Skip to main content

Advanced mathematical techniques increase confidence in banking

Bayesian quantile regression incorporated in major statistical software suites globally

The need

Following the 2007 financial crisis, modelling of financial risk became a significant issue in banking and finance. Quantile-based risk measures are more sensitive to events that happen in the tail end of distribution – the tail risk. Bayesian methods allow prior knowledge of the process to be incorporated into the risk analysis. 

The solution

Bayesian quantile regression (BQR) was first introduced by Prof Yu and has been available for risk analysis by the millions of users of the statistical software suite SAS since 2009. The SAS software is currently installed at 83,000 business, government and university sites worldwide. BQR has been particularly useful to banks and made available to them through the R and SAS software packages. 

The outcome

  • Advanced mathematical techniques for risk analysis incorporated in major statistical software suites

  • People’s Bank of China were able to increase their investments in individual businesses year-on-year because with the BQR model they were more confident about the profit on each investment. In one year alone (2015), they used Prof Yu’s model to make decisions on 20,000 business cases worth £110,000,000. 

  • The China Minsheng Bank believe the use of more reliable risk management systems enabled by BQR has allowed them to provide loans to 2,000 more customers per annum.

Partnering with confidence

Organisations interested in our research can partner with us with confidence backed by an external and independent benchmark: The Knowledge Exchange Framework. Read more.

Case study last modified 12/10/2022

Contact us

  • Get in touch
    If you are interested in working with our experts please leave us your details and we will be in touch with you shortly.
  • Name