Quant Insights
AI, Machine Learning and Risk
London & Online, 15th November 2019
5th Annual Conference
Brought to you by
CQF Institute and Wilmott
London & Online, 12th - 14th November

2 Organizers

10 Talks

120 Live Tickets

200+ Online Tickets

About the Conference

Canary Wharf, London, E14 5GN

With the growth and development of artificial intelligence, the use of data and machine learning in finance has become a hot topic in the last few years. The Quant Insights conference will bring together leading industry practitioners to talk about the latest techniques they are using, incorporating AI and machine learning in trading, portfolio management and risk management.

Book Now

Conference Speakers & Panellists

Confirmed speakers and panellists.

Alexander Denev
AI Risks in Finance – Is it Too Early to Be Concerned?
AI Risks in Finance – Is it Too Early to Be Concerned?

With the advent of new AI technologies an increasing number of AI models is being deployed across financial institutions: from customer chatbots to credit approval and trading systems. The increased adoption of AI comes with risks that must be controlled to avoid reputational and financial damage for institutions. This talk will give an overview of AI risks and how they can be mitigated.

Alexander Denev, Head of AI - Financial Services, Deloitte
Alexander Denev, Head of AI - Financial Services, Deloitte

Alexander has more than 15 years of experience in finance, financial modelling and machine learning. Prior to joining Deloitte, he led the Quantitative Research at IHS Markit where he created and maintained a center of excellence. He has written several papers and two books on topics ranging from stress testing and scenario analysis to asset allocation. He has provided thought leadership engagements for conferences, journals and global forums. He founded Global Graph Analytics - a company focused on dynamic scenario analysis. He also worked as a senior advisor to Risk Dynamics, an arm of McKinsey & Company. Previously he was Director of Risk Models at the Royal Bank of Scotland, where his responsibilities included development of the stress testing methodologies and credit models, and a Fixed Income Structurer for a front office desk. He has also held roles at the European Investment Bank and the European Investment Fund and has participated in the engineering of both the European Financial Stability Facility and the European Stability Mechanism. Alexander Denev attained his Master of Science degree in Physics with a focus on Artificial Intelligence from the University of Rome, Italy, and he holds a degree in Mathematical Finance from the University of Oxford, UK, where he continues as a visiting lecturer.

Marc Henrard
A Quant Perspective on LIBOR Fallback
A Quant Perspective on LIBOR Fallback

Dr. Marc Henrard, Managing Partner, muRisQ Advisory and Visiting Professor, University College London
Dr. Marc Henrard, Managing Partner, muRisQ Advisory and Visiting Professor, University College London

Over the last 20 years, Marc has worked in various areas of quantitative finance including risk management, trading, software development, and quantitative research. He is also Head of Quantitative Research at OpenGamma and prior to that was Head of Interest Rate Modelling for Dexia Group, Deputy Head of Treasury Risk at the Bank for International Settlements (BIS) and Head of Quantitative Research and Deputy Head of Interest Rate Trading also at BIS.
Marc's research focuses on interest rate modelling and risk management. More recently he focused his attention to market infrastructure (initial margin, product design, quantitative impacts of regulation, LIBOR fallback). He authored two books: The multi-curve framework: foundation, evolution, implementation and Algorithmic Differentiation in Finance Explained. Marc holds a PhD in mathematics from the University of Louvain, Belgium.

Andrew Green
Bayesian and Machine Learning Approaches to XVA Integration
Bayesian and Machine Learning Approaches to XVA Integration

XVAs are expected values that are classically solved by high dimensional numeric integration. For example, in a classic CVA calculation where credit and market risk are assumed independent, the model factors the numerical integral into two parts, the expected exposure profile calculated using Monte Carlo simulation, and a simple one dimensional numeric integrations over the probability of default. The overall numerical error in the computation is often not well understood or controlled, while day on day behaviour of the numeric integral can lead to significant artificial carry. This paper takes a fresh look at the XVA calculation through the lens of Bayesian Analysis and Machine Learning.

Dr. Andrew Green, MD and XVA Lead Quant, Scotiabank
Dr. Andrew Green, MD and XVA Lead Quant, Scotiabank

Andrew Green is a Managing Director and lead XVA Quant at Scotiabank in London. He is the author of XVA: Credit, Funding and Capital Valuation Adjustments which is published by Wiley, co-editor of Landmarks in XVA which is published by Risk Books and co-author of a number of technical articles on XVA in recent years.

Patrik Karlsson
Deep Execution – Reinforcement Learning and Generative Models in Algo Trading
Deep Execution – Reinforcement Learning and Generative Models in Algo Trading

The first part will cover reinforcement learning for algorithmic trading and the two main approaches, value- and policy-based, for training an AI agent that can be used for trading and beating market benchmarks. The second part will cover the promising area of generative models and its application to algorithmic trading.

Dr. Patrik Karlsson, Quant Trader, SEB
Dr. Patrik Karlsson, Quant Trader, SEB

Patrik is responsible for the FX algorithmic execution at SEB and a PhD supervisor on the Wallenberg AI program, researching on deep learning in algo trading. He has previously been a quant at ING, specializing in GPU accelerating computing, market maker at Handelsbanken, PhD Associate at Goldman Sachs, research fellow at Caltech, ETH Zurich, UTS Sydney and CWI Netherlands. Patrik holds a PhD from Lund University, proud publisher in the Wilmott magazine, represented the Swedish national team in swimming and is a former Swedish champion.

Andrea Karlova
"Prototype then Edit" the Time Series Forecast
"Prototype then Edit" the Time Series Forecast

Deep learning generative models has been find useful in the time series prediction as they can learn different components of the time series, e.g. trend or recurrent observations.
When monitoring the prediction error, we may need to decide to retrain the time-series due to large generalisation error of the trained model.
Retraining of the models may often not be feasible and may be computationally demanding, which increases the economical cost of the model.
We introduce new architecture which utilises variational auto-encoders and learns how we need to modify the prediction as the real-life observations corrects the forecast. So rather then re-learning the time-series behaviour, we learn how to "edit" online the prediction of the time-series.
Practically speaking, we firstly generate sample scenarios of the future development of the time series in order to build the first rough structure of the future timeline and then we fine-tune this structure with the additional editing neural architecture which is trained on potential errors of the forecasting algorithms.

Andrea Karlova, Head of Data Science, Fractal Labs
Andrea Karlova, Head of Data Science, Fractal Labs

Andrea is Head of Data Science at Fractal Labs Ltd. The main focus of her R&D team is in NLP related tasks, time series modeling and categorisation problems.
Prior to switching to Fintech startup industry, she was funded by Gorrila Science and under supervision of Patrick S. Hagan and co-authored new volatility surface model based on tempered Levy flights dynamics.
During that time she held visiting research positions at Columbia University, Oxford Man Institute and University College London.
Early in her career Andrea spent five years working at Validation Unit at KBC Global Services and as a consultant for PwC.
Her main background is in mathematics, mainly in probability theory. She developed extensive knowledge of deep learning and reinforcement learning algorithms during her close collaboration with the Computer Science Department at University College London.

Yves Hilpisch
Artificial Intelligence in Finance
Artificial Intelligence in Finance

The programmatic availability of basically any kind of (financial) data has reshaped finance from a theory-driven to a data-driven discipline. Recent advances in AI in combination with the programmatic availability of (financial) data with further change finance to an AI-first discipline. The talk discusses several important aspects in this regard and provides concrete examples in Python.

Dr. Yves J. Hilpisch, Founder and CEO, The Python Quants
Dr. Yves J. Hilpisch, Founder and CEO, The Python Quants

Dr. Yves J. Hilpisch is founder and CEO of The Python Quants (http://tpq.io) a group focusing on the use of open source technologies for financial data science, artificial intelligence, algorithmic trading, and computational finance. He is also founder and CEO of The AI Machine (http://aimachine.io), a company focused on AI-powered algorithmic trading based on a proprietary strategy execution platform.

Yves Hilpisch
Evaluating Risk Through Vicarious Views and Expectations
Evaluating Risk Through Vicarious Views and Expectations
Grant Fuller, CEO, Irithmics & Michael Aichinger, CEO, uni software plus GmbH

Traditionally, equity risk has focused heavily on price and its derivatives, return, volatility and covariance. Deep learning provides new techniques to evaluate and contextualise risk across capital markets, including corporate issuers, fund investors and activist managers. We describe how derived views and expectations of institutional investors enhance evaluation of risk, its mitigation and management. Finally, we discuss how these enhanced understandings may be used to construct suitable hedge instruments.

Grant Fuller, CEO, Irithmics
Grant Fuller, CEO, Irithmics

Grant co-founded Irithmics in 2012. The firm's deep learning technology provides data and services to institutional investors, asset managers, exchanges, corporates, brokers and research analysts. Previously part of Ernst & Young's fund advisory practice, Grant also helped develop Bloomberg's successful hedge fund trading and analytics technology, leading the firm's European and Asian AIM business. Prior to Bloomberg, Grant was part of RiskMetrics, establishing their European fund and asset management analytics and consulting capabilities. He holds a BSc in Chemistry from the University of St Andrews. He remained at St Andrews to undertake a PhD applying neural networks in chemistry, after which he joined academic research at Cambridge University, applying neural networks to public health epidemiology.

Yves Hilpisch
Evaluating Risk Through Vicarious Views and Expectations
Evaluating Risk Through Vicarious Views and Expectations
Grant Fuller, CEO, Irithmics & Michael Aichinger, CEO, uni software plus GmbH

Traditionally, equity risk has focused heavily on price and its derivatives, return, volatility and covariance. Deep learning provides new techniques to evaluate and contextualise risk across capital markets, including corporate issuers, fund investors and activist managers. We describe how derived views and expectations of institutional investors enhance evaluation of risk, its mitigation and management. Finally, we discuss how these enhanced understandings may be used to construct suitable hedge instruments.

Michael Aichinger, CEO, uni software plus GmbH
Michael Aichinger, CEO, uni software plus GmbH

Michael Aichinger has a PhD in theoretical physics, and after several years as a senior postdoc at the Radon Institute for Computational and Applied Mathematics of the Austrian Academy of Sciences, he became the CEO of uni software plus in 2014. He has been working in the field of quantitative finance for more than 10 years.

Conrad Wolfram
Breaking the Primal Barrier
Breaking the Primal Barrier

Here, we present a new approach for Automatic Adjoint Differentiation with a special focus on computations where derivatives are required for multiple instances of vectors $X$. In practice, the presented approach is able to calculate all the differentials faster than the primal (original) C++ program for $F$.

Dmitri Goloubentsev, Head of Automatic Adjoint Differentiation, Matlogica
Dmitri Goloubentsev, Head of Automatic Adjoint Differentiation, Matlogica

Dmitri has 15 years of combined experience in model development working on C++ quant libraries. He worked as a Senior Quant Analyst in Interest rate derivatives and played a leading role in delivering XVA solution at a major Canadian bank. Prior to focusing on AAD, he was responsible for construction of SIMM/MVA model. Dmitri earned his degree in Maths and Applied Maths from the Moscow State University.

Conrad Wolfram
 

 

Conrad Wolfram, Strategic Director and European CEO/Co-Founder, Wolfram Research
Conrad Wolfram, Strategic Director and European CEO/Co-Founder, Wolfram Research

Conrad Wolfram, physicist, mathematician and technologist, is Strategic Director and European Co-Founder/CEO of Wolfram - the “computation company” behind Mathematica, Wolfram Language and Wolfram|Alpha (which powers knowledge answers for Apple's Siri) for over 30 years. Wolfram pioneers new approaches to data science and computation-based development, with technology and consulting solutions that drive innovation in analytics, software development and modeling. Working with start-ups to Fortune 500 companies, it spans industries as diverse as medicine, finance and telecoms. Conrad is recognized as a thought leader in AI, data science and computation, pioneering a Multi-Paradigm data science approach.
Conrad is also a leading advocate for a fundamental shift of maths education to become computer-based or alternatively introduce a new core subject of computational thinking. He founded computerbasedmath.org and computationalthinking.org to fundamentally fix maths education for the AI age - rebuilding the curriculum assuming computers exist. The movement is now a worldwide force in re-engineering the STEM curriculum. Conrad regularly appears in the media to talk about subjects ranging from decisions and data science to 21st century education. He holds degrees in Natural Sciences and Maths from the University of Cambridge, UK.

Paul Wilmott

Dr. Paul Wilmott, President, CQF Institute (Panellist)
Dr. Paul Wilmott, President, CQF Institute

Paul is the founder of the Certificate in Quantitative Finance and Wilmott.com and he is internationally renowned as a leading expert on quantitative finance. His research work is extensive, with more than 100 articles in leading mathematical and finance journals, as well as several internationally acclaimed books on mathematical modeling and derivatives, including the best-selling Paul Wilmott On Quantitative Finance, published by John Wiley & Sons.

Conference Tickets

All tickets include 60 days of access to Video on Demand.

15th November

£295 Early Bird
£345 Standard

Live & Online

Book Now
Early Bird tickets are available until 20th October

Prices above exclude VAT of 20%

Discounts

Become a CQF Institute member

CQF Institute Premium Member: 50%
CQF Institute Basic members: 20%

Students: 50%
Bulk (3+ Tickets): 25%

To claim your discount code, email us at events@cqfinstitute.org

For Python Quants Bootcamp Series

Brought to you by the CQF Institute and The Python Quants

All tickets include 60 days of access to Video on Demand.

Yves Hilpisch
Dr. Yves J. Hilpisch, Founder and CEO, The Python Quants
12th - 14th November 2019, Live and Online
Fitch Learning, 55 Mark Lane, London, EC3R 7NE
Early Bird tickets are available until 20th October

Become a CQF Institute member

CQF Institute Premium Member: 25% Discount
CQF Institute Basic members: 10% Discount

Students: 25% Discount
Package (2+ Bootcamps): 15% Discount

To claim your discount code or package bookings, email us at events@cqfinstitute.org

Prices above exclude VAT of 20%

Conference Organizers

Quant Insights is presented by the CQF Institute & Wilmott
CQF Instiute

Part of Fitch Learning, the CQF Institute is a global membership platform for educating and building the quant finance community.

Fitch Learning

Part of the Fitch Group, Fitch Learning partners with clients to enhance knowledge, skills and conduct. Fitch Learning advises and builds learning solutions to accelerate the achievements of individuals and companies.

Wilmott

Wilmott is the leading resource for the quant finance community, comprised a website and discussion forum and Wilmott magazine.

Conference Sponsors

Gold Sponsors
QuantHouse
UnRisk
 
Wiley
Wiley
Affiliate Sponsor
NAG

Venue

Conference

Fitch Ratings Auditorium,
30 North Colonnade,
Canary Wharf,
London,
E14 5GN