Press, Research, and Articles

Press

BMO is using Riskfuel AI to accelerate Structured Note Pricing and Scenario Analysis

Bank of Montreal, Sept 2021

It’s official! BMO is a Riskfuel customer. After a successful pilot tackling one of their most complicated valuation models, we are joining forces to accelerate a whole slate of models used by the structured products desk.

Press

Eureka! The XVA Compute Challenge Solved

Wilmott Magazine, Sept 2021

XVA sees your trading book valuation problem and raises it by whatever magnitude induces hyperventilation. Ryan Ferguson discusses how a moment of inspiration led to total domination of the XVA compute problem

Press

BMO Financial Group Taps Riskfuel Analytics

Wilmott Magazine, Sept 2021

BMO Financial Group, the 8th largest bank, by assets, in North America, and Riskfuel Analytics a Toronto-based start-up, have announced a partnership to develop models for pricing and scenario analysis of structured derivatives transactions.

Press

How XVA quants learned to stop worrying and trust the machine

Risk.net Magazine, July 2021

Initial scepticism about using neural networks for derivatives pricing is giving way to enthusiasm. Last year, Scotiabank began using a deep neural network developed by Riskfuel, a fintech start-up, to approximate the outputs of the Monte Carlo models it uses for derivatives pricing.

Article

How Riskfuel is using Inlets to build machine learning models at scale

July 2021

In this blog, we’ll show how Riskfuel is using Inlets to securely oversee fully remote and hybrid cloud deployments.

Research

Arbitrage-Free Implied Vol Surface Generation with Variational Autoencoders

Aug 2021

We propose a hybrid method for generating arbitrage-free implied volatility  surfaces consistent with historical data by combining model-free Variational Autoencoders with continuous time stochastic differential equation driven models.

Press

Riskfuel Joins OnRamp Insurance Accelerator

May 2021

Riskfuel has been selected to take part in gener8tor’s OnRamp Insurance Accelerator in partnership with Allianz Life and Securian Financial. Riskfuel is one of five startups chosen from over 500 applicants to participate in gener8tor’s three-month, concierge accelerator program. 

Video

Completing Partial Implied Vol Surfaces with Variational Autoencoders

June 2021

In this talk, we will explain how variational autoencoders can remove human bias from this procedure and let the data speak for itself through unsupervised learning.

Press

Riskfuel Wins WatersTechnology's Best Sell-Side Newcomer Award

May 2021

Riskfuel has been awarded the Best Sell-Side Newcomer award by leading industry journal WatersTechnology.  Judged by a panel of industry experts from across the market, the highly valued Sell-Side Technology Awards  acknowledge excellence in trading technology. Riskfuel stands in the winners’ circle with other winners including Bloomberg and Numerix.

Video

Deeply Learning Derivatives: from Hilbert to Riskfuel

March 2021

In this talk, we will explain how graphical solvers of Hilbert’s day fit into the modern deep learning framework and ultimately allow us to build networks that replicate the solutions operator of stochastic differential equations governing the valuation of high dimensional contingent claims.

Video

Hands-Off Approach to Completing Implied Volatility Surfaces

March 2021

A type of deep neural network called the variational autoencoder is used to automatically complete partial volatility surfaces.

Research

Variational Autoencoders: A Hands-Off Approach to Volatility

Feb 2021

Variational autoencoders can be used to construct a complete volatility surface when only a small number of points are available without making assumptions about the process driving the underlying asset or the shape of the surface.

Press

Riskfuel Wins FIA Innovator of the Year Award

Nov 2020

Riskfuel was one of nine startups selected to participate in the annual Innovators Pavilion at the FIA Expo. The startups were evaluated on the degree of innovation, the relevance to derivatives markets, and the potential impact on the industry and judges chose Riskfuel for “its innovative solution to the challenges of derivatives valuation”.

Press

Riskfuel Customer Wins Top Risk.net Award

Feb 2021

Scotiabank wins Risk.net’s Technology Innovation of the Year. In partnership with tech vendor Riskfuel, the bank has trained deep neural networks (DNNs) as a valuation methodology within the framework. Put into practice, the platform’s web interface allows the bank’s front office to run XVA analysis with real-time data on either existing active trades or ‘what-if’ trades with potential clients.

Video

Ultra-fast and Accurate Derivatives Pricing with Deep Learning

Jun 2020

Technical details to accompany the article written by Ian Finder of Microsoft.

Article

Deep Learning to Jump

Oct 2020

We describe a Jump Unit that can be used to fit a step function with a simple neural network. Our motivation comes from quantitative finance problems where discontinuities often appear

Article

Exploring Riskfuel's Bermudan Swaption Pricing Demo

Feb 2020

This paper describes the Bermudan Swaption and its valuation models, and discusses a small case study to illustrate the accuracy of the Riskfuel model and compare its run-time performance again the target Quantlib model.

Press

Microsoft: Riskfuel Technology is 20,000,000x faster

Ian Finder, Microsoft, April 2020

Results of Microsoft collaboration with Riskfuel to measure performance of Riskfuel-accelerated production models. 

Research

Deeply Learning Derivatives: The Paper that Started It All

Oct 2018

This paper uses deep learning to value derivatives. The approach is broadly applicable, and we use a call option on a basket of stocks as an example. We show that the deep learning model is accurate and very fast, capable of producing valuations a million times faster than traditional models.

Article

1,000,000x faster models: how it works

Jan 2020

Deep neural networks can be trained to learn a functional approximation of derivatives valuation models that use mathematic simulations. Riskfuel AI-based technology cuts the computation costs to virtually zero allowing for on-demand recalculation of portfolio values and a complete up-to-the-second view on risk

Riskfuel

1,000,000x