15-06-2022

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.

Download the publication

    Authors

  • Laurens Swinkels - Head of Quant Strategy

    Laurens Swinkels

    Head of Quant Strategy

  • Tobias Hoogteijling - Researcher

    Tobias Hoogteijling

    Researcher

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

The contents of this document have not been reviewed by the Securities and Futures Commission ("SFC") in Hong Kong. If you are in any doubt about any of the contents of this document, you should obtain independent professional advice. This document has been distributed by Robeco Hong Kong Limited (‘Robeco’). Robeco is regulated by the SFC in Hong Kong. This document has been prepared on a confidential basis solely for the recipient and is for information purposes only. Any reproduction or distribution of this documentation, in whole or in part, or the disclosure of its contents, without the prior written consent of Robeco, is prohibited. By accepting this documentation, the recipient agrees to the foregoing This document is intended to provide the reader with information on Robeco’s specific capabilities, but does not constitute a recommendation to buy or sell certain securities or investment products. Investment decisions should only be based on the relevant prospectus and on thorough financial, fiscal and legal advice. Please refer to the relevant offering documents for details including the risk factors before making any investment decisions. The contents of this document are based upon sources of information believed to be reliable. This document is not intended for distribution to or use by any person or entity in any jurisdiction or country where such distribution or use would be contrary to local law or regulation. Investment Involves risks. Historical returns are provided for illustrative purposes only and do not necessarily reflect Robeco’s expectations for the future. The value of your investments may fluctuate. Past performance is no indication of current or future performance.