{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:47:28Z","timestamp":1781279248352,"version":"3.54.1"},"reference-count":47,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T00:00:00Z","timestamp":1717718400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"TalTech by the Estonian Research Council","award":["PRG1573"],"award-info":[{"award-number":["PRG1573"]}]},{"name":"TalTech by the Estonian Research Council","award":["952410"],"award-info":[{"award-number":["952410"]}]},{"name":"TalTech by the Estonian Research Council","award":["778398"],"award-info":[{"award-number":["778398"]}]},{"name":"TalTech Industrial project","award":["PRG1573"],"award-info":[{"award-number":["PRG1573"]}]},{"name":"TalTech Industrial project","award":["952410"],"award-info":[{"award-number":["952410"]}]},{"name":"TalTech Industrial project","award":["778398"],"award-info":[{"award-number":["778398"]}]},{"name":"CatChain project","award":["PRG1573"],"award-info":[{"award-number":["PRG1573"]}]},{"name":"CatChain project","award":["952410"],"award-info":[{"award-number":["952410"]}]},{"name":"CatChain project","award":["778398"],"award-info":[{"award-number":["778398"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>In the realm of international trade and economic development, the prediction of trade flows between countries is crucial for identifying export opportunities. Commonly used log-linear regression models are constrained due to difficulties when dealing with extensive, high-cardinality datasets, and the utilization of machine learning techniques in predictions offers new possibilities. We examine the predictive power of Graph Neural Networks (GNNs) in estimating the value of bilateral trade between countries. We work with detailed UN Comtrade data that represent annual bilateral trade in goods between any two countries in the world and more than 5000 product groups. We explore two different types of GNNs, namely Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs), by applying them to trade flow data. This study evaluates the effectiveness of GNNs relative to traditional machine learning techniques such as random forest and examines the possible effects of data drift on their performance. Our findings reveal the superior predictive capability of GNNs, suggesting their effectiveness in modeling complex trade relationships. The research presented in this work offers a data-driven foundation for decision-making and is relevant for business strategies and policymaking as it helps in identifying markets, products, and sectors with significant development potential.<\/jats:p>","DOI":"10.3390\/bdcc8060065","type":"journal-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T08:05:17Z","timestamp":1717747517000},"page":"65","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Harnessing Graph Neural Networks to Predict International Trade Flows"],"prefix":"10.3390","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6869-3518","authenticated-orcid":false,"given":"Bassem","family":"Sellami","sequence":"first","affiliation":[{"name":"Department of Software Science, Tallinn University of Technology, Akadeemia tee 15a, 12618 Tallinn, Estonia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2063-2844","authenticated-orcid":false,"given":"Chahinez","family":"Ounoughi","sequence":"additional","affiliation":[{"name":"Department of Business Administration, Tallinn University of Technology, Ehitajate tee 5, 12618 Tallinn, Estonia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4895-4466","authenticated-orcid":false,"given":"Tarmo","family":"Kalvet","sequence":"additional","affiliation":[{"name":"Department of Business Administration, Tallinn University of Technology, Ehitajate tee 5, 12618 Tallinn, Estonia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2484-5003","authenticated-orcid":false,"given":"Marek","family":"Tiits","sequence":"additional","affiliation":[{"name":"Department of Business Administration, Tallinn University of Technology, Ehitajate tee 5, 12618 Tallinn, Estonia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8982-1678","authenticated-orcid":false,"given":"Diego","family":"Rincon-Yanez","sequence":"additional","affiliation":[{"name":"Department of Information and Electrical Engineering and Applied Mathematics, University of Salerno, Via Giovanni Paolo II 132, 84084 Fisciano, Italy"},{"name":"Facultad de Ingenier\u00edas y Tecnolog\u00edas, Universidad de Santander, C\u00facuta 540001, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"305","DOI":"10.2307\/1884452","article-title":"Location Theory and Trade Theory: Short-Run Analysis","volume":"68","author":"Isard","year":"1954","journal-title":"Q. J. Econ."},{"key":"ref_2","unstructured":"Tinbergen, J. (1962). Shaping the World Economy: Suggestions for an International Economic Policy, Twentieth Century Fund."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"100288","DOI":"10.1016\/j.joitmc.2024.100288","article-title":"Relatedness and Product Complexity Meet Gravity Models of International Trade","volume":"10","author":"Tiits","year":"2024","journal-title":"J. Open Innov. Technol. Mark. Complex."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A Comprehensive Survey on Graph Neural Networks","volume":"32","author":"Wu","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wu, L., Cui, P., Pei, J., Zhao, L., and Guo, X. (2022, January 14\u201318). Graph Neural Networks: Foundation, Frontiers, and Applications. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA.","DOI":"10.1145\/3534678.3542609"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"79143","DOI":"10.1109\/ACCESS.2021.3082932","article-title":"Foundations and Modeling of Dynamic Networks Using Dynamic Graph Neural Networks: A Survey","volume":"9","author":"Skarding","year":"2021","journal-title":"IEEE Access"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1504\/IJFIP.2013.058607","article-title":"Intelligent piggybacking: A foresight policy tool for small catching-up economies","volume":"9","author":"Tiits","year":"2013","journal-title":"Int. J. Foresight Innov. Policy"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"112","DOI":"10.14254\/2071-8330.2022\/15-4\/7","article-title":"Defence industries in small European states: Key contemporary challenges and opportunities","volume":"15","author":"Ploom","year":"2022","journal-title":"J. Int. Stud."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/s43546-023-00461-0","article-title":"Review of the gravity model: Origins and critical analysis of its theoretical development","volume":"3","author":"Capoani","year":"2023","journal-title":"SN Bus. Econ."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"447","DOI":"10.5530\/jscires.11.3.48","article-title":"Scientific Mapping of Gravity Model of International Trade Literature: A Bibliometric Analysis","volume":"11","author":"Sharma","year":"2023","journal-title":"J. Scientometr. Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.1162\/003465303772815970","article-title":"Intranational Home Bias: Some Explanations","volume":"85","author":"Hillberry","year":"2003","journal-title":"Rev. Econ. Stat."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yotov, Y.V., Piermartini, R., Monteiro, J.-A., and Larch, M. (2016). An Advanced Guide to Trade Policy Analysis: The Structural Gravity Model, WTO iLibrary.","DOI":"10.30875\/abc0167e-en"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1162\/003465302317411587","article-title":"Insecurity and the Pattern of Trade: An Empirical Investigation","volume":"84","author":"Anderson","year":"2002","journal-title":"Rev. Econ. Stat."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3692","DOI":"10.1016\/j.procs.2023.10.364","article-title":"Enhancing downstream tasks in Knowledge Graphs Embeddings: A Complement Graph-based Approach Applied to Bilateral Trade","volume":"225","author":"Mouakher","year":"2023","journal-title":"Procedia Comput. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Baldwin, R., and Taglioni, D. (2006). Gravity for Dummies and Dummies for Gravity Equations, National Bureau of Economic Research. Working Paper.","DOI":"10.3386\/w12516"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1007\/s00191-019-00638-7","article-title":"Bilateral relatedness: Knowledge diffusion and the evolution of bilateral trade","volume":"30","author":"Jun","year":"2020","journal-title":"J. Evol. Econ."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1146\/annurev-economics-080217-053433","article-title":"Machine Learning Methods That Economists Should Know About","volume":"11","author":"Athey","year":"2019","journal-title":"Annu. Rev. Econ."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"James, G., Witten, D., Hastie, T., Tibshirani, R., and Taylor, J. (2023). An Introduction to Statistical Learning: With Applications in Python, Springer.","DOI":"10.1007\/978-3-031-38747-0"},{"key":"ref_19","unstructured":"Ho, T. (1995, January 14\u201316). Random decision forests. Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, Canada."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2008","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Li, J., Rong, Y., Cheng, H., Meng, H., Huang, W., and Huang, J. (2019, January 13\u201317). Semi-supervised graph classification: A hierarchical graph perspective. Proceedings of the World Wide Web Conference, San Francisco, CA, USA.","DOI":"10.1145\/3308558.3313461"},{"key":"ref_22","unstructured":"Kipf, T.N., and Welling, M. (2016). Semi-Supervised Classification with Graph Convolutional Networks. arXiv."},{"key":"ref_23","unstructured":"Li, Y., Yu, R., Shahabi, C., and Liu, Y. (2017). Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv."},{"key":"ref_24","unstructured":"Verstyuk, S., and Douglas, M. (2024, March 08). Machine Learning the Gravity Equation for International Trade. Available online: https:\/\/ssrn.com\/abstract=4053795."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Minakawa, N., Izumi, K., and Sakaji, H. (2022, January 17\u201320). Bilateral Trade Flow Prediction by Gravity-informed Graph Auto-encoder. Proceedings of the 2022 IEEE International Conference On Big Data (Big Data), Osaka, Japan.","DOI":"10.1109\/BigData55660.2022.10021066"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Monken, A., Haberkorn, F., Gopinath, M., Freeman, L., and Batarseh, F. (2021). Graph neural networks for modeling causality in international trade. Int. Flairs Conf. Proc., 34.","DOI":"10.32473\/flairs.v34i1.128485"},{"key":"ref_27","unstructured":"Atwood, J., and Towsley, D. (2016). Diffusion-convolutional neural networks. Adv. Neural Inf. Process. Syst., 29."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Cao, S., Lu, W., and Xu, Q. (2016, January 12\u201317). Deep neural networks for learning graph representations. Proceedings of the AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA.","DOI":"10.1609\/aaai.v30i1.10179"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Qiu, J., Dong, Y., Ma, H., Li, J., Wang, K., and Tang, J. (2018, January 5\u20139). Network embedding as matrix factorization: Unifying deepwalk, line, pte, and node2vec. Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, Los Angeles, CA, USA.","DOI":"10.1145\/3159652.3159706"},{"key":"ref_30","first-page":"101789","article-title":"Accurate prediction of international trade flows: Leveraging knowledge graphs and their embeddings","volume":"35","author":"Ounoughi","year":"2023","journal-title":"J. King Saud Univ.-Comput. Inf. Sci."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Ahmed, F., Cui, Y., Fu, Y., and Chen, W. (2021, January 17\u201319). A graph neural network approach for product relationship prediction. Proceedings of the International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Online.","DOI":"10.1115\/DETC2021-69462"},{"key":"ref_32","unstructured":"Panford-Quainoo, K., Bose, A., and Defferrard, M. (2024, May 22). Bilateral Trade Modelling with Graph Neural Networks. ICLR Workshop on Practical ML for Developing Countries. Available online: https:\/\/www.researchgate.net\/profile\/Kobby-Panford-Quainoo\/publication\/339200492_Bilateral_Trade_Modeling_with_Graph_Neural_Networks\/links\/5f781d37299bf1b53e099940\/Bilateral-Trade-Modeling-with-Graph-Neural-Networks.pdf."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Di Paolo, G., Rincon-Yanez, D., and Senatore, S. (2023). A Quick Prototype for Assessing OpenIE Knowledge Graph-Based Question-Answering Systems. Information, 14.","DOI":"10.3390\/info14030186"},{"key":"ref_34","unstructured":"Rincon-Yanez, D., and Senatore, S. (June, January 29). FAIR Knowledge Graph construction from text, an approach applied to fictional novels. Proceedings of the 1st International Workshop on Knowledge Graph Generation from Text and the 1st International Workshop on Modular Knowledge Co-Located with 19th Extended Semantic Conference (ESWC 2022), Crete, Greece."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Poenaru-Olaru, L., Cruz, L., Rellermeyer, J., and Van Deursen, A. (2023, January 15\u201316). Maintaining and monitoring AIOps models against concept drift. Proceedings of the 2023 IEEE\/ACM 2nd International Conference on AI Engineering\u2013Software Engineering for AI (CAIN), Melbourne, Australia.","DOI":"10.1109\/CAIN58948.2023.00024"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1080\/01621459.1951.10500769","article-title":"The Kolmogorov-Smirnov test for goodness of fit","volume":"46","author":"Massey","year":"1951","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1038\/s42254-020-00275-1","article-title":"Economic complexity theory and applications","volume":"3","author":"Hidalgo","year":"2021","journal-title":"Nat. Rev. Phys."},{"key":"ref_38","first-page":"435","article-title":"Complex economic activities concentrate in large cities","volume":"6","author":"Balland","year":"2022","journal-title":"Nat. Hum. Behav."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Tiits, M., Karo, E., and Kalvet, T. Small countries facing the technological revolution: Fostering synergies between economic complexity and foresight research. Compet. Rev., 2024. in press.","DOI":"10.1108\/CR-03-2023-0051"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Bekkers, V., Edelenbos, J., and Steijn, B. (2011). Small States, Innovation and Administrative Capacity. Innovation in the Public Sector: Linking Capacity and Leadership, Palgrave Macmillan.","DOI":"10.1057\/9780230307520"},{"key":"ref_41","unstructured":"Tiits, M., and Kalvet, T. (2012). Nordic Small Countries in the Global High-Tech Value Chains: The Case of Telecommunications Systems Production in Estonia, TUT Ragnar Nurkse Department of Innovation and Governance. Available online: http:\/\/technologygovernance.eu\/files\/main\/2012022211372121.pdf."},{"key":"ref_42","unstructured":"Tiits, M., Kalvet, T., and Mehide, I. (2023). Goodtrade.ai Export Strategy Analytics Platform, Policy Lab. Available online: https:\/\/www.goodtrade.ai\/."},{"key":"ref_43","unstructured":"Kalvet, T., Tiits, M., Ounoughi, C., Ben Sassi, I., and Ben Yahia, S. (Manag. Mark. J., 2024). At the Crossroads of Product Complexity, Market Demand, and Machine Learning, Manag. Mark. J., accepted for publication."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Cuyvers, L., and Viviers, W. (2012). Export Promotion: A Decision Support Model Approach, Sun Press.","DOI":"10.18820\/9780992180614"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1108\/JITLP-11-2020-0061","article-title":"Identifying export opportunities for China in the \u201cBelt and Road Initiative\u201d group of countries: A decision support model approach","volume":"20","author":"Cameron","year":"2021","journal-title":"J. Int. Trade Law Policy"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Aucamp, M., Steenkamp, E.A., and Bezuidenhout, C. (2023). Comparing International Market Selection Methods Using Export Potential Values for South Africa. Int. Trade J., 1\u201323.","DOI":"10.1080\/08853908.2023.2166628"},{"key":"ref_47","unstructured":"Kalvet, T., and Tiits, M. (2024). Identification of Export-led Catching-up Opportunities in Turbulent Times, Unpublished manuscript."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/8\/6\/65\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:55:19Z","timestamp":1760108119000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/8\/6\/65"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,7]]},"references-count":47,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["bdcc8060065"],"URL":"https:\/\/doi.org\/10.3390\/bdcc8060065","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,7]]}}}