AFTAs 2022: Most innovative third-party technology vendor (analytics)—Numerix

Project: CrossAsset


Commodity markets are currently experiencing significant uncertainty and crack spread and calendar spread trading have become important means of hedging positions. Numerix has focused on modeling stochastic spreads between different underlyings such as crude oil and gasoline futures and implemented a two-factor Quasi-Gaussian Andersen model. To handle new underlier price distributions when values are close to zero, the Bachelier model for commodities was developed to supplement the Black model in commodity pricing.


Volatile markets require advanced modeling of underliers when the corresponding prices move in wider ranges, including moves around zero or into negative territory as crude oil did in April 2020. These volatile market dynamics pose significant challenges to quantitative pricing models. Numerix is well known for the flexibility, accuracy, transparency and performance of its various models, essential for navigating the fast-evolving commodities markets while also helping firms to comply with their regulatory obligations. 

“Numerix commodity analytics are unique in their sophisticated modeling, transparency and flexible trade-term capturing, plus they provide pricing, potential future exposure, value at risk and XVA analytics all in the same, consistent framework. There is no other vendor in the commodity space who can provide such a competitive suite of analytics.”

Examples of innovation

The two-factor Quasi-Gaussian Andersen model was added to Numerix’s model library, enabling clients to more accurately handle stochastic spreads between different underlyings. 

A historical calibration tool was released, which enables the fast calibration of some of the parameters of the model to historical time-series data. This historical calibrator was implemented in Python using optimization algorithms from TensorFlow and can be run on AWS.

Future developments

Numerix will continue to focus on the development of the Andersen Commodity model (natural gas) to encapsulate the Gabillon model (oil) with historical calibration.

Why they won

Numerix follows up its win in the best agile initiative category in last year’s AFTAs by taking home the most innovative third-party technology vendor (analytics) category in this year’s edition, thanks to its CrossAsset derivatives pricing and risk management analytics library. CrossAsset itself is not new by any means, but its recent enhancements focused on the commodity market are, especially the addition of its two-factor Quasi-Gaussian Andersen model, designed to allow commodity traders to more accurately handle stochastic spreads between different underlying commodities.  

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 or view our subscription options here:

You are currently unable to copy this content. Please contact to find out more.

Most read articles loading...

You need to sign in to use this feature. If you don’t have a WatersTechnology 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