling more informed decision-making in a rapidly evolving economic landscape.

Keywords

economic growth; gross regional product; regional economy; machine learning; time series

JEL classification

References

1. Choudhury, P., Allen, R.T., Endres, M.G. (2021). Machine learning for pattern discovery in management research. Strategic Management Journal, Vol. 42, Issue 1, 30–57. https://doi.org/10.1002/smj.3215

   2. Graziano, M., Alexander, K.A., Liesch, M., Lema, E., Torres, J.A. (2019). Understanding an emerging economic discourse through regional analysis: Blue economy clusters in the US Great Lakes basin. Applied Geography, Vol. 105, 111–123. https://doi.org/10.1016/j.apgeog.2019.02.013

   3. Gu, G., Wu, B., Zhang, W., Lu, R., Feng, X., Liao, W., Pang, C., Lu, C. (2023). Comparing machine learning methods for predicting land development intensity. PLOS ONE, Vol. 18, Issue 4, e0282476. https://doi.org/10.1371/journal.pone.0282476

   4. Hassan, M.M., Mirza, T. (2021). Using Time Series Forecasting for Analysis of GDP Growth in India. International Journal of Education and Management Engineering, Vol. 11, No. 3, 40–49. https://doi.org/10.5815/ijeme.2021.03.05

   5. Maccarrone, G., Morelli, G., Spadaccini, S. (2021). GDP Forecasting: Machine Learning Linear or Autoregression? Frontiers in Artificial Intelligence, Vol. 4, 757864. https://doi.org/10.3389/frai.2021.757864

   6. Tran, C.L.H., Phan, T.H., Thi-Ngoc-Diem, P., Nguyen, H.T. (2023). Gross Domestic Product Prediction in Various Countries with Classic Machine Learning Techniques. In: Nature of Computation and Communication. Proceedings of 8th EAI International Conference, ICTCC 2022. Vol. 473. Edited by C.V. Phan, T.D. Nguyen. Springer Cham, 136–147. https://doi.org/10.1007/978-3-031-28790-9_9

   7. Puttanapong, N., Prasertsoong, N., Peechapat, W. (2023). Predicting Provincial Gross Domestic Product Using Satellite Data and Machine Learning Methods: A Case Study of Thailand. Asian Development Review, Vol. 40, No. 2, 39–85. https://doi.org/10.1142/S0116110523400024

   8. Martin, L.-C. (2019). Machine Learning vs. Traditional Forecasting Methods: An Application to South African GDP. Stellenbosch Economic Working Papers, No. WP12/2019. University of Stellenbosch, Department of Economics, 29 p. Available at: https://www.ekon.sun.ac.za/wpapers/2019/wp122019

   9. Richardson, A., van Florenstein Mulder, T., Vehbi, T. (2021). Nowcasting GDP using machine-learning algorithms: A real-time assessment. International Journal of Forecasting, Vol. 37, Issue 2, 941–948. https://doi.org/10.1016/j.ijforecast.2020.10.005

   10. Azarnova, T.V., Treshchevsky, Y.I., Papin, S.N. (2020). Prediction of parameters of socioeconomic development of the region using standard neural networks (on the example of GRP of the Voronezh Region). Modern Economy: Problems and Solutions, Vol. 3, 8–25. (In Russ.). https://doi.org/10.17308/meps.2020.3/2321

   11. Ivchenko, Yu.S. (2019). Determination of the main factors of the gross regional product level by econometric modeling methods for the totality of regions of the Russian Federation. Statistics and Economics, Vol. 16, No. 6, 4–18. (In Russ.). https://doi.org/10.21686/2500-3925-2019-6-4-18

   12. Barykin, S.E., Mikheev, A.A., Kiseleva, E.G., Putikhin, Y.E., Alekseeva, N.S., Mikhaylov, A. (2022). An Empirical Analysis of Russian Regions’ Debt Sustainability. Economies, Vol. 10, Issue 5, 106. https://doi.org/10.3390/economies10050106

   13. Lavrovsky, B.L., Shiltsin, E.A. (2016). Spatial Configuration of Gross Regional Product of Russian Regions: Estimation and Forecast. R-Economy, Vol. 2, No. 2, 205–215. https://doi.org/10.15826/recon.2016.2.2.018

   14. Skufina, T., Baranov, S., Samarina, V., Shatalova, T. (2015). Production Functions in Identifying the Specifics of Producing Gross Regional Product of Russian Federation. Mediterranean Journal of Social Sciences, Vol. 6, No. 5, 265. https://doi.org/10.5901/mjss.2015.v6n5s3p265

   15. Prokapalo, O., Bardal, A., Isaev, A., Mazitova, M., Suslov, D. (2020). Economic Situation in the Far Eastern Federal District in 2019. Spatial Economics, No. 2, 142–184. (In Russ.). https://doi.org/10.14530/se.2020.2.142-184

   16. Yoon, J. (2021). Forecasting of Real GDP Growth Using Machine Learning Models: Gradient Boosting and Random Forest Approach. Computational Economics, Vol. 57, 247–265. https://doi.org/10.1007/s10614-020-10054-w

   17. Breiman, L. (2001). Random forests. Machine learning, Vol. 45, Issue 1, 5–32. https://dx.doi.org/10.1023/A:1010933404324

   18. Dudek, G. (2015). Short-Term Load Forecasting Using Random Forests. Proceedings of the 7th IEEE International Conference Intelligent Systems IS’2014, Vol. 2: Tools, Architectures, Systems, Applications. Edited by D. Filev, J. Jabłkowski, J. Kacprzyk, M. Krawczak, I. Popchev, L. Rutkowski, V. Sgurev, E. Sotirova, P. Szynkarczyk, S. Zadrozny. Springer Cham, 821–828. https://doi.org/10.1007/978-3-319-11310-4_71

   19. Shrivastava, G., Karmakar, S., Kowar, M., Guhathakurta, P. (2012). Application of Artificial Neural Networks in Weather Forecasting: A Comprehensive Literature Review. International Journal of Computer Applications, Vol. 51, No. 18, 17–29. https://doi.org/10.5120/8142-1867

   20. Zhang, G.P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, Vol. 50, 159–175. https://doi.org/10.1016/S0925-2312(01)00702-0

   21. Kontopoulou, V., Panagopoulos, A., Kakkos, I., Matsopoulos, G. (2023). A Review of ARIMA vs. Machine Learning Approaches for Time Series Forecasting in Data Driven Networks. Future Internet, Vol. 15, Issue 8, 255. https://doi.org/10.3390/fi15080255

   22. Hamzaçebi, C. (2008). Improving artificial neural networks’ performance in seasonal time series forecasting. Information Sciences, Vol. 178, Issue 23, 4550–4559. https://doi.org/10.1016/j.ins.2008.07.024

   23. Cools, M., Moons, E., Wets, G. (2009). Investigating the variability in daily traffic counts through use of ARIMAX and SARIMAX models: assessing the effect of holidays on two site locations. Transportation Research Record, Vol. 2136, Issue 1, 57–66. https://doi.org/10.3141/2136-07

   24. Vu, D.H., Muttaqi, K.M., Agalgaonkar, A.P., Bouzerdoum, A. (2017). Short-term electricity demand forecasting using autoregressive based time varying model incorporating representative data adjustment. Applied Energy, Vol. 205, 790–801. https://doi.org/10.1016/j.apenergy.2017.08.135

   25. Wang, J.J., Wang, J.Z., Zhang, Z.G., Guo, S.P. (2012). Stock index forecasting based on a hybrid model. Omega, Vol. 40, Issue 6, 758–766. https://doi.org/10.1016/j.omega.2011.07.008

   26. Lydia, M., Kumar, S.S., Selvakumar, A.I., Kumar, G.E.P. (2016). Linear and non-linear autoregressive models for short-term wind speed forecasting. Energy Conversion and Management, Vol. 112, 115–124. https://doi.org/10.1016/j.enconman.2016.01.007

   27. Joaquin, A.R., Javier, E.O. (2023). Skforecast. Zenodo, Version v0.10.1dev. https://doi.org/10.5281/zenodo.8382788

   28. Casdagli, M., Eubank, S., Farmer, J.D., Gibson, J. (1991). State space reconstruction in the presence of noise. Physica D: Nonlinear Phenomena, Vol. 51, Issues 1-3, 52–98. https://doi.org/10.1016/0167-2789(91)90222-U

   29. Cheng, H., Tan, P. N., Gao, J., Scripps, J. (2006). Multistep-ahead time series prediction. In: Advances in Knowledge Discovery and Data Mining. Proceedings of 10th Pacific-Asia Conference. Edited by W.-K. Ng, M. Kitsuregawa, J. Li, K. Chang. Springer Berlin, Heidelberg, 765–774. https://doi.org/10.1007/11731139_89

   30. Hamzaçebi, C., Akay, D., Kutay, F. (2009). Comparison of direct and iterative artificial neural network forecast approaches in multi-periodic time series forecasting. Expert Systems with Applications, Vol. 36, Issue 2, Part 2, 3839–3844. https://doi.org/10.1016/j.eswa.2008.02.042

   31. Kline, D.M. (2004). Methods for multi-step time series forecasting neural networks. In: Neural Networks in Business Forecasting. Edited by G. Zhang. IGI Global, 226–250. https://doi.org/10.4018/978-1-59140-176-6.ch012

   32. Sorjamaa, A., Hao, J., Reyhani, N., Ji, Y., Lendasse, A. (2007). Methodology for long-term prediction of time series. Neurocomputing, Vol. 70, Issues 16-18, 2861–2869. https://doi.org/10.1016/j.neucom.2006.06.015

   33. Tiao, G.C., Tsay, R.S. (1994). Some advances in non-linear and adaptive modelling in time-series. Journal of Forecasting, Vol. 13, Issue 2, 109–131. https://doi.org/10.1002/for.3980130206

   34. Bontempi, G., Ben Taieb, S., Le Borgne, Y.A. (2013). Machine Learning Strategies for Time Series Forecasting. In: Business Intelligence. Second European Summer School, eBISS 2012. Lecture Notes in Business Information Processing, Vol. 138. Edited by M.-A. Aufaure, E. Zimányi. Springer Berlin, Heidelberg, 62–77. https://doi.org/10.1007/978-3-642-36318-4_3

   35. Camastra, F., Filippone, M. (2009). A comparative evaluation of nonlinear dynamics methods for time series prediction. Neural Computing and Applications, Vol. 18, 1021–1029. https://doi.org/10.1007/s00521-009-0266-y

About Authors

Daniel Musafiri Balungu

Assistant, Basic Department of Big Data Analytics and Video Analysis Methods, Institute of Radioelectronics and Information Technologies, Ural Federal University named after the first President of Russia B.N. Yeltsin, Yekaterinburg, Russia (620002, Yekaterinburg, Mira street, 19); ORCID https://orcid.org/0009-0001-5098-7603 e-mail: danielbal03.db@gmail.com

Avinash Kumar

Assistant, Basic Department of Big Data Analytics and Video Analysis Methods, Institute of Radioelectronics and Information Technologies, Ural Federal University named after the first President of Russia B.N. Yeltsin, Yekaterinburg, Russia (620002, Yekaterinburg, Mira street, 19); ORCID https://orcid.org/0000-0001-6929-1852 e-mail: avinash.kumar@urfu.ru

For citation

Balungu, D.M., Kumar, A. (2024). Forecasting The Economic Growth of Sverdlovsk Region: A Comparative Analysis of Machine Learning, Linear Regression and Autoregressive Models. Journal of Applied Economic Research, Vol. 23, No. 3, 674-695. https://doi.org/10.15826/vestnik.2024.23.3.027

Article info

Received April 26, 2024; Revised June 22, 2024; Accepted June 27, 2024.

DOI: https://doi.org/10.15826/vestnik.2024.23.3.027

Download full text article: