Machine Learning and Causality: The Impact of Financial Crises on Growth

31 Pages Posted: 3 Dec 2019

See all articles by Andrew Tiffin

Andrew Tiffin

International Monetary Fund (IMF)

Date Written: November 2019

Abstract

Machine learning tools are well known for their success in prediction. But prediction is not causation, and causal discovery is at the core of most questions concerning economic policy. Recently, however, the literature has focused more on issues of causality. This paper gently introduces some leading work in this area, using a concrete example-assessing the impact of a hypothetical banking crisis on a country's growth. By enabling consideration of a rich set of potential nonlinearities, and by allowing individually-tailored policy assessments, machine learning can provide an invaluable complement to the skill set of economists within the Fund and beyond.

Keywords: Financial soundness indicators, Economic analysis, Financial crises, Banking crisis, Economic sectors, Supervised machine learning, causal inference, policy evaluation, counterfactual prediction, randomized experiments, treatment effects, financial crisis., WP, treatment effect, covariates, dataset, machine learn

JEL Classification: C21, C40, E6, E44, E50, E60, F3, G01, G20, E01, E6

Suggested Citation

Tiffin, Andrew, Machine Learning and Causality: The Impact of Financial Crises on Growth (November 2019). IMF Working Paper No. 19/228, Available at SSRN: https://ssrn.com/abstract=3496706

Andrew Tiffin (Contact Author)

International Monetary Fund (IMF) ( email )

700 19th Street, N.W.
Washington, DC 20431
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
165
Abstract Views
778
Rank
325,881
PlumX Metrics