Det er lykkedes at lande Dr. Antoine Savine, Superfly Analytics, Danske Bank, til et webinar udbudt af Finansforeningen. Her vil han give dig en grunding historiefortælling omkring emner, som eksempelvis automatic adjoint differentiation (AAD), classic automatic differentiation algorithms, reverse order differentiation og generalizing classic backpropagation to arbitrary computations – med andre ord, et absolut “I must participate event” for super-nørder indenfor den danske finansielle sektor – og alligevel områder, som formentlig bliver alment kendte begreber indenfor en overskuelig fremtid. Vi byder dig velkommen til fremtiden indenfor dansk finans!

Webinaret afholdes på engelsk.

You don’t want to miss this unique opportunity to meet one of the brightest minds in Machine Learning (ML), Dr. Antoine Savine from Superfly Analytics, Danske Bank, and participate at his presentation: Deep Analytics; Risk Management with AI

AI and Machine Learning. The ML trends is one of the most promising and profound areas in risk management, gaining momentum in the financial sector. Not only in Asset Management (as we will witness soon – see “Asset Management & AI”, scheduled for June 25th), but also within trading, risk and compliance, just to name a few.
The webinar will focus on Differential ML, an extension of supervised learning, where ML models are trained on examples of not only inputs and labels, but also differentials of labels to inputs.

Dr. Antoine Savine will take us into the world of ML and present differential deep learning (DL), arguably the strongest application. Standard DL trains neural networks (NN) on punctual examples, whereas differential DL teaches them the shape of the target function, resulting in vastly improved performance, illustrated with a number of numerical examples, both idealized and real world.

Differential ML is applicable in situations where high quality first order derivatives, with respect to training inputs, are available. In the context of financial derivatives and risk management, pathwise differentials are efficiently computed with automatic adjoint differentiation. Differential machine learning, combined with AAD, provides extremely effective pricing, valuation outputs and risk approximations. Antoine will show, how one can produce fast pricing analytics – and in realtime – in models too complex for closed form solutions, extract the risk factors of complex transactions and trading books, and effectively compute risk management metrics like reports across a large number of scenarios, backtesting and simulation of hedge strategies, or regulations like XVA, CCR, FRTB or SIMM-MVA.

So if you are into machine learning in general, and want to understand what is going on and what the future brings, this is a webinar you don’t want to miss.