Flying Monday to Amsterdam with my colleagues from Superfly Analytics of Danske Bank, including Brian Huge and Ove Scavenius, to attend the RiskMinds 2019 risk management conference and the award ceremony, where our group is nominated for ‘Excellence in risk management and modeling’. We will be presenting our vision of modern risk management systems and the ‘One Analytics’ platform: full front to back consistency with scripting of cash-flows , model hierarchies and AAD. Further, we will present ‘Deep Analytics’: leveraging risk management systems with AI to learn revaluation and risk analytics on the fly. For those unable to attend, we posted our slides online here:
My paper “Computation graphs for AAD and Machine Learning part I: Introduction to computation graphs and automatic differentiation” was just published in Wilmott, the first in a series of articles with code dedicated to Computational Finance. It covers computation graphs, backpropagation, AAD and implementation in finance, taking inspiration in the recent achievements of the Superfly Analytics group of Danske Bank.
By Brian Huge and Antoine Savine
Deep learning derivatives pricing, and risk, with differential regularisation
See our slides here:
Back in March, I gave a series of lectures at Kings College London on automatic adjoint differentiation, backpropagation and machine learning, and how it all connects and applies to risk management of financial derivatives.
The lectures were recorded and made freely available online, either from Kings own page:
or, on YouTube:
It is my understanding that the audience at Kings found the talks useful, and I hope that they may be beneficial to a wider audience on the internet.
By popular demand, I just made my tutorial for exporting your C++ functions to Excel, a stand-alone GitHub repo:
We had another fantastic conference from QuantMinds last week in Vienna, where I was honored to chair the Numerical and Computational Finance stream. The agenda was dominated by the application of machine learning to derivatives finance.
Brian Huge and I gave a talk on Deep Analytics to a vast audience of delegates, professionals and academics, including Bruno Dupire, Leif Andersen, Jesper Andreasen, Michael Dempster and many others. The room was full and some had to stand in the back for the whole 90 minutes!
Among many presentations focusing on big data, large infrastructures and deep neural networks, our talk stood out by a principled approach and the systematic integration and synergy of new methods from the deep learning world within the mature financial theoretical framework and in combination with other powerful financial techniques. Following Jesper Andreasen’s tradition of “computing XVA on iPad Mini”, we effectively trained small networks, within seconds to minutes, on trader workstations. We also proposed new techniques for the improvement of financial neural networks, not necessarily appropriate to other contexts, but particularly powerful for the pricing and revaluation of derivatives transactions and trading books. The most prominent of these techniques, “differential regularization”, leverages both AAD on the simulation side and back-prop on the neural side.
We extend billion thanks to our exceptional audience for a fantastic reception and feedback, to our colleagues of Danske Bank’s quantitative research for helping us polish the material and delivery, and to Danske Bank itself for encouraging and nurturing the research and development efforts necessary to properly produce game changing technologies like scripting, model hierarchies, parallel simulations, AAD and now, neural analytics.
It goes without saying that we heard other exceptional presentations, including, in my stream alone, Pierre Henry-Labordere‘s ground breaking work on the application of Schrodinger Bridges to stochastic volatility, and Jesper Andreasen’s rare and inspiring talk about scripting.
Outside of the stream, a series of filmed interviews gave me a chance to express my views on automatic differentiation (AAD), its exceptional contribution to risk management, its evolution and its future in quantitative finance combined with machine learning.
Finally, the presentation and interviews gave us an opportunity to introduce Danske Bank’s vision of “One Calculation Engine”. A core principle within Danske Bank’s quantitative research, this is a unique, single and consistent framework for the risk management of derivatives and the computation of regulations like XVA, CCR, FRTB… with the articulation of scripting, model hierarchies, parallel simulation engines, AAD and… deep analytics.
Antoine Savine, May 2019
The Practitioners’ Lecture Series, March 28-29, 2019
Introduction to back-propagation and automatic differentiation (AAD) in machine learning and finance
Much honored to be invited to give the titular workshop lecture at Kings College London on 28 and 29 March. See the event page here: https://www.eventbrite.co.uk/e/the-practitioners-lecture-series-introduction-to-back-propagation-and-automatic-adjoint-tickets-58436780985
See a brief, non-technical abstract on QuantMinds page here. The 6-hour workshop is a technical one. We will discuss the mathematics of deep learning and back-propagation, and the application of AAD with implementations in Python/TensorFlow and C++. The presentation slides are found on my GitHub repo (Intro2AADinMachineLearningAndFinance.pdf), together with supplementary material: code, spreadsheets and notebooks in the folder ‘Workshop’: https://github.com/asavine/CompFinance
The event was arranged by Blanka Horvath, author of Deep Learning Volatility, where the matter of quick European option pricing in rough volatility models is resolved with deep learning methods. Thank you, Blanka.
Registration is absolutely free, but seating is limited to 40 people. I am looking forward to meet an audience interested in the most recent additions to computational finance.