Forecasting stock crash risk with machine learning

Machine learning techniques can be used to uncover nonlinear relationships between several variables to help forecast stock crash risk. As a result, the performance of quant equity strategies can be potentially enhanced by avoiding companies with elevated distress risk.


  • Laurens Swinkels

    Head of Quant Strategy

  • Tobias Hoogteijling


Significant developments in big data and machine learning (ML) are pushing back the frontier of quant investing. This progress has been facilitated by the increase in computational power, which enables the deployment and use of ML models. In contrast to rule-based models, ML models adopt a fully data-driven approach and are capable of modelling complex, nonlinear relationships. They can potentially uncover systematic and repeating patterns that simple linear models do not capture.

Relatedly, avoiding investments in companies that experience financial distress can potentially enhance the performance of quant equity strategies. That said, detecting those firms most likely to face distress in the future is far from straightforward. While there are numerous characteristics that can help forecast such outcomes, these variables perhaps do so most effectively in a nonlinear fashion or in specific combinations. Fortunately, ML techniques are designed to deal with such challenges.

In our white paper, we take a deep dive into how ML techniques can be used to forecast individual stock price crashes.

Download the publication

Important information

This information is for informational purposes only and should not be construed as an offer to sell or an invitation to buy any securities or products, nor as investment advice or recommendation. The contents of this document have not been reviewed by the Monetary Authority of Singapore (“MAS”). Robeco Singapore Private Limited holds a capital markets services license for fund management issued by the MAS and is subject to certain clientele restrictions under such license. An investment will involve a high degree of risk, and you should consider carefully whether an investment is suitable for you.