Machine Learning in International Trade Research : Evaluating the Impact of Trade Agreements

Modern trade agreements contain a large number of provisions besides tariff reductions, in areas as diverse as services trade, competition policy, trade-related investment measures, or public procurement. Existing research has struggled with overfitting and severe multicollinearity problems when try...

Full description

Bibliographic Details
Main Authors:	Breinlich, Holger, Corradi, Valentina, Rocha, Nadia, Ruta, Michele, Santos Silva, J.M.C., Zylkin, Tom
Format:	Working Paper
Language:	English
Published:	World Bank, Washington, DC 2021
Subjects:	TRADE POLICY TRADE AGREEMENTS PREFERENTIAL TRADE AGREEMENTS DEEP TRADE AGREEMENT MACHINE LEARNING LASSO
Online Access:	http://documents.worldbank.org/curated/en/730781618338899906/Machine-Learning-in-International-Trade-Research-Evaluating-the-Impact-of-Trade-Agreements http://hdl.handle.net/10986/35451

id	okr-10986-35451
recordtype	oai_dc
spelling	okr-10986-354512022-09-20T00:08:41Z Machine Learning in International Trade Research : Evaluating the Impact of Trade Agreements Breinlich, Holger Corradi, Valentina Rocha, Nadia Ruta, Michele Santos Silva, J.M.C. Zylkin, Tom TRADE POLICY TRADE AGREEMENTS PREFERENTIAL TRADE AGREEMENTS DEEP TRADE AGREEMENT MACHINE LEARNING LASSO Modern trade agreements contain a large number of provisions besides tariff reductions, in areas as diverse as services trade, competition policy, trade-related investment measures, or public procurement. Existing research has struggled with overfitting and severe multicollinearity problems when trying to estimate the effects of these provisions on trade flows. This paper builds on recent developments in the machine learning and variable selection literature to propose novel data-driven methods for selecting the most important provisions and quantifying their impact on trade flows. The proposed methods have the advantage of not requiring ad hoc assumptions on how to aggregate individual provisions and offer improved selection accuracy over the standard lasso. The analysis finds that provisions related to technical barriers to trade, antidumping, trade facilitation, subsidies, and competition policy are associated with enhancing the trade-increasing effect of trade agreements. 2021-04-19T19:38:00Z 2021-04-19T19:38:00Z 2021-04 Working Paper http://documents.worldbank.org/curated/en/730781618338899906/Machine-Learning-in-International-Trade-Research-Evaluating-the-Impact-of-Trade-Agreements http://hdl.handle.net/10986/35451 English Policy Research Working Paper;No. 9629 CC BY 3.0 IGO http://creativecommons.org/licenses/by/3.0/igo World Bank World Bank, Washington, DC Publications & Research Publications & Research :: Policy Research Working Paper
repository_type	Digital Repository
institution_category	Foreign Institution
institution	Digital Repositories
building	World Bank Open Knowledge Repository
collection	World Bank
language	English
topic	TRADE POLICY TRADE AGREEMENTS PREFERENTIAL TRADE AGREEMENTS DEEP TRADE AGREEMENT MACHINE LEARNING LASSO
spellingShingle	TRADE POLICY TRADE AGREEMENTS PREFERENTIAL TRADE AGREEMENTS DEEP TRADE AGREEMENT MACHINE LEARNING LASSO Breinlich, Holger Corradi, Valentina Rocha, Nadia Ruta, Michele Santos Silva, J.M.C. Zylkin, Tom Machine Learning in International Trade Research : Evaluating the Impact of Trade Agreements
relation	Policy Research Working Paper;No. 9629
description	Modern trade agreements contain a large number of provisions besides tariff reductions, in areas as diverse as services trade, competition policy, trade-related investment measures, or public procurement. Existing research has struggled with overfitting and severe multicollinearity problems when trying to estimate the effects of these provisions on trade flows. This paper builds on recent developments in the machine learning and variable selection literature to propose novel data-driven methods for selecting the most important provisions and quantifying their impact on trade flows. The proposed methods have the advantage of not requiring ad hoc assumptions on how to aggregate individual provisions and offer improved selection accuracy over the standard lasso. The analysis finds that provisions related to technical barriers to trade, antidumping, trade facilitation, subsidies, and competition policy are associated with enhancing the trade-increasing effect of trade agreements.
format	Working Paper
author	Breinlich, Holger Corradi, Valentina Rocha, Nadia Ruta, Michele Santos Silva, J.M.C. Zylkin, Tom
author_facet	Breinlich, Holger Corradi, Valentina Rocha, Nadia Ruta, Michele Santos Silva, J.M.C. Zylkin, Tom
author_sort	Breinlich, Holger
title	Machine Learning in International Trade Research : Evaluating the Impact of Trade Agreements
title_short	Machine Learning in International Trade Research : Evaluating the Impact of Trade Agreements
title_full	Machine Learning in International Trade Research : Evaluating the Impact of Trade Agreements
title_fullStr	Machine Learning in International Trade Research : Evaluating the Impact of Trade Agreements
title_full_unstemmed	Machine Learning in International Trade Research : Evaluating the Impact of Trade Agreements
title_sort	machine learning in international trade research : evaluating the impact of trade agreements
publisher	World Bank, Washington, DC
publishDate	2021
url	http://documents.worldbank.org/curated/en/730781618338899906/Machine-Learning-in-International-Trade-Research-Evaluating-the-Impact-of-Trade-Agreements http://hdl.handle.net/10986/35451
_version_	1764483060955348992

Machine Learning in International Trade Research : Evaluating the Impact of Trade Agreements

Similar Items