IDEAS home Printed from https://ideas.repec.org/p/cir/cirwor/2025s-14.html

Beyond PPML: Exploring Machine Learning Alternatives for Gravity Model Estimation in International Trade

Author

Listed:
  • Lucien Chaffa
  • Martin Trépanier
  • Thierry Warin

Abstract

This study investigates the potential of machine learning (ML) methods to enhance the estimation of the gravity model, a cornerstone of international trade analysis that explains trade flows based on economic size and distance. Traditionally estimated using methods such as the Poisson Pseudo Maximum Likelihood (PPML) approach, gravity models often struggle to fully capture nonlinear relationships and intricate interactions among variables. Leveraging data from Canada and the US, one of the largest bilateral trading relationships in the world, this paper conducts a comparative analysis of traditional and ML approaches. The findings reveal that ML methods can significantly outperform traditional approaches in predicting trade flows, offering a robust alternative for capturing the complexities of global trade dynamics. These results underscore the value of integrating ML techniques into trade policy analysis, providing policymakers and economists with improved tools for decision-making. Cette étude examine le potentiel des méthodes d'apprentissage automatique (ML) pour améliorer l'estimation du modèle de gravité, une méthode clé de l'analyse du commerce international qui explique les flux commerciaux en fonction de la taille de l'économie et de la distance. Traditionnellement estimés à l'aide de méthodes telles que l'approche du pseudo-maximum de vraisemblance de Poisson (PPML), les modèles de gravité ont souvent du mal à saisir pleinement les relations non linéaires et les interactions complexes entre les variables. En s'appuyant sur les données du Canada et des États-Unis, l'une des relations commerciales bilatérales les plus importantes au monde, cet article effectue une analyse comparative des approches traditionnelles et des approches par apprentissage automatique. Les résultats révèlent que les méthodes de ML peuvent être nettement plus performantes que les approches traditionnelles pour prédire les flux commerciaux, offrant ainsi une alternative robuste pour saisir les complexités de la dynamique du commerce mondial. Ces résultats soulignent la valeur de l'intégration des techniques de ML dans l'analyse de la politique commerciale, fournissant aux décideurs politiques et aux économistes des outils améliorés pour la prise de décision.

Suggested Citation

  • Lucien Chaffa & Martin Trépanier & Thierry Warin, 2025. "Beyond PPML: Exploring Machine Learning Alternatives for Gravity Model Estimation in International Trade," CIRANO Working Papers 2025s-14, CIRANO.
  • Handle: RePEc:cir:cirwor:2025s-14
    as

    Download full text from publisher

    File URL: https://cirano.qc.ca/files/publications/2025s-14.pdf
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. J. M. C. Santos Silva & Silvana Tenreyro, 2022. "The Log of Gravity at 15," Portuguese Economic Journal, Springer;Instituto Superior de Economia e Gestao, vol. 21(3), pages 423-437, September.
    2. Holger Breinlich & Dennis Novy & J. M. C. Santos Silva, 2024. "Trade, Gravity, and Aggregation," The Review of Economics and Statistics, MIT Press, vol. 106(5), pages 1418-1426, September.
    3. Anna D’Ambrosio & Sandro Montresor, 2022. "The pro-export effect of subnational migration networks: new evidence from Spanish provinces," Review of World Economics (Weltwirtschaftliches Archiv), Springer;Institut für Weltwirtschaft (Kiel Institute for the World Economy), vol. 158(1), pages 53-107, February.
    4. Santos Silva, J.M.C. & Tenreyro, Silvana, 2011. "Further simulation evidence on the performance of the Poisson pseudo-maximum likelihood estimator," Economics Letters, Elsevier, vol. 112(2), pages 220-222, August.
    5. J. M. C. Santos Silva & Silvana Tenreyro, 2006. "The Log of Gravity," The Review of Economics and Statistics, MIT Press, vol. 88(4), pages 641-658, November.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Eduardo Rodrigues Sanguinet & Augusto Mussi Alvim & Miguel Atienza, 2022. "Trade agreements and participation in global value chains: Empirical evidence from Latin America," The World Economy, Wiley Blackwell, vol. 45(3), pages 702-738, March.
    2. Doukoure Charle Fe, 2021. "Trade flows between the West African Economic and Monetary Union's members so little: does exports structure matter ?," Economics Bulletin, AccessEcon, vol. 41(2), pages 816-833.
    3. Mohamed Amara & Hatem Jemmali, 2018. "Deciphering the Relationship Between Internal Migration and Regional Disparities in Tunisia," Social Indicators Research: An International and Interdisciplinary Journal for Quality-of-Life Measurement, Springer, vol. 135(1), pages 313-331, January.
    4. Agostino Capponi & Zhaonan Qu, 2025. "Handling Sparse Non-negative Data in Finance," Papers 2509.01478, arXiv.org.
    5. Bacher, Etienne & Beine, Michel & Rapoport, Hillel, 2025. "Do Anti-Immigration Attitudes Discourage Immigration? Evidence from a New Instrument," IZA Discussion Papers 18192, IZA Network @ LISER.
    6. Marie M Stack & Rob Ackrill & Martin Bliss, 2019. "Sugar trade and the role of historical colonial linkages," European Review of Agricultural Economics, Oxford University Press and the European Agricultural and Applied Economics Publications Foundation, vol. 46(1), pages 79-108.
    7. Maria Cipollina & Luca De Benedictis & Luca Salvatici & Claudio Vicarelli, 2016. "Policy Measurement And Multilateral Resistance In Gravity Models," Working Papers LuissLab 16130, Dipartimento di Economia e Finanza, LUISS Guido Carli.
    8. Tamara de la Mata, 2014. "Does trade creation by social and business networks hold in services?," Applied Economics, Taylor & Francis Journals, vol. 46(13), pages 1509-1525, May.
    9. Martin, Will, 2020. "Making Gravity Great Again," 2020: Economic Implications of COVID-19, December 14-15, Virtual Platform 339376, International Agricultural Trade Research Consortium.
    10. Chowdhury, Subhasish M. & Jewell, Sarah & Singleton, Carl, 2024. "Can awareness reduce (and reverse) identity-driven bias in judgement? Evidence from international cricket," Journal of Economic Behavior & Organization, Elsevier, vol. 226(C).
    11. Nazir Muhammad Abdullahi & Xuexi Huo & Qiangqiang Zhang & Aminah Bolanle Azeez, 2021. "Determinants and Potential of Agri-Food Trade Using the Stochastic Frontier Gravity Model: Empirical Evidence From Nigeria," SAGE Open, , vol. 11(4), pages 21582440211, December.
    12. Stacy Julius & Nnanna P. Azu & Maimuna Y. Muhammad, 2019. "Assessing the Impact of Terrorism in Trade Development in the SADC Region: A Gravity Model Approach," Asian Economic and Financial Review, Asian Economic and Social Society, vol. 9(10), pages 1147-1159, October.
    13. Aiyar, Shekhar & Calomiris, Charles W. & Hooley, John & Korniyenko, Yevgeniya & Wieladek, Tomasz, 2014. "The international transmission of bank capital requirements: Evidence from the UK," Journal of Financial Economics, Elsevier, vol. 113(3), pages 368-382.
    14. Jhorland Ayala-García & Federico Ceballos-Sierra, 2024. "How do environmental shocks affect competitors in a supply chain? Evidence from a competitors’ weighting matrix," Documentos de trabajo sobre Economía Regional y Urbana 324, Banco de la Republica de Colombia.
    15. Fally, Thibault, 2015. "Structural gravity and fixed effects," Journal of International Economics, Elsevier, vol. 97(1), pages 76-85.
    16. Kareem, Fatima Olanike & Martinez-Zarzoso, Inmaculada & Brümmer, Bernhard, 2016. "Fitting the Gravity Model when Zero Trade Flows are Frequent: a Comparison of Estimation Techniques using Africa's Trade Data," GlobalFood Discussion Papers 230588, Georg-August-Universitaet Goettingen, GlobalFood, Department of Agricultural Economics and Rural Development.
    17. Head, Keith & Mayer, Thierry, 2014. "Gravity Equations: Workhorse,Toolkit, and Cookbook," Handbook of International Economics, in: Gopinath, G. & Helpman, . & Rogoff, K. (ed.), Handbook of International Economics, edition 1, volume 4, chapter 0, pages 131-195, Elsevier.
    18. Koffi Dumor & Yao Li & Ma Yongkai & Enock Mintah Ampaw & Hafez Komla Dumor, 2022. "Evaluating the belt and road initiative effects on trade and migration: Evidence from the East African community," African Development Review, African Development Bank, vol. 34(1), pages 16-28, March.
    19. Michel Beine & Luisito Bertinelli & Rana Cömertpay & Anastasia Litina & Jean-François Maystadt, 2020. "The Gravity Model of Forced Displacement Using Mobile Phone Data," DEM Discussion Paper Series 20-13, Department of Economics at the University of Luxembourg.
    20. Nunnenkamp, Peter & Öhler, Hannes & Sosa Andrés, Maximiliano, 2012. "Need, merit, and politics in multilateral aid allocation: A district-level analysis of World Bank projects in India," Kiel Working Papers 1783, Kiel Institute for the World Economy.

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;
    ;
    ;
    ;
    ;

    JEL classification:

    • F10 - International Economics - - Trade - - - General
    • F14 - International Economics - - Trade - - - Empirical Studies of Trade
    • C13 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods and Methodology: General - - - Estimation: General
    • C45 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods: Special Topics - - - Neural Networks and Related Topics

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:cir:cirwor:2025s-14. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Webmaster (email available below). General contact details of provider: https://edirc.repec.org/data/ciranca.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.