Volatility spikes and impacts on liquidity

Predicting events, such as spikes in volatility, in financial markets is notoriously difficult.

At BestX we have been researching the use of Hawkes processes to model events, and our latest paper is a follow up to our publication on this subject in August 2020.

We extend the framework to model the impact on liquidity, and therefore transaction costs, with the use of an unsupervised machine learning method to categorise the number of observed liquidity states for a security. This provides the potential for an ‘early warning system’, resulting from monitoring, for example the VIX index, to indicate if sudden changes in liquidity are expected.

If you are a BestX client and would like a copy of the paper please contact us at support@bestx.co.uk.