Sell-Side Technology Awards 2023: Best sell-side newcomer product (trading, pricing and analytics)—CompatibL

Overview

CompatibL Platform, featuring autoencoder market models (AEMMs), is designed to support forward-looking risk scenarios and portfolio valuation calculations. These scenarios include all possible interest rate regimes covered by historical time series for all currencies, some with interest rates reaching new levels and others with rates staying at moderate or low levels.

The solution

Users can choose AEMMs for all calculations, from valuation and credit valuation adjustments in risk-neutral measures to counterparty credit risk and limits in real-world measures. The variational autoencoders (VAEs) in these models are trained on a large and diverse dataset that includes multiple decades of historical time series across numerous currencies. This allows AEMMs to represent the diverse risk scenarios needed in today’s capital markets with their unprecedented levels of risk.

Secret sauce

The mapping produced by the VAEs means that model factors are adjusted to the level of the interest rates, producing the best fit across all market regimes. The autoencoder-generated map of market regimes can also be used to identify the possible direction of evolution beginning with the current market regime, a valuable feature in today’s uncertain market environment.

Recent enhancements

• Extended the use of AEMMs for additional asset classes
• Improved the performance and efficiency of AEMMs
• Enhanced the visualization capabilities when using autoencoders for the visualization of complex market data and identification of market data regimes

Future objectives

CompatibL plans to:

• Extend the use of autoencoders in market models for credit
• Extend the use of autoencoders in market models for commodities

Why they won

CompatibL follows up its win in the most innovative third-party technology vendor (AI and machine learning) category in last year’s American Financial Technology Awards (AFTAs) by winning this award on the back of the innovations it has introduced, most notably with the inclusion of autoencoder market models in the firm’s flagship offering, CompatibL Platform. These models are especially beneficial for users during times of extreme uncertainty and volatility because of their ability to accurately predict risk measures for which historical scenarios and data does not exist.