Structural Reforms and Economic Growth: A Machine Learning Approach

Structural Reforms and Economic Growth: A Machine Learning Approach


Anil Ari; Gabor Pula; Sun of Liyang

Publication date:

September 16, 2022

Electronic access:

Free download. Use the free Adobe Acrobat Reader software to view this PDF file

Disclaimer: IMF Working Papers describe ongoing research by the author(s) and are published to elicit comment and encourage debate. The opinions expressed in IMF Working Papers are those of the authors and do not necessarily represent the views of the IMF, its Executive Board, or IMF management.


The qualitative and granular nature of most structural indicators and the variety of data sources complicate the consistency of cross-country assessments and empirical analyses. We overcome these problems by using a machine learning approach (the partial least squares method) to combine a large set of cross-country structural indicators into a small number of synthetic scores that correspond to key structural domains and are suitable for consistent quantitative comparisons. across countries and time. With this newly constructed dataset of synthetic structural scores in 126 countries between 2000 and 2019, we establish stylized facts about structural gaps and reforms, and analyze the impact of reforms targeting different structural areas on economic growth. Our results suggest that structural reforms in the area of ​​product, labor and capital markets as well as the legal system have a significant impact on economic growth in a 5-year horizon, with a one standard deviation improvement in the one of these areas of reform increasing cumulative 5-year growth by 2 to 6 percent. We also see synergies between different structural areas, in particular between product and labor market reforms.

Sherry J. Basler