CompatibL’s founder and Head of Quant Research, Alexander Sokol, sat down with WatersTechnology’s Victor Anderson to talk about the limitations of traditional interest rate pricing and risk models, and how these models can be enhanced with machine learning.
In this fireside chat, Alexander discusses the practical implications of firms adopting CompatibL’s new machine learning-based pricing and risk model for interest rate derivatives as well as the critical role machine learning plays in its accuracy. He also explains how capital markets firms can access the model and discloses the market’s response to it to date.
Click here to watch the video.
Interested in learning more? Watch our previous podcast on machine learning models and the challenge of validation.
What Are Autoencoder Market Models?
Autoencoder market models are a new type of interest rate models based on machine learning algorithms called autoencoders. CompatibL uses these algorithms to represent the historical yield curve and volatility surface shapes optimally, using the smallest number of model variables and without any preexisting notion of what their behavior should be.