Forecasting Stock Market Crashes via Machine Learning
63 Pages Posted: 11 May 2021 Last revised: 6 Sep 2022
Date Written: May 10, 2021
This paper uses a comprehensive set of variables from the five largest Eurozone countries to compare the performance of simple univariate and machine learning-based multivariate models in forecasting stock market crashes. In terms of statistical predictive performance, a support vector machine-based prediction model outperforms a random classifier and is superior to the average univariate benchmark as well as a multivariate logistic regression model. Incorporating nonlinear and interactive effects is both imperative and foundation for the outperformance of support vector machines. Their ability to forecast stock market crashes out-of-sample translates into substantial value-added to active investors. From a policy perspective, the use of machine learning-based crash prediction models can help activate macroprudential tools in time, aiming at safeguarding financial and macroeconomic stability.
Keywords: extreme event prediction, stock market crashes, machine learning, active trading strategy
JEL Classification: G11, G12, G14, G17
Suggested Citation: Suggested Citation