Quant Insights
AI, Machine Learning and Risk
London & Online, 16th November 2018
4th Annual Conference
Brought to you by
CQF Institute and Wilmott
For Python Quants Bootcamp Series
London & Online, 13th - 15th 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 a ticket

Conference Schedule

View the running order of the day

8.00 - 8.50
Registration and Morning Coffee
8.50 - 9.00
Welcome & Opening Remarks
Dr. Randeep Gug, Director, CQF Institute
9.00 - 9.40
Machine Learning for Multi-Factor Equity Portfolio
Tony Guida, Senior Investment Manager - Quantitative PM
9.40 - 10.20
From Machines to Robots: The Case of High-Dimensional Stress Tests in Risk and Algorithmic Trading
Dr. Karolos Korkas, Risk Quant, Citigroup Inc
10.20 - 11.00
Big Data and Machine Readable News to Trade Markets
Saeed Amen, Founder, Cuemacro
11.00 - 11.20
Morning Break
11.20 - 12.00
Optimizing Dynamic Trading Strategies on Gaussian Returns
Dr. Nick Firoozye, Director, IF Resources UK, and Honorary Sr Lecturer, UCL
12.00 - 12.40
The AI Machine – Solving the Last Mile Problem in Algorithmic Trading
Dr. Yves Hilpisch, Founder & Managing Partner, The Python Quants
12.40 - 13.30
Lunch and Networking
13.30 - 14.10
Keynote: Machine Learning And Me - A Love/Hate Relationship
Dr. Paul Wilmott, President, CQF Institute
14.10 - 14.50
Making Data Pay: AI and ML in Trade Finance
Dr. Philipp Schoenbucher, Co-Founder and Chief Data Scientist, Previse
14.50 - 15.30
Deep Learning in Finance: Prediction of Stock Return with Long Short-Term Memory Networks
Dr. Miquel Noguer Alonso, Co-Founder, Artificial Intelligence Finance Institute
15.30 - 15.45
Afternoon Break
15.45 - 16.25
Neocybernetics
Dr. Paul A Bilokon, Founder and CEO, Thalesians Ltd
16.25 - 17.10
Panel Discussion
Expert Panel
17.10 - 17.15
Closing Remarks
Dr. Randeep Gug, Director, CQF Institute
17.15
Conference Get Together

Conference Speakers & Talks

Paul Wilmott
Keynote: Machine Learning And Me - A Love/Hate Relationship
Keynote: Machine Learning And Me - A Love/Hate Relationship

Dr. Paul Wilmott, President, CQF Institute
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.

Miquel Noguer Alonso
Deep Learning in Finance: Prediction of Stock Return with Long Short-Term Memory Networks
Deep Learning in Finance: Prediction of Stock Return with Long Short-Term Memory Networks

In this new research we investigate the portability of a quantitative trading strategy based on Deep Learning methods. Specially we focus on a variant of the Recurrent Neural Network (RNN), the Long Short-Term Memory Network (LSTM) and show its predictive power on stock price data. We use LSTM networks for selecting stocks using historical price. The reason why RNNs are good for regression or classication of time series or data where time ordering matters is that RNNs capture the variation through time, thanks to its internal state dynamics. We will analyse a univariate and multivariate applications of LSTMs. The results show that LSTMs are a good addition to quantitative analysts’ model toolbox.

Dr. Miquel Noguer Alonso, Co-Founder, Artificial Intelligence Finance Institute
Dr. Miquel Noguer Alonso, Co-Founder, Artificial Intelligence Finance Institute

Miquel Noguer is a financial markets practitioner with more than 20 years of experience in asset management, he is currently Head of Development at Global AI ( Big Data Artificial Intelligence in Finance company ) and Head on Innovation and Technology at IEF. He worked for UBS AG (Switzerland) as Executive Director.for the last 10 years. He worked as a Chief Investment Office and CIO for Andbank from 2000 to 2006. He is professor of Big Data in Finace at ESADE and Adjunct Professor at Columbia University teaching Asset Allocation, Big Data in Finance and Fintech. He received an MBA and a Degree in business administration and economics in ESADE in 1993. In 2010 he earned a PhD in quantitative finance with a Summa Cum Laude distinction (UNED – Madrid Spain).

Tony Guida
Machine Learning for Multi-Factor Equity Portfolios
Machine Learning in Systematic Equity Allocation: A Model Comparison

In this talk, we compare popular machine learning (ML) approaches (random forest, boosted trees and neural networks) to build diversified equity portfolio, using different weighting scheme and cash neutral long-short portfolios. We demonstrate that using ML models on a large number of features gives an average error rate of 39% for predicting the 12-month sector neutral outperformance of a stock. We find that, irrespective of the weighting scheme, boosted trees and neural networks outperform a long-only factor investing type of global equity portfolio. Boosted trees shows the best risk/return profile from the set of ML algorithms used. It generates on average an excess return of 2.1% per annum, compared to a simple multifactor portfolio on a long-short basis and 1.1% above multi-factor for the only strategies across all weighting scheme.

Tony Guida, Senior Investment Manager - Quantitative PM
Tony Guida, Senior Investment Manager - Quantitative PM

Tony is Senior Investment Manager - Quantitative PM, managing multi-factor equity portfolios for the asset manager of a UK pension fund in London. Prior to that Tony was Senior Research Consultant for Smart Beta and Risk allocation at EDHEC RISK Scientific Beta, advising asset owners how to construct and allocate to risk premia. Before joining EDHEC Tony worked eight years at UNIGESTION as a Senior Research Analyst. He was a member of the Research and Investment Committee for Minimum Variance Strategies and he was leading Factor Investing research group for institutional clients. He is the editor and co-author of the forthcoming book: Practical Applications of Machine learning and Big Data for Quantitative Investment (Winter 2018). He holds Bachelor and Master degrees in Econometry and Finance from the University of Savoy, France.

Yves Hilpisch
The AI Machine – Solving the Last Mile Problem in Algorithmic Trading

Dr. Yves Hilpisch, Founder & Managing Partner, The Python Quants
The AI Machine - Solving the Last Mile Problem in Algorithmic Trading

This talk considers the consequences of recent advances in the field of Artificial Intelligence (AI) for finance in general and algorithmic trading in particular. The core of the talk is about building The AI Machine, an AI-powered, scalable algorithmic trading platform mainly using Python. It allows (retail) algorithmic traders to deploy their trading algorithms in robust and reliable fashion, taking care of data processing, signal generation, order execution, risk management and trading strategy life cycle management. The AI Machine solves the last mile problem for both algorithmic traders on the one hand and brokers on the other hand when it comes to deploying trading algorithms in a standardized way.

Dr. Yves Hilpisch, Founder & Managing Partner, The Python Quants

Yves is founder and Managing Partner of The Python Quants, a group focusing on the use of open source technologies for financial data science, artificial intelligence, algorithmic trading and computational finance. He is author of the books Python for Finance (O'Reilly, 2nd edition, 2018), Listed Volatility and Variance Derivatives (Wiley, 2017), Derivatives Analytics with Python (Wiley, 2015) and Python for Finance (O'Reilly, 2014). Yves lectures on computational finance at the CQF Program and on algorithmic trading at the EPAT Program. He is also the director of the first online training program leading to a University Certificate in Python for Algorithmic Trading. Yves has written the financial analytics library DX Analytics and organizes meetups, conferences and bootcamps about python for quantitative finance.

Karolos Korkas
From Machines to Robots: The Case of High-Dimensional Stress Tests in Risk and Algorithmic Trading
From Machines to Robots: The Case of High-Dimensional Stress Tests in Risk and Algorithmic Trading

Banks and financial institutions continuously face scrutiny by regulators over the development of efficient models to forecast capital sufficiency under adverse macroeconomic scenarios or determine an algorithm performance under extremely volatile markets in a high frequency trading environment. The curse of dimensionality is naturally embedded in these models and dealing with it requires taking a step further away from the traditional statistical methodologies. In this talk, I will show how to detect a period of high stress from a large dataset using machine learning techniques and discuss the prospects of AI in this context.

Dr. Karolos Korkas, Risk Quant, Citigroup Inc
Dr. Karolos Korkas, Risk Quant, Citigroup Inc

Karolos is a vice president in the Model Risk Management division of Citigroup overseeing model validations for various asset classes. Previously, he worked on the FX electronic trading desk of MUFG Bank as a quantitative researcher. There, he developed algorithms using statistical and machine learning techniques to extract meaningful patterns inside the big data produced in a high frequency trading environment. Karolos holds a PhD in Statistics from the London School of Economics and was a Fellow in Finance at the same school; he is also a published author and his research interests lie in the detection of change-points in big datasets and high dimensional risk management.

Nick Firoozye
Optimizing Dynamic Trading Strategies on Gaussian Returns
Optimizing Dynamic Trading Strategies on Gaussian Returns

Dynamic trading strategies, in the spirit of trend-following or mean-reversion, represent an only partly understood but lucrative and pervasive area of modern finance. Assuming Gaussian returns, we are able to derive closed-form expressions for the first four moments of the strategy’s returns, in terms of correlations between the random signals and unknown future returns. We demonstrate that positive skewness and excess kurtosis are essential components of all positive Sharpe dynamic strategies, which is well-known empirically; that orthogonal or total least squares (TLS) is more appropriate than OLS for maximizing the Sharpe ratio; derive standard errors on Sharpe ratios which are tighter than the commonly used standard errors from [Lo(2002)]; and derive standard errors on skewness and kurtosis of strategies, apparently new results. We introduce an over-fitting penalization on Sharpe ratios which is meant to be a better predictor of out-of-sample performance, contrasting this to other over-fitting techniques such as multiple-hypothesis testing, and apply this technique to model selection on the returns of over 1500 assets, showing that TLS together with the covariance penalty largely outperforms other methods with commonly used AIC for model choice and in terms of decreased over-optimism. Finally, we extend the work to optimize the utility of returns using nonlinear transforms of signals, considering as well standard errors of the resulting strategy design.

Dr. Nick Firoozye, Director, IF Resources UK, and Honorary Sr Lecturer, UCL
Dr. Nick Firoozye, Director, IF Resources UK, and Honorary Sr Lecturer, UCL

Nick is a mathematician & statistician with over 20 years of experience in the finance industry, in both buy and sell-side firms, largely in research. He started his career in Lehman doing MBS/ABS modeling, heading teams in portfolio strategy and EM quant, later taking a variety of senior roles at Goldman Sachs, and Deutsche Bank, and at the asset managers, Sanford Bernstein, and Citadel, in areas ranging from quantitative strategy, relative value strategy and trading, to fixed income asset allocation. He was previously MD and Head of Global Derivative Strategy, part of the QIS team at Nomura, and currently heads Quantitative Strategy at a hedge fund, Symmetry. He is also an Honorary Senior Lecturer in C.S. at University College London, focusing on Robust Machine Learning in finance. He recently co-authored a book, entitled Managing Uncertainty, Mitigating Risk, about the role of uncertainty and imprecise probability in financial crises, and he is writing a book on Algorithmic Trading Strategies based on his recent PhD and MSc courses on the same topic offered at UCL.

Saeed Amen
Big Data and Machine Readable News to Trade Markets
Big Data and Machine Readable News to Trade Markets

We give a brief overview of using Big Data and alternative data in financial markets, as well as some use cases for machine learning. We present a case study, examining how machine readable news can be used to trade FX systematically. We also show how news can help understand the market volatility around FOMC and ECB meetings.

Saeed Amen, Founder, Cuemacro
Saeed Amen, Founder, Cuemacro

Saeed Amen is the founder of Cuemacro. Over the past decade, Saeed Amen has developed systematic trading strategies at major investment banks including Lehman Brothers and Nomura. He is also the author of Trading Thalesians: What the ancient world can teach us about trading today. Through Cuemacro, he now consults and publishes research for clients in the area of systematic trading. He has developed many popular open source Python libraries including finmarketpy. His clients have included major quant funds and data companies such as Bloomberg. He has presented his work at many conferences and institutions which include the IMF, Bank of England and Federal Reserve Board. He is also a co-founder of the Thalesians.

Phillip Schoenbucher
Making Data Pay: AI and ML in Trade Finance
Making Data Pay: AI and ML in Trade Finance

Previse pioneered the application of AI to revolutionise trade finance. Replacing manual process-based invoice approvals with automated ML-based scoring decisions has opened up supplier finance to thousands of SMEs, enabling them to have their invoices paid instantly. In this talk, we define the business problem to be solved, cast it in quantitative terms, discuss some of the challenges, and present results. We also discuss similarities and differences to classical scoring methods, in particular credit scoring, and point out future directions.

Dr. Philipp Schoenbucher, Co-Founder and Chief Data Scientist, Previse
Dr. Philipp Schoenbucher, Co-Founder and Chief Data Scientist, Previse

Philipp's professional experience includes seven years at the Department of Mathematics of ETH Zurich as Professor for Quantitative Methods of Risk Management, and seven years at Goldman Sachs International, London. He was awarded Risk Magazine’s “Quant of the Year” in 2005 for his work on Credit Derivatives pricing models, and is author of “Credit Derivatives Pricing Models” (Wiley, 2003) which was named "Quant Book of the Year" in 2003. He authored multiple academic publications on multiple topics including Credit Risk, Liquidity Risk, Stochastic Volatility, and Numerical Methods.

Paul Bilokon
Neocybernetics
Neocybernetics

As we have emerged from a succession of AI Winters, it is time to revisit another line of research that has been frozen: cybernetics. Based on the work of one of the founders of stochastic analysis and, by implication, quantitative finance, cybernetics relies heavily on advances in AI. In this talk we shall introduce a new approach to cybernetics, which we call neocybernetics, and explain why quants are best-positions to advance this field.

Dr. Paul A Bilokon, Founder and CEO, Thalesians Ltd
Dr. Paul A Bilokon, Founder and CEO, Thalesians Ltd

CEO and Founder of Thalesians Ltd. Previously served as Director and Head of global credit and core e-trading quants at Deutsche Bank, the teams that he helped set up with Jason Batt and Martin Zinkin. Having also worked at Morgan Stanley, Lehman Brothers, and Nomura, Paul pioneered electronic trading in credit with Rob Smith and William Osborn. Paul has graduated from Christ Church, University of Oxford, with a distinction and Best Overall Performance prize. He has also graduated twice from Imperial College London. Paul’s lectures at Imperial College London in machine learning for MSc students in mathematics and finance and his course consistently achieve top rankings among the students. Paul has made contributions to mathematical logic, domain theory, and stochastic filtering theory, and, with Abbas Edalat, has published a prestigious LICS paper. Paul’s books are being published by Wiley and Springer. Dr. Bilokon is a Member of British Computer Society, Institution of Engineering and Technology, and European Complex Systems Society.

Conference Tickets

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

16th November

£295 Standard

Online

Book Now

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 Hilpisch, Managing Partner of The Python Quants Inc
13th - 15th November 2018, Live and Online
Fitch Learning, 55 Mark Lane, London, EC3R 7NE

Become a CQF Institute member

CQF Institute Premium Member: 30% 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

Silver Sponsor
QuantHouse
Wiley
Affiliate Sponsor
NAG
Quantifi

Venues

Conference

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

Bootcamp Series

Fitch Learning,
The Corn Exchange,
55 Mark Lane,
London,
EC3R 7NE