IMF Working Papers

Surrogate Data Models: Interpreting Large-scale Machine Learning Crisis Prediction Models

By Jorge A Chan-Lau, Ruofei Hu, Maksym Ivanyna, Ritong Qu, Cheng Zhong

February 24, 2023

Download PDF

Preview Citation

Format: Chicago

Jorge A Chan-Lau, Ruofei Hu, Maksym Ivanyna, Ritong Qu, and Cheng Zhong. Surrogate Data Models: Interpreting Large-scale Machine Learning Crisis Prediction Models, (USA: International Monetary Fund, 2023) accessed December 12, 2024

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.

Summary

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.

Keywords: Crisis prediction, Explainable models, Machine learning, Surrogates

Publication Details

  • Pages:

    31

  • Volume:

    ---

  • DOI:

    ---

  • Issue:

    ---

  • Series:

    Working Paper No. 2023/041

  • Stock No:

    WPIEA2023041

  • ISBN:

    9798400234828

  • ISSN:

    1018-5941