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 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 these on flows. In this paper, we develop new method impact individual flows that does not require ad hoc assumptions how aggregate provisions. Building recent developments machine learning variable selection literature, propose data-driven methods for selecting most important quantifying their We find related antidumping, technical barriers facilitation are associated enhancing trade-increasing effect agreements.