Workshop 1
26 June 2017
Time: 09:00 – 17:00

Log Optimal Growth & Kelly Strategy

Background

The concepts underlying gambling and risk aversion are very much in the mainstream of betting, daily trading in the markets and growth of capital. The basic theory was introduced by the Bernoulli family of mathematicians as early as the 1700s. In recent times, dedicated researchers – successful and committed traders and gamblers –such as Thorp, Shannon, Kelly and Ziemba, have refined the theory through academic rigour; they have also field-tested the strategies in betting venues and financial markets.
This workshop sets out to explain why Log Optimal Growth & Kelly Strategy has become mainstream and is accepted as the foundation of winning strategies for betting and trading. As the saying goes, “All you need is an edge”: so follow the maths and you will win.

Workshop Presenters include:
Leonard MacLean, Dalhousie University, Canada
Gautam Mitra, OptiRisk Systems; UCL
M.A.H. Dempster, Cambridge Systems Associates; University of Cambridge
Sebastien Lleo, Associate Professor of Finance and Director of doctoral program at NEOMA Business School – Reims Campus, France

Uncertain Outcomes: Foundations of Betting and Trading Strategies
Speaker: Gautam Mitra, OptiRisk Systems; UCL
Abstract:

  • Why Gamble ? Why Trade ?
  • Grow your money over time ? How fast ?
  • Mathematical underpinning; computing ‘The Edge’ !
  • Risk aversion and Log Utility Function
  • Volatility pumping and money management
  • Kelly strategy a simplified approach

Speaker’s CV: Gautam Mitra is the founder and the MD of OptiRisk Systems. He is an internationally renowned research scientist in the field of Operational Research in general and computational optimisation and modelling in particular. He has developed a world class research group in his area of specialisation with researchers from Europe, UK , USA and India. He has published five books and over hundred and fifty research articles. He is an alumni of UCL and currently a Visiting Professor of UCL. In 2004 he was awarded the title of ‘distinguished professor’ by Brunel University in recognition of his contributions in the domain of computational optimisation, risk analytics and modelling. In OptiRisk Systems he directs research and actively pursues the development of the company as a leader in the domain of financial analytics. Professor Mitra is also the founder and chairman of the sister company UNICOM seminars. OptiRisk systems and UNICOM Seminars also have subsidiaries in India. In India and Southeast Asia both the companies are going through a period of organic growth. [Chairperson]

The Kelly Strategy for Investing: Risk and Reward
Speaker: Leonard MacLean, Dalhousie University, Canada
Abstract: A strategy which has been of long standing interest in investing is the Kelly strategy, where the expected logarithm of wealth is maximized. There are many attractive properties when this strategy is used over a long planning horizon. Notably, the asymptotic growth rate of wealth is optimal and the time to reach asymptotically large wealth targets is minimized. However, the risk aversion of the Kelly strategy is essentially zero and the strategy is very risky in the short term. Investors can lose most of their wealth with a string of bad outcomes. In this paper the Kelly strategy and the associated fractional strategies are considered. The advantages and disadvantages are described in general and in particular with application to a variety of market scenarios. The conclusion discusses the use of Kelly type strategies by great investors.

Growing Wealth with Fixed Mix Strategies
Speaker: M A H Dempster, Centre for Financial Research, Statistical Laboratory, University of Cambridge & Cambridge Systems Associates
Abstract: This talk surveys theoretical research on the long-term performance of fixed-mix investment strategies. These self-financing strategies rebalance the portfolio over time so as to keep constant the proportions of wealth invested in various assets. The main result is that wealth can be grown exponentially from volatility. This finding demonstrates the benefits of active portfolio management and the potential of financial engineering. Popular myths on the topic will be debunked and open problems discussed.

Speaker’s CV: Professor M A H Dempster is Professor Emeritus, Centre for Financial Research, Statistical Laboratory,University of Cambridge. He has been consultant to a number of global financial institutions and several governments and is regularly involved in research presentations and executive education in financial engineering and risk management around the world. He has authored 17 books and over 110 published research articles in leading international journals. His work has won several awards and he is an Honorary Fellow of the UK Institute of Actuaries, a Foreign Member of the Academia Nationale Lincei (the Italian Academy and the world’s oldest scientific society) and Managing Director of Cambridge Systems Associates, a financial analytics consultancy and software company.

Optimal Growth Investment and Wealth Benchmarking
Speaker: Leonard MacLean, Dalhousie University, Canada
Abstract: The expected log capital growth criterion is an important approach to making decisions on investment in risky assets. It was dubbed “Fortunes Formula” by Ed Thorp. The optimal growth theory provides the maximum long run asymptotic growth, but the wealth trajectories for the Kelly investor are very volatile and risky. To control for downside risk, benchmarks are imposed on wealth at each decision point and shortfalls are penalized. The financial market setting is a Markov regime switching framework, with geometric Brownian motion prices within each regime. The resulting log prices have a normal mixture distribution, which provides the flexibility needed to obtain accurate price predictions as inputs to investment decisions. The investment model maximizes capital growth with a penalty for shortfalls, subject to a dynamic VaR constraint requiring wealth to exceed a specified benchmark with high probability. The modification of the Kelly strategy based on the switching structure is developed. The sensitivity of investment decisions to benchmarks and model parameters is shown with computational results.

Covariance complexity and rates of return on assets
Speaker: Leonard MacLean, Dalhousie University, Canada
Abstract: This paper considers the estimation of the expected rate of return on a set of risky assets. It is well known that estimation errors have a significant impact on investment decisions and portfolio returns. The approach to estimation in this paper focuses on the covariance matrix for the returns. The structure in the covariance matrix determines shared information which is useful in estimating the mean return for each asset. An empirical Bayes estimator is developed using the covariance structure of the returns distribution. The estimator is an improvement on the maximum likelihood and Bayes–Stein estimators in terms of mean squared error. The effect of reduced estimation error on accumulated wealth is analyzed for the portfolio choice problem with log utility, the optimal growth model.

Speaker’s CV: Leonard MacLean is Professor in the School of Business Administration at Dalhousie University in Halifax, Canada. Dr. MacLean has held visiting appointments at Cambridge University, University of Bergamo, University of British Columbia, Simon Fraser University, Royal Roads University, University of Zimbabwe, and University of Indonesia. From 1989 to 1995 he served as Director of the School of Business Administration at Dalhousie University. Professor MacLean’s research focuses on stochastic models in finance, and models for repairable systems in aviation. He has published over 80 papers and co – authored 3 books. This work is funded by grants from the Natural Sciences and Engineering Council of Canada and the Herbert Lamb Trust. Dr. MacLean is the Editor of Quantitative Finance Letters. He teaches in the areas of statistics and operations management.

Your opinion, your Kelly strategy
Speaker: Sebastien Lleo, Associate Professor of Finance and Director of doctoral program at NEOMA Business School – Reims Campus, France
Abstract: One of the great challenges for fund managers and investors is to formulate accurate views about the future performance of individual securities. The difficulty is that the underlying state of the securities markets is not directly observable. To address this problem, we propose a continuous-time asset allocation model with partial observation, which uses a filter to estimate a hidden state variable from observable variables. These observations include both securities prices and expert opinions. The model sheds new light on dynamic investment management, and extends the idea of fractional Kelly strategies to account for differences in strategies observed among investors.

Speaker’s CV: Sebastien Lleo is an Associate Professor in the Finance Department at NEOMA Business School and a tutor on the Certificate in Quantitative Finance at FitchLearning. He was previously Research Associate at Imperial College London in the UK, worked for in the investment industry in Canada and consulted on risk management and asset allocation projects in Canada and the UK. His main interests include investment management, stochastic control and stochastic analysis, data science and data analytics, behavioural finance, risk management. Sebastien holds a PhD in Mathematics from Imperial College London (UK), a MBA from University of Ottawa (Canada), and MSc in Management from NEOMA Business School (France). He is also a CFA Charterholder, a Certified Financial Risk Manager, a Professional Risk Manager, and a CQF alumnus.

 

Workshop 2
27 June 2017
Time: 09:30 – 17:00

Sentiment Extraction and Applications for Financial Prediction

Background

Extracting sentiment out of text-based information sources is both an art and a science. Diverse information sources such as corporate filings, macroeconomic announcements, as well as extreme events such as natural disasters, war and political turmoil, all lead to significant impacts on the financial and retail consumer markets. In this workshop both extraction of information and sentiment and predictive models which utilise this information and sentiment are analysed and discussed.

Workshop Presenters include:
Ashok Banerjee, IIM Calcutta, India
Sanjiv Das, Santa Clara University, USA

Predicting Corporate Default using Text of Corporate Filings 
Speaker: Ashok Banerjee, IIM Calcutta, India
Banks and financial institutions in emerging markets are saddled with a huge proportion of bad loans. Banking regulations require lenders to provide for troubled debt which adversely affects the profitability of banks. The capital market also reacts negatively to such write-offs of big ticket debts. Banks are, therefore, putting significant resources into developing early warning signals to arrest eventual default. The financial institutions use a wide range of default prediction models to estimate the loan loss. These models use data from financial statements and the market. The present study shows that such models fail to provide effective early warning signals. We use annual reports of companies to develop a default model which is predictive and hence has the capability of providing early warning signals. Using information from Directors’ Reports, Audit Reports and notes to accounts, our model successfully discriminates the ‘good’ firms from the ‘bad’ ones.


Attention and Sentiment
Speaker: Ashok Banerjee, IIM Calcutta, India
Abstract: Studies at the Finance Lab of IIM Calcutta show that the effect of any news on the market depends on the attention of investors. If the attention of investors were somewhere else, even news carrying strong positive/negative sentiment would go unnoticed or would be penalized. This is particularly true in the case of major non-market attention grabbing events. In other words, attention overwhelms the effect of sentiment. Processing any attention-grabbing event requires effort. If that effort is directed towards some particular information, people are too lazy to put in the extra effort to process any other information at the same time, no matter how much sentiment that information might carry.

Speaker’s CV: Ashok Banerjee is currently the Departmental Head of Finance and Control, at the Indian Institute of Management (IIM) Calcutta. He joined IIM Calcutta as Professor (Finance and Control) in 2004 and has been instrumental in setting up the state-of-the-art Financial Research and Trading Laboratory (Finance Lab) there. He is also the founding member of Indian Finance Association.

 

Text Analytics for Sentiment Extraction in Finance with Applications
Speaker: Sanjiv Das, William and Janice Terry Professor of Finance, Leavey School of Business, Santa Clara University, USA

This tutorial surveys the technology and empirics of text analytics in finance. It covers various tools of information extraction and text analytics for determining sentiment. We present a range of techniques of classification and predictive analytics, topic analysis, and metrics used to assess the performance of sentiment algorithms. We also visit the literature on text mining and predictive analytics in finance, covering a wide range of text sources such as blogs, news, web posts, corporate filings, etc. The R programming language is used, and various packages therein are presented.

Part I: Information Extraction and Text Analytics
Part II: Techniques of Classification and Predictive Analytics
Part III: Use of R and Applications

Speaker’s CV: Sanjiv Das is the William and Janice Terry Professor of Finance at Santa Clara University’s Leavey School of Business. He was previously Associate Professor at Harvard Business School and UC Berkeley. He holds post-graduate degrees in Finance (M.Phil and Ph.D. from New York University), Computer Science (M.S. from UC Berkeley), an MBA from the Indian Institute of Management, and is a qualified Cost and Works Accountant. He edits several academic journals. Prior to being an academic, he worked in the derivatives business as a Vice-President at Citibank. His current research interests include: the modeling of default risk, machine learning, social networks, derivatives pricing models, portfolio theory, and venture capital. He has published over ninety articles in academic journals, and won numerous awards for research and teaching. His recent book “Derivatives: Principles and Practice” was published in May 2010. He currently also serves as a Senior Fellow at the FDIC Center for Financial Research.

 

Workshop 3
30 June 2017
Time: 09:30 – 15:00

Novel Data Sources and Contents for Financial Markets

Background

In the last 20 years, society has experienced a major paradigm shift in communication. More than 2 billion people use mobile devices and constantly communicate what they see and think on social media. By using advanced sentiment analysis and deep learning, it is possible to mine these sources. Leading research teams have embarked upon ways to extract and exploit information from these multiple information streams. These workshops provide a glimpse of the revolutionary developments which are afoot in this domain.

Workshop Presenters include:
Karo Moilanen, CTO & Co-founder, TheySay Ltd, Visiting Academic at the Department of Computer Science, University of Oxford
Satoshi Shizume, Financial Technology Research Institute
Elisabetta Fersini, University of Milano-Bicocca Italy
Anders Bally, Sentifi

Combining quantitative classification with NLP approach: Text and Sentiment to Financial Signals
Speaker: Karo Moilanen, CTO & Co-founder, TheySay Ltd, Visiting Academic at the Department of Computer Science, University of Oxford

Speaker’s CV: Dr Karo Moilanen, with a background in linguistics, has over fourteen years of experience in natural language technology spanning industrial and academic contexts. Karo’s PhD research work at Oxford focused on fine-grained compositional sentiment analysis. Karo’s industrial NLP work (at Infonic, Powerset, Microsoft Search Labs (Silicon Valley), AlphaSense Inc., and TheySay Ltd) has covered the entire life cycle of text analytics applications and platforms across most aspects of natural language technology. Karo is currently developing NLP applications for Finance inspired by emotion psychology and functional linguistics towards augmented trading models, and more nuanced information extraction and knowledge management solutions.

Title To be Announced
Speaker: Satoshi Shizume, Financial Technology Research Institute

Sentiment Analysis in Microblogs
Speaker: Elisabetta Fersini, Assistant Professor, University of Milano-Bicocca Italy

In this talk we address the challenges of sentiment analysis of microblogs. We show how combining post contents and network structure information may lead to significant improvements in the polarity classification of the sentiment both at post and at user level. We also discuss the potential of deep learning for enhancing the classification performance through a high-level feature representation.

Speaker’s CV: Elisabetta Fersini is currently assistant professor at the University of Milano-Bicocca (Computer Science Dept.). Her research activity is mainly focused on propositional and relational machine learning for natural language processing.

 

Social Listening & Financial Crowd-Intelligence
Speaker: Anders Bally, Sentifi

In the early 90’s the majority of financial market participants used news mainly from services like Bloomberg and Reuters to inform themselves. 20 years later, they still do. During the same period, our society went through a communication paradigm shift. Today more than 2 Billion people walk around with mobile devices and communicate what they see and think on social media. These billions of voices, when structured, can generate insights which can help investors make better investment decisions. This presentation will touch on how Sentifi structures and delivers these insights, providing an information advantage for media platforms globally.

Speaker’s CV: Anders Bally is CEO and founder of Sentifi. Based in Switzerland he has co-built a number of companies in the areas Asset Management, Private Equity, Software and Social Media since 1992. After 8 years in pioneering environmental fund management he earned a PhD analyzing influence of environmental stakeholders on Shareholder Value. After exiting with a software company to SAP, he returned to stakeholder influencing again and founded Sentifi in 2012. Sentifi’s vision is to build the largest eco-system of crowd-intelligence globally for the financial markets by structuring billions of unstructured data from stakeholders of listed companies, commodities and currencies.

 

Price for the Workshops

  • Super Early Bird: £175 + VAT per day until 28 April
  • Early Bird: £250 + VAT per day until 19 May
  • Standard Price: £325 + VAT per day
  • Buy ticket

Receive a complimentary copy of the landmark publication Handbook of Sentiment Analysis in Finance (pub 2016) when you register for the workshop on 30 June!
The Handbook is priced at £95 but is free to attendees at the workshop on 30 June.

 
There are preferential rates for academics, students and also combined price with conference, please contact aqeela@unicom.co.uk