Monday 22nd March 2021
Founder, CEO, Thalesians & Senior Quantitative Consultant, BNP Paribas
Paul Bilokon: Founder, CEO, Thalesians & Senior Quantitative Consultant, BNP Paribas
Dr. Paul Bilokon is CEO and Founder of Thalesians Ltd and an expert in electronic and algorithmic trading across multiple asset classes, having helped build such businesses at Deutsche Bank and Citigroup. Before focussing on electronic trading, Paul worked on derivatives and has served in quantitative roles at Nomura, Lehman Brothers, and Morgan Stanley. Paul has been educated at Christ Church College, Oxford, and Imperial College. Apart from mathematical and computational finance, his academic interests include machine learning and mathematical logic.
- Artificial intelligence (AI), in particular deep learning, has become a subject of intense media hype
- Strengths and limitations of machine learning, deep learning and AI more generally
- Applying deep learning techniques to the investment process
- A stock selection model that uses neural networks and compare its performance to “classical” machine learning models, such as decision trees and regularised regression
- Results and contribution to the long-term investment strategies
David Jessop: Head of Investment Risk at Columbia Threadneedle Investments EMEA APAC
David is the Head of Investment Risk at Columbia Threadneedle Investments EMEA APAC. Previously the Global Head of Equities Quantitative Research at UBS. His areas of research include portfolio analysis and construction, style analysis and risk modelling. He also helps clients understand, use and implement the quantitative tools available from UBS. David joined UBS in 2002. Prior to this, he spent seven years at Citigroup as Head of Global Quantitative Marketing. Before moving to the sell side he spent six years at Morgan Grenfell Asset Management, where he managed index funds, asset allocation funds and also an option overwriting fund.
David graduated from Trinity College, Cambridge with an MA in Mathematics.
Market generators are machine learning algorithms for generating realistic samples of market data when historical time series has insufficient length or gaps. While most of the recent research on market generators focused on daily time horizons, the problem of generating realistic market data samples for time horizons from 1 year to 30 years and longer has multiple applications including limit management, insurance (economic scenario generation) and macro investing.
In this presentation, we describe a family of market generators that use machine learning to generate market scenarios with accurate probability distribution over long time horizons from limited time series.
Executive Chairman and Head of Quant Research, CompatibL
Alexander Sokol: Executive Chairman and Head of Quant Research, CompatibL
Alexander Sokol is the founder, Executive Chairman, and Head of Quant Research at CompatibL, a trading and risk technology company. He is also the co-founder of Numerix, where he served as CTO from 1996 to 2003, and the co-founder of Duality Group, where he served as CTO from 2017 to 2020.
Alexander won the Quant of the Year Award in 2018 together with Leif Andersen and Michael Pykhtin, for their joint work revealing the true scale of the settlement gap risk that remains even in the presence of initial margin. Alexander’s other notable research contributions include systemic wrong-way risk (with Michael Pykhtin, Risk Magazine), joint measure models, and the local price of risk (with John Hull and Alan White, Risk Magazine), and mean reversion skew (Risk Books, 2014).
Alexander earned his BA from the Moscow Institute of Physics and Technology at the age of 18, and a PhD from the L. D. Landau Institute for Theoretical Physics at the age of 22. He was the winner of the USSR Academy of Sciences Medal for Best Student Research of the Year in 1988.
Inspired by a series of remarkable papers in recent years*, that use Deep Neural Networks (DNN) to substantially speed up the calibration of rough volatility models, we investigate the use of Chebyshev Tensors instead of DNNs. Given that Chebyshev Tensors (CT) can be, under certain circumstances, more efficient than DNNs at exploring the input space of the function that needs to be approximated – due to their exponential convergence – the problem of calibration of rough volatility models seems, a priori, a good candidate to explore the use of CTs.
In this piece of research, we built CTs, either directly or with the help of Tensor Extension Algorithms, to tackle the computational bottleneck associated with the calibration of rough volatility models. Results are encouraging as the accuracy of model calibration via CTs is similar to that when using DNNs, but with building times that were 100 more efficient in some of the experiments. Our tests indicate that when using CTs, the calibration of rough volatility models is around 40,000 times more efficient than if calibrated via “brute-force” (using the pricing function).
In this talk we will introduce the problem being tackled, discuss the fundamentals of the approach via CTs and show the numerical results obtained.
- The problem of pricing model calibration
- Brief overview of existing literature
- A candidate to help in the problem: Chebyshev Tensor; key properties and potential limitations
- How to use Chebyshev Tensors for pricing model calibration
- Direct approach
- In combination to Tensor Extension Algorithms
- Numerical results
- Constant term structure models
- Varying terms structure models
- C. Bayer, B. Stemper. (2018). Deep calibration of rough stochastic volatility models.
- B. Horvath, A. Muguruza, M. Thomas (2019) Deep Learning Volatility
Founder & CEO, MoCaX Intelligence
Ignacio Ruiz: Founder & CEO, MoCaX Intelligence
Ignacio Ruiz has been the head strategist for Counterparty Credit Risk, exposure measurement, for Credit Suisse, as well as the Head of Risk Methodology, equities, for BNP Paribas. In 2010, Ignacio set up iRuiz Consulting as an independent advisory business in this field. In 2014, Ignacio founded iRuiz Technologies to develop and commercialise MoCaX Intelligence.
He holds a PhD in nano-physics from Cambridge University.
Head of Research and Development: MoCaX Intelligence
Mariano Zeron: Head of Research and Development: MoCaX Intelligence
Mariano leads our Research & Development work. He has vast experience in Chebyshev Spectral Decomposition, machine-learning and related disciplines, and their application to quantitative problems in the financial markets. Mariano holds a Ph.D. in Mathematics from Cambridge University.
Founder & CEO, Riskfuel
Ryan Ferguson: Founder & CEO, Riskfuel
Ryan is Founder and CEO at Riskfuel, a capital markets focused startup that is developing ultra-fast AI-based valuation technologies.Previously, Ryan was Managing Director and Head of Securitization, Credit Derivatives and XVA at Scotiabank. Prior roles have included credit correlation trading and managing the equity derivatives trading desk. Ryan began his career with positions in risk management and financial engineering. Ryan has a PhD in Physics from Imperial College, and a BASc and MASc in Electrical Engineering from the University of Waterloo.
Monday 22nd March 2021
We introduce a first theory of price impact in presence of an interest-rates term structure. We explain how one can formulate instantaneous and transient price impact on bonds with different maturities, including a cross price impact that is endogenous to the term structure. We connect the introduced impact to classic no-arbitrage theory for interest rate markets, showing that impact can be embedded in the pricing measure and that no-arbitrage can be preserved. We present pricing examples in presence of price impact and numerical examples of how impact changes the shape of the term structure. Finally, to show that our approach is applicable we solve an optimal execution problem in interest rate markets with the type of price impact we developed in the paper.
Chair in Mathematical Finance and Stochastic Analysis, Imperial College London, Dept. of Mathematics
Damiano Brigo: Chair in Mathematical Finance and Stochastic Analysis, Imperial College London, Dept. of Mathematics
Professor Damiano Brigo is Chair of Mathematical Finance & co-Head of group at Imperial College, London, consistently ranked among the top 10 Universities in the world. Damiano is also part of the Stochastic Analysis Group at Imperial and serves in several advisory and consulting roles in the financial industry.
Damiano’s previous roles include Gilbart Professor and Head of Group at King’s College London, Managing Director & Global Head of Quantitative Innovation in Fitch Ratings, Head of Credit Models in Banca IMI, Fixed Income Professor at Bocconi University in Milan, Quantitative Analyst at Banca Intesa and Head of the Capco Institute.
Damiano published 100+ works in top journals for Mathematical Finance, Systems Theory, Probability and Statistics, and books for Springer and Wiley that became field references in stochastic interest rate and credit modeling, with H-index 38 and 7000+ citations on Scholar. Damiano is Editor of the International Journal of Theoretical & Applied Finance and of Mathematics of Control, Signals & Systems, and has been listed as the most cited author in Risk Magazine in 1998-2017.
Damiano’s past work and current interests include valuation across asset classes, credit derivatives, interest rate, equity and FX derivatives, univariate and multivariate volatility smile modeling, hedging, risk measurement, funding costs, counterparty credit risk, valuation adjustments, stochastic models for commodities and inflation, dependence dynamics, liquidity risk, optimal execution, information geometry and stochastic analysis, nonlinear stochastic filtering, stochastic processes consistent with mixtures of distributions, and stochastic differential geometry.
Damiano obtained a Ph.D. in stochastic filtering with differential geometry in 1996 from the Free University of Amsterdam, following a BSc in Mathematics with honours from the University of Padua.
MD, Head of Quantitative Analytics and Quantitative Development, NatWest Markets
Vladimir Piterbarg: MD, Head of Quantitative Analytics and Quantitative Development at NatWest Markets
Senior Director, Head of Methodology and Analytics, Capital Markets Risk Management, CIBC
Hany Farag: Senior Director, Head of Methodology and Analytics, Capital Markets Risk Management, CIBC
Hany Farag is Senior Director and Head of Risk Methodology and Analytics at CIBC. Prior to his current position he was a partner at Eastmoor Capital Partners, LLP; Managing Director and Head of FX Statistical Arbitrage at CIBC; and Head of Quantitative Research at OANDA Corporation. Prior to his industry positions he was a Postdoctoral Fellow at Caltech and at Rice University. He holds a PhD in Mathematical Analysis from Yale, a MS in Theoretical Physics from Yale, and a BSC in Electronics and Communication Engineering from Ain Shams.