Prediction Dynamics launches hedge fund modelling platform

Aimed at high-end users, including hedge funds and proprietary trading desks in investment banks, Crucible is a flexible and scalable modelling system enabling quantitative researchers to build, analyse and maintain a large number of accurate and predictive financial models.

The financial prediction infrastructure has applications in systematic trading, active risk management and quantitative research, which can be used to build and maintain a large number of predictive models across a variety of financial markets and asset classes.

“The beta programme which started at the beginning of November last year has been completed, and now Crucible is live in two global banks and a hedge fund,” said John Carney, chief technology officer at Prediction Dynamics. “Three new clients – two hedge funds and another international bank – are due to roll out the application in the next few weeks.”

The core engines for building and analysing non-parametric multifactor models – FactorEngine and ModelEngine – are based on patent-pending technologies developed in-house.

FactorEngine enables clients to analyse and identify optimal factor sets that drive a market, while ModelEngine allows users to create non-parametric predictive models based on the factors defined by the FactorEngine. The multifactor models can be built with any number of relevant input factors.

Ease of implementation, so often a crucial factor when a new financial product is launched, is one of Crucible’s strengths. “Clients are usually up and running within a month,” claimed Carney. “One client, an options trading desk that wanted the software to predict implied volatility rolled out the application even quicker.”

  • LinkedIn  
  • Save this article
  • Print this page  

Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.

To access these options, along with all other subscription benefits, please contact [email protected] or view our subscription options here: http://subscriptions.risk.net/subscribe

You are currently unable to copy this content. Please contact [email protected] to find out more.

You need to sign in to use this feature. If you don’t have a Risk.net account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here: