---
title: Predicting Stock Market Crises
url: https://www.ml-quant.com/papers/repec/gam-jjrfmx-v-17-y-2024-i-12-p-554-d-1540423/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: RePEc:gam:jjrfmx:v:17:y:2024:i:12:p:554-:d:1540423
source_url: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fwww.mdpi.com%2F1911-8074%2F17%2F12%2F554%2Fpdf%3Bh%3Drepec%3Agam%3Ajjrfmx%3Av%3A17%3Ay%3A2024%3Ai%3A12%3Ap%3A554-%3Ad%3A1540423
featured: 2024-12-18
citations: unknown
topic: Macro-Finance & Rates
---


# Predicting Stock Market Crises

Extreme gradient boosting (XGBoost) is the best machine learning algorithm for predicting African stock market crises, with historical stock prices and exchange rates as key predictors.

- Source: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fwww.mdpi.com%2F1911-8074%2F17%2F12%2F554%2Fpdf%3Bh%3Drepec%3Agam%3Ajjrfmx%3Av%3A17%3Ay%3A2024%3Ai%3A12%3Ap%3A554-%3Ad%3A1540423
- Identifier: RePEc:gam:jjrfmx:v:17:y:2024:i:12:p:554-:d:1540423
- Released: 2024-12-18
- First featured: Quant Letter No. 79 (2024-12-18): https://www.ml-quant.com/issues/2024-12-18/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Macro-Finance & Rates

## Related

- [Exchange Rates Forecasting with Interpretable Machine Learning](https://www.ml-quant.com/papers/repec/taf-apeclt-v-30-y-2023-i-15-p-2052-2059/): The Light Gradient Boosting Machine model has been found to be the most effective at predicting 12 exchange rates due to its ability to extract short-term information and robustness on small datasets.
- [Cross-Currency Basis Swaps Referencing Backward-Looking Rates](https://www.ml-quant.com/papers/arxiv/2410.08477/): The article discusses the pricing and hedging methods for financial products linked to the SOFR and AONIA, which have replaced LIBOR as the main benchmark rate for borrowing costs.
- [Topological components in a community currency network](https://www.ml-quant.com/papers/arxiv/2409.13674/): Analysis of Kenya's Sarafu token network data shows the significance of cycles in economic networks and potential system misuse by some users.
- [Machine Learning-based Relative Valuation of Municipal Bonds](https://www.ml-quant.com/papers/arxiv/2408.02273/): A data-driven model using the CatBoost algorithm is introduced to create a supervised similarity framework for the muni bond market, outperforming both rule-based and heuristic-based methods.
- [An Interpretable Machine Learning Approach in Predicting Inflation Using Payments System Data: A Case Study of Indonesia](https://www.ml-quant.com/papers/arxiv/2506.10369/): A study shows machine learning algorithms, particularly the Extreme Gradient Boosting model, are more effective than traditional methods in predicting Indonesia's inflation.
- [Forecasting China’s Inflation Rate: Evidence from Machine Learning Methods](https://www.ml-quant.com/papers/ssrn/4781171/): Eight machine learning models, notably the gradient boost decision tree and forecast combination model, excel in predicting China's inflation rate over the autoregressive benchmark.