Antoine Savine is a researcher in quantitative finance and a long time practitioner of financial derivatives. Antoine works with Danske Bank after globally leading the quantitative effort of a major French bank for more than ten years. He is an experienced C++ programmer and one of the key contributors to Danske Bank's xVA system, which won the In-House System of the Year 2015 Risk award. Antoine Savine also lectures on topics including volatility and numerical finance in the Masters of Science in Mathematics and Economics at the Copenhagen University. Antoine is a regular speaker and chairman for Quant Minds and World Business Strategies conferences. Antoine Savine is the author of the Modern Computational Finance series of books with Wiley. The first volume, AAD and Parallel Simulations, dedicated to Automatic Adjoint Differentiation, Monte-Carlo simulations and parallel computing, launches in November 2018. It is also the curriculum for numerical and computational finance in the University of Copenhagen. The second book, Scripting for Financial Derivatives, covers in deep detail the ideas and the practical implementation of scripting financial cash-flows, including applications to the risk management of derivatives transactions and portfolios, or regulatory calculations like CVA (counterparty value adjustment), xVA (various other value adjustments), FRTB (fundamental review of the trading book) or CCR (counterparty credit risk).The third book, expected late 2019, is dedicated to xVA. Antoine holds a Masters in Mathematics from the University of Paris-Jussieu, and a PhD, also in Mathematics, from the University of Copenhagen. He is best known for his work on volatility alongside Bruno Dupire, scripting alongside Jesper Andreasen and Leif Andersen, multi-factor interest rate models alongside Marek Musiela, as well as automatic differentiation and parallel Monte-Carlo simulations. He has been influential in the universal adoption of scripting in financial systems, the systematic application of generalized derivatives and Tanaka's formulas in the context of local and stochastic volatility models, and the adoption of automatic adjoint differentiation (AAD) in finance. Antoine Savine
I will be delivering the keynote at Bloomberg’s Quant Seminar in NYC next week, June 22th 2022, 17:00.
The event can be followed in person or virtually. Registration is free but mandatory. Here is the registration link: https://go.bloomberg.com/attend/invite/bloombergquant-bbq-seminar-june2022/
In this event hosted by Bruno Dupire at Bloomberg’s headquarters, I will present advances in…
Co-author Brian Huge and I were interviewed by Risk Magazine last week and got a chance to present differential ML and related algorithms in non-technical terms. The podcast is publicly available https://www.risk.net/cutting-edge/views/7880346/podcast-huge-and-savine-on-turbo-charging-derivatives-pricing
Podcast: Huge and Savine on turbo-charging derivatives pricing
Differential regression illustrates the main ideas of differential machine learning, and demonstrates its power in a very simple context. We posted a small article with code on Google Colab, run it here:
https://colab.research.google.com/github/differential-machine-learning/notebooks/blob/master/DifferentialRegression.ipynb
Differential Dimension Reduction from Antoine Savine on Vimeo.
Brian Huge and Antoine Savine of Fuperfly Analytics at Danske Bank extend differential machine learning (ML) to unsupervised models and design a new breed of principal component analysis (PCA) to correctly reduce dimension for risk management of financial Derivatives. Applications include the specification and calibration of pricing models, the automatic identification of regression features, and the preprocessing of simulated datasets for (differential) machine learning.
Complimentary Preview: Modern Computational Finance Volume 2
Modern Computational Finance Volume 2: Scripting for Derivatives and xVA by Jesper Andreasen and Antoine Savine -- free preview now available
read the draft now
See download link at the bottom of this page and leave your suggestions and comments on the linkedIn group Machine Learning in Quantitative Finance (you may need to request membership).
We count on the suggestions and comments left by advanced readers in the linkedIn thread to quickly complete this work with the quality expected from the Modern Computational Finance series.
Differential Machine Learning (Risk, 2020) — Live Production Demo We have just presented our latest Risk paper Differential Machine Learning at QuantMinds International 2020. The presentation includes a live demo of how differential ML is implemented in production, and combined with cash-flow scripting to provide truly general means of learning the pricing and risk function of arbitrary financial instruments. See the 5min demonstration below:
Differential Machine Learning: 5min video overview Differential ML tutorial on YouTube In this lightning talk delivered for Bloomberg's BBQ seminar 28th May 2020, we expose the main ideas of differential machine learning and application to derivatives pricing and risk management. Complete presentation slides here:
annaxmalina
prguitarman
germansingergirl
janainaart
pixelskylines
theartofmadeline
2087
turnnoffyourmind