Cover IMF Working Papers
Buy Book in Print
Surrogate Data Models: Interpreting Large-scale Machine Learning Crisis Prediction Models
Author:
Mr. Jorge A Chan-Lau
Search for other papers by Mr. Jorge A Chan-Lau in
Current site
Google Scholar Close
,
Ruofei Hu
Search for other papers by Ruofei Hu in
Current site
Google Scholar Close
,
Maksym Ivanyna https://isni.org/isni/0000000404811396 International Monetary Fund

Search for other papers by Maksym Ivanyna in
Current site
Google Scholar Close
,
Ritong Qu
Search for other papers by Ritong Qu in
Current site
Google Scholar Close
, and
Cheng Zhong
Search for other papers by Cheng Zhong in
Current site
Google Scholar Close
Series:
IMF Working Papers
Volume/Issue:
Volume 2023: Issue 041
Language:
English
Publication Date:
24 Feb 2023
DOI:
https://doi.org/10.5089/9798400234828.001
ISBN:
9798400234828
ISSN:
1018-5941
Pages:
31
Keywords:
Crisis prediction; machine learning; surrogates; explainable models; IMF ML crisis; ML crisis prediction; Annex I. IMF ML; surrogate data models; model interpretability; Early warning systems; Yield curve; Deposit rates; Global
Legal-disclaimer:
IMF Working Papers describe research in progress by the author(s) and are published to elicit comments and to encourage debate. The views expressed in IMF Working Papers are those of the author(s) and do not necessarily represent the views of the IMF, its Executive Board, or IMF management.
Download PDF (3.4 MB) Download Epub
Machine learning models are becoming increasingly important in the prediction of economic crises. The models, however, use datasets comprising a large number of predictors (features) which impairs model interpretability and their ability to provide adequate guidance in the design of crisis prevention and mitigation policies. This paper introduces surrogate data models as dimensionality reduction tools in large-scale crisis prediction models. The appropriateness of this approach is assessed by their application to large-scale crisis prediction models developed at the IMF. The results are consistent with economic intuition and validate the use of surrogates as interpretability tools.
  • Collapse
  • Expand
Cover IMF Working Papers
IMF Working Papers
ISSN:
1018-5941
Publisher:
International Monetary Fund