A Machine Learning Approach to Forecast International Trade: The Case of Croatia

Jošić, Hrvoje; Žmuk, Berislav

doi:10.2478/bsrj-2022-0030

Abstract

Background: This paper presents a machine learning approach to forecast Croatia’s international bilateral trade.

Objectives: The goal of this paper is to evaluate the performance of machine learning algorithms in predicting international bilateral trade flows related to imports and exports in the case of Croatia.

Methods/Approach: The dataset on Croatian bilateral trade with over 180 countries worldwide from 2001 to 2019 is assembled using main variables from the gravity trade model. To forecast values of Croatian bilateral exports and imports for a horizon of one year (the year 2020), machine learning algorithms (Gaussian processes, Linear regression, and Multilayer perceptron) have been used. Each forecasting algorithm is evaluated by calculating mean absolute percentage errors (MAPE).

Results: It was found that machine learning algorithms have a very good predicting ability in forecasting Croatian bilateral trade, with neural network Multilayer perceptron having the best performance among the other machine learning algorithms.

Conclusions Main findings from this paper can be important for economic policymakers and other subjects in this field of research. Timely information about the changes in trends and projections of future trade flows can significantly affect decision-making related to international bilateral trade flows.

References

1. Abirami, S. and Chitra, P. (2020), “Energy-efficient edge based real-time healthcare support system”. In Pethuru, R. and Preetha, E. (Eds.), The Digital Twin Paradigm for Smarter Systems and Environments: The Industry Use Cases, pp. 339-368.10.1016/bs.adcom.2019.09.007
Search in Google Scholar Back to article
2. Almog, A., Bird, R. and Garlaschelli, D. (2019), “Enhanced Gravity Model of Trade: Reconciling Macroeconomic and Network Models”, Frontiers in Physics, Vol. 7, pp. 1-17.10.3389/fphy.2019.00055
Search in Google Scholar Back to article
3. Arnerić, J., Poklepović, T., & Teai, J. W. (2018), “Neural network approach in forecasting realized variance using high-frequency data”. Business Systems Research: International journal of the Society for Advancing Innovation and Research in Economy, Vol. 9, No. 2, pp. 18-34.10.2478/bsrj-2018-0016
Search in Google Scholar Back to article
4. Batarseh, F. A., Gopinath, M. and Anderson, M. (2020), “Artificial Intelligence Methods for Evaluating Global Trade Flows”, International Finance Discussion Papers 1296. Washington: Board of Governors of the Federal Reserve System, available at: https://www.federalreserve.gov/econres/ifdp/files/ifdp1296.pdf (August 28, 2022)10.17016/IFDP.2020.1296
Search in Google Scholar Back to article
5. Batarseh, F. A., Gopinath, M., Nalluru, G. and Beckman, J. (2021), “Application of Machine Learning in Forecasting International Trade Trends”, available at: https://arxiv.org/abs/1910.03112 (August 28, 2022)
Search in Google Scholar Back to article
6. Baxter, G. and Srisaeng, P. (2018), “The use of an artificial neural network to predict Australia’s export air cargo demand”, International Journal for Traffic and Transport Engineering, Vol. 8, No.1, pp. 15-30.10.7708/ijtte.2018.8(1).02
Search in Google Scholar Back to article
7. Brownlee, J. (2019).”How To Use Regression Machine Learning Algorithms in Weka”, Available at: https://machinelearningmastery.com/use-regression-machine-learning-algorithms-weka/ (August 28, 2022)
Search in Google Scholar Back to article
8. CEPII (2021), GeoDist, available at: http://www.cepii.fr/cepii/en/bdd_modele/presentation.asp?id=6 (August 28, 2022)
Search in Google Scholar Back to article
9. Chan, E.M.H., Ho, DCK and Tsang, C.-W. (2021),” Estimating United States Asia Clothing Trade: Multiple Regression vs. Artificial Neural Networks”, Journal of Asian Finance, Economics and Business, Vol. 8, No. 7, pp. 403–411
Search in Google Scholar Back to article
10. Circlaeys, S., Kanitkar, C. and Kumazawa, D. (2017), “Bilateral Trade Flow Prediction”, available at: http://cs229.stanford.edu/proj2017/final-reports/5240224.pdf (August 28, 2022)
Search in Google Scholar Back to article
11. Ćorić, I. (2016), “Comparison of Multivariate Statistical Analysis and Machine Learning Methods in Retailing: Research Framework Proposition”, ENTRENOVA-ENTerprise REsearch InNOVAtion, Vol. 2, No. 1, pp. 32-38.
Search in Google Scholar Back to article
12. Data Science (2021), “Equation of a Multilayer Perceptron Network”, available at: https://datascience.stackexchange.com/questions/84016/equation-of-a-multi-layer-perceptron-network (August 28, 2022)
Search in Google Scholar Back to article
13. Dumor, K. and Yao, L. (2019), “Estimating China’s Trade with Its Partner Countries within the Belt and Road Initiative Using Neural Network Analysis”, Sustainability, Vol. 11, No. 5, pp. 1-22.10.3390/su11051449
Search in Google Scholar Back to article
14. Goldfarb, A. and Trefler, D. (2018), “Artificial Intelligence and International Trade, NBER Chapters”, in: The Economics of Artificial Intelligence: An Agenda, pp. 463-492, National Bureau of Economic Research, Inc.10.7208/chicago/9780226613475.003.0019
Search in Google Scholar Back to article
15. Gopinath, M. et al. (2021), “International agricultural trade forecasting using machine learning”, Data & Policy, Vol. 3, No.1, pp. 1-20.10.1017/dap.2020.22
Search in Google Scholar Back to article
16. Hall, M. A., Eibe, F., Witten, I. H. & Pal, C. J. (2011).” Data Mining: Practical Machine Learning Tools and Techniques”, Third Edition, Morgan Kaufman.
Search in Google Scholar Back to article
17. Kraser, M. (2018).”Gaussian Processes”, Available at: http://krasserm.github.io/2018/03/19/gaussian-processes/ (August 28, 2022)
Search in Google Scholar Back to article
18. Kulkarni, A. D. and More, A. (2016), „Formulation of a Prediction Index with the Help of WEKA Tool for Guiding the Stock Market Investors“, Oriental journal of Computer science & technology, Vol. 9, No.3, pp. 212-225.10.13005/ojcst/09.03.07
Search in Google Scholar Back to article
19. LeNail, (2019), “NN-SVG: Publication-Ready Neural Network Architecture Schematics”, Journal of Open Source Software, Vol. 4 No. 33, 747.10.21105/joss.00747
Search in Google Scholar Back to article
20. Lewis, C. D. (1982), “Industrial and Business Forecasting Methods”, Butterworths Publishing, London.
Search in Google Scholar Back to article
21. Medić, T., Bach, M. P., & Jaković, B. (2020, June). Stock market analysis and price prediction using deep learning and artificial neural networks. In Proceedings of FEB Zagreb International Odyssey Conference on Economics and Business Vol. 2, No. 1, pp. 450-462. University of Zagreb, Faculty of Economics and Business.
Search in Google Scholar Back to article
22. Menzies, T., Kocaguneli, E., Turhan, B., Minku, L. and Peters, F. (2014), “Sharing Data and Models in Software Engineering”, Morgan Kaufmann; 1st edition.10.1016/B978-0-12-417295-1.00001-1
Search in Google Scholar Back to article
23. Mitrea, C. A., Lee, C. K. M., & Wu, Z. (2009), “A comparison between neural networks and traditional forecasting methods: A case study”, International journal of engineering business management, Vol. 1, pp. 11.10.5772/6777
Search in Google Scholar Back to article
24. Nuroglu, E. (2012), “Estimating Trade Flows of Turkey Using Panel Data Analysis and Neural Networks”, available at: https://www.researchgate.net/publication/261001076_Estimating_Trade_Flows_of_Turkey_Using_Panel_Data_Analysis_and_Neural_Networks (August 28, 2022)
Search in Google Scholar Back to article
25. Nyoni, T. (2019). “Exports and imports in Zimbabwe: recent insights from artificial neural networks”, MPRA Paper 96906, University Library of Munich, Germany, available at: https://ideas.repec.org/p/pra/mprapa/96906.html (August 28, 2022)
Search in Google Scholar Back to article
26. Quimba, F. M. A. and Barral, M. A. A. (2018), “Exploring Neural Network Models in Understanding Bilateral Trade in APEC: A Review of History and Concepts”, Discussion Papers DP 2018-33, Philippine Institute for Development Studies.
Search in Google Scholar Back to article
27. Rasmussen, C. E. and Williams, C. K. I. (2006), “Gaussian Processes for Machine Learning”. MIT Press.10.7551/mitpress/3206.001.0001
Search in Google Scholar Back to article
28. Salama, M., Abdelkader, H., & Abdelwahab, A. (2022). A novel ensemble approach for heterogeneous data with active learning. International Journal of Engineering Business Management, Vol. 14, 18479790221082605.10.1177/18479790221082605
Search in Google Scholar Back to article
29. Trade Map (2021), Trade Map Index Page [Internet], available at: https://www.trademap.org/ (August 28, 2022)
Search in Google Scholar Back to article
30. University of Waikato (2021), “WEKA: The workbench for machine learning”, [Internet], available at: https://www.cs.waikato.ac.nz/ml/weka/ (August 28, 2022)
Search in Google Scholar Back to article
31. Wohl, I. and Kennedy, J. (2018), “Neural Network Analysis of International Trade”, Office of Industries, Working Paper ID-049, available at: https://www.usitc.gov/publications/332/working_papers/050218_neural.html (August 28, 2022)
Search in Google Scholar Back to article
32. World Bank (2021), “GDP (current US$)”, [Internet], available at: https://data.worldbank.org/indicator/NY.GDP.MKTP.CD (August 28, 2022)
Search in Google Scholar Back to article
33. World Trade Organization (2021), “Members and Observers”, [Internet], available at: https://www.wto.org/english/thewto_e/whatis_e/tif_e/org6_e.htm (August 28, 2022)
Search in Google Scholar Back to article
34. Vidya, C. T. and Prabheesh, K. P. (2020), “Implications of COVID-19 Pandemic on the Global Trade Networks”, Emerging Markets Finance and Trade, Vol. 56, No. 10, pp. 2408-242110.1080/1540496X.2020.1785426
Search in Google Scholar Back to article
35. Zekić-Sušac, M., Pfeifer, S., & Šarlija, N. (2014). A comparison of machine learning methods in a high-dimensional classification problem. Business Systems Research: International journal of the Society for Advancing Innovation and Research in Economy, Vol. 5, No. 3, pp. 82-96.10.2478/bsrj-2014-0021
Search in Google Scholar Back to article
36. Žmuk, B. and Jošić, H. (2020).”Forecasting stock market indices using machine learning algorithms”, Interdisciplinary Description of Complex Systems: INDECS, Vol.18, No.4, pp. 471-489.10.7906/indecs.18.4.7
Search in Google Scholar Back to article