Sponsored by ?

This article was paid for by a contributing third party.More Information.

Machine learning models: the validation challenge

Machine learning models are seeing increasing demand across the capital markets spectrum. But how can firms improve their chances of gaining internal and regulatory approval for these type of models?

Machine learning models are seeing increasing demand across the capital markets spectrum. But how can firms improve their chances of gaining internal and regulatory approval for these type of models?

Earlier this year, trading and risk software solutions provider CompatibL won the Risk Markets Technology Award for Best modelling innovation for its machine learning-based market generator, which enables more accurate modelling of market scenarios for interest rates and foreign exchange over longer-term time horizons. The firm’s latest research takes a step further with the development and application of autoencoder market models.

In this video, Alexander Sokol, founder and head of quant research at CompatibL  discusses the unique properties of this new breed of machine learning models and explains how firms can avoid the pitfalls of validation and regulatory approval for these type of models.

00:45 – Development and key attributes of machine learning-based autoencoder market models

02:54 – Applications of machine learning models in capital markets

05:30 – Model risk management and validation challenges

 

Read more on Compatibl’s autoencoder market model for interest rates

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