Surrogate Data Models: Interpreting Large-scale Machine Learning Crisis Prediction Models
Author/Editor: Jorge A Chan-Lau, Ruofei Hu, Maksym Ivanyna, Ritong Qu, Cheng Zhong
Release Date: © February, 2023
ISBN
: 979-8-40023-482-8
English
Stock Status: On back-order
Languages and formats available
English | French | Spanish | Arabic | Russian | Chinese | Portuguese | |
Paperback | Yes | ||||||
Yes | |||||||
ePub | Yes |
Description
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.
More publications in this series: Working Papers
More publications by: Jorge A Chan-Lau ; Ruofei Hu ; Maksym Ivanyna ; Ritong Qu ; Cheng Zhong