## Predicting Fiscal Crises: A Machine Learning Approach

_IMF Working Papers, May 27, 2021_

## Source details

**Canonical URL:** [Predicting Fiscal Crises: A Machine Learning Approach](https://www.imf.org/en/publications/wp/issues/2021/05/27/predicting-fiscal-crises-a-machine-learning-approach-50234)

## Other formats

- [Markdown version](/en/publications/wp/issues/2021/05/27/predicting-fiscal-crises-a-machine-learning-approach-50234/index.md)
- [Structured JSON version](/en/publications/wp/issues/2021/05/27/predicting-fiscal-crises-a-machine-learning-approach-50234/index.json)
- [Bundle manifest](/en/publications/wp/issues/2021/05/27/predicting-fiscal-crises-a-machine-learning-approach-50234/bundle-manifest.json)

## Bibliographic details
- Authors: Klaus-Peter Hellwig
- Published: May 27, 2021
- Series: IMF Working Papers
- DOI: https://doi.org/10.5089/9781513573588.001

---

### Overview and methodology
- Assesses the ability of econometric and machine learning techniques to predict fiscal crises out of sample.
- Compares econometric approaches commonly used in policy applications with simple heuristic rules and with machine learning techniques.
- Machine learning techniques used: elastic net, random forest, gradient boosted trees.
- Expands the set of potential predictors and uses algorithmic selection techniques rather than relying on a small set of variables chosen by the literature.

### Key findings
- Econometric approaches used in many policy applications cannot outperform a simple heuristic rule of thumb.
- Machine learning techniques (elastic net, random forest, gradient boosted trees) deliver significant improvements in accuracy.
- Performance of machine learning techniques improves further, particularly for developing countries, when the set of potential predictors is expanded and algorithmic selection techniques are used.
- There is considerable agreement across learning algorithms in the set of selected predictors.
- Results confirm the importance of external sector stock and flow variables found in the literature.
- Demographics and the quality of governance emerge as important predictors of fiscal crises.
- Fiscal variables appear to have less predictive value.
- Public debt matters only to the extent that it is owed to external creditors.

### Implications for practice and analysis
- Relying on a small set of variables deemed important by prior literature may limit predictive performance; algorithmic selection across a broader predictor set can improve results.
- Machine learning approaches can provide materially better out-of-sample prediction of fiscal crises than standard econometric models and simple heuristics.
- Particular gains from machine learning are observed for developing countries when broader predictor sets are considered.

*Source: Predicting Fiscal Crises: A Machine Learning Approach (IMF Working Paper by Klaus-Peter Hellwig, May 27, 2021).*

---

## Content in this bundle

- **Working Paper**
  - [Working Paper (Markdown version)](/-/media/files/publications/wp/2021/english/wpiea2021150-print-pdf.pdf.md){rel="alternate" type="text/markdown"}
  - [Working Paper (PDF)](/-/media/files/publications/wp/2021/english/wpiea2021150-print-pdf.pdf){rel="external" type="application/pdf"}

---

_Source: https://www.imf.org/en/publications/wp/issues/2021/05/27/predicting-fiscal-crises-a-machine-learning-approach-50234_