Organised by:

Unicom Seminars

 

Behavioural Models & Sentiment Analysis Applied to Finance

Venue: Fitch 7 City Learning, London
Date: 2 - 3 July 2013

 

Pre-conference workshop:
Market Microstructure Liquidity & Trading
1 July 2013 London

Thanks to the generous support of our sponsors, we are offering special price of £425 +VAT for combined booking of Conference + Pre-conference workshop

Background

Sentiment analysis has developed as a technology that applies machine learning and makes a rapid assessment of the sentiments expressed in news releases. News events impact market sentiment and financial news moves stock prices through a direct impact on a company’s expected future cash flows. This conference presents the current state of the art. It also explains how to apply Sentiment Analysis to the respective models of trading, fund management and risk control. The conference will present in a summary form the research results in this fast-emerging field.


Topics covered include:

  • Adoption of Sentiment Analysis in Fund Management and Trading Strategies
  • Trading Across Multiple Asset Classes Based on News Sentiment
  • Inside Global Brain: How Sentiment trends in news and social media influence global equity and currency values
  • Network Finance Models
  • Text mining for systemic risk
  • Order books, News flows, News Metadata, Market data: Predicting directional properties and volatility of asset prices
  • Introducing sentiment in the Predictive Analysis of Asset Behaviour: Return, Volatility and Liquidity in an Intra-day Setting
  • Social media metadata, trust, information leakage: impact on trading and compliance

Attendees at our previous/other finance events

  • Barclay Capital
  • Barclaycard
  • BNP Paribas
  • BP Pension Trustees Ltd
  • Citigroup
  • Credit Suisse
  • Deloitte
  • Deutsche Bank
  • Deutsche Boerse AG
  • Ernst & Young
  • Fidelity Investment
  • Financial Services Authority
  • GMI Resources
  • HSBC
  • IBM
  • JP Morgan
  • KPMG
  • Legal & General
  • Manualife Asset Management
  • Markit
  • Morgan Stanley
  • Neural Futures LLC
  • Royal Bank of Scotland
  • Standard Chartered
  • UBS Investment Bank

Preliminary programme

 

 

Day One: 2 July 2013

 

09:00—09:20  Registration and Coffee

09:20—09:30   Welcome & Introduction
                             By Gautam Mitra

09:30—10:15  Text Mining for Systemic Risk
Sanjiv Das, Professor of Finance,
Santa Clara University
¨ Tools and techniques for text-mining
¨ Generation of sentiment indexes
¨ Assessment of predictive value

10:15—11:00  Market- Level Sentiment for Trading Forex and Equity Indexes
Peter Hafez, Director of Quantitative Research,
RavenPack
Significant advances have been made in sentiment analysis and understanding its impact on financial markets in the last few years. One of these advances is news analytics finding its way from equities, where it started, into other assets like foreign exchange, commodities and sovereign debt. Peter Hafez  will present some of the latest research results of applying news analytics to finance, specifically market-level sentiment. He will use a number of empirical studies covering (i) short-term FX trading based on sentiment inflection points, (ii) short to mid-term FX trading based on relative sentiment, and  (iii) longer-term pairs trading on broad equity indexes

11:00– 11:30  Coffee Break

11:30– 12:00  Behaviouralising Finance: Maximising Anxiety Adjusted Returns
Greg B Davies, Managing Director/ Head of Behavioural Investment Philosophy, Barclays Wealth
We attain good investment returns not only (or even mostly) by knowing the 'right' answer: to be good investors we also need to be comfortable with our decisions over the journey. And yet all the tools of classical finance are geared towards instructing us in the 'right' answer, under the assumptions that a) we're superhumanly able to enact and stick with this, and b) that all that investors care about is efficient risk adjusted returns. They don't. What investors both want and need are anxiety adjusted returns: sufficiently good risk adjusted returns AND  a sufficiently comfortable investment journey. Only by behaviouralising classical finance models in pursuit of both these goals can we help investors get the best long run returns.

12:00—13:00  Panel 1: Adoption of sentiment analysis in fund management and trading strategies
Chairperson: Armando Gonzalez, CEO, RavenPack;
Panellists include: Greg B Davies, Managing Director/ Head of Behavioural Investment Philosophy, Barclays Wealth;
Sanjiv Das, Professor of Finance, Santa Clara University; Gautam Mitra, CEO, OptiRisk; Gurvinder Brar, Head of Quantitative Research Group, Macquarie;

13:00—14:00  Lunch Break

14:00—14:45  Network Finance Models
Sanjiv Das, Professor of Finance, Santa Clara University
¨ Social network models in Finance
¨ Illustrative applications in private equity research
¨ Illustrative applications in systemic risk 

14:45—15:30  New research results of Sentiment Analysis
Gurvinder Brar, Head of Quantitative Research Group, Macquarie

15:30—16:00  Tea and Coffee Break

16:00—16:30 Impact of news events and its application in trading strategies
Gautam Mitra, Managing Director, OptiRisk Systems
¨ Filtering news events
¨ Sentiment & impact of news events
¨ Trading strategies using impact
¨ Comparison of strategies with and without news

16:30—17:15  Panel 2: Use of Sentiment Data for Risk Control and Compliances
Chairperson: Peter van Kleef, Lakeview
Panellists include: Dan diBartolomeo, President, & Founder, Northfield Information Services Inc; Gautam Mitra, CEO, OptiRisk; Mats Wilhelmsson, COO Scila AB; Chrisol Correia, Strategy & Business Development Director, DowJones Risk and Compliance,Nicolas Mallison Risk & Compliance Data Analytics Subject Matter Expert

17:15—18:30  Drinks and Networking

 

 

Day Two: 3 July 2013

 

Case Studies and Technology Overview

 

09:00—09:30 Tea and Coffee

09:30—10:15 Inside the Global Brain: How sentiment trends in news and social media influence global equity and currency values
Richard Peterson, CEO, MarketPsych
"Achetez aux canon, vendez auz clarions" [Buy to the sound of cannons, sell to the sound of trumpets]
~ Attributed to Baron Nathan Rothschild, 1812.
Rothschild’s quote captures the essence of a contrarian country investment philosophy – the best time to invest in a nation is during a period of war or panic, and the best time to sell is during a time of contentment and celebration. The convergence of natural language processing, cloud computing, and map reduce architectures (big data), allow the quantification of real-time information flow into numerical streams useful in quantitative analysis. This presentation examines studies performed on a country-level sentiment data feed and concludes with a review of the impact of both country and currency sentiments on future global equity and currency pricing.

10:15—10:45 How to use Language Recognition and Quantifiable News Flow in creating Trading Strategies
Marco Dion, Managing Director, Global Head of     Equity Quant Strategy, J. P. Morgan
Company News flow has an undeniable impact on stock prices. Depending on how positive or negative the news item, it can even represent the most important element defining a stock’s annual performance. In our paper, we have used the Thomson Reuters – News Analytics data to test alternative ideas and explore if news flow can be used for longer-term investment (daily, weekly and monthly) by Quant Managers to generate alpha or manage risk. While initial (and naïve) testing failed due to the fast decay of news items, we did find methodologies that turned news flow signals into alpha sources. The key results are that :those strategies based on various holding periods (short-term and medium term), on news momentum, news signals for turn-around companies, conditioning of signals for short-sellers, sector allocators can improve the overall efficiency of Quant Factor Models

10:45—11:15 Tea and Coffee Break 

11:15—12:00 Credit Risk Assessment of Corporate and Bank Debt using Sentiment and News
Dan diBartolomeo, President, & Founder,
Northfield Information Services Inc
We illustrate the use of sentiment statistics obtained from quantified news to calibrate and update the credit risk of corporations and financial institutions. A modified version of the Merton (1974) contingent claims model (diBartolomeo, 2010,2011) is used to break each corporate debt into two pieces. The first considers riskless debt and the second equity in the issuer.  The sentiment statistics is used to continuously calibrate the expected volatility and bankruptcy potential of the equity portion thereby the credit risk of the debt. Unlike use of sentiment statistics in the search for alpha within equity strategies, where “good” or “bad” news may already have been acted : upon by other market participants, use of sentiment for credit risk has the advantage that it is largely unambiguous “good” news is good and “bad news” is bad for creditors. 

12:00—12:30 Introducing Sentiment in the Predictive Analysis of Asset Behaviour: Return, Volatility and Liquidity in an Intra-day Setting
Xiang Yu, Researcher News Analytics; Keming Yu & Gautam Mitra, Brunel University.
We report an empirical study of a predictive analysis model for equities; the model uses high frequency (minute-bar) market data and quantified news sentiment data. The purpose of the study is to identify a predictive model which can be used in designing automated trading strategies. Given that trading strategies take into consideration three important characteristics of an asset, namely, return, volatility and liquidity, our model is de-signed to predict these three parameters for a collections of assets (finance industry stocks). The minute-bar market data as well as intraday news sentiment meta-data have been provided by Thomson Reuters.

12:30—13:30 Lunch Break

13:30—14:15 Improvement of the volatility measurement through inclusion of market  behaviour
Giles-Arnaud Nzouankeu Nana , Researcher, Fraunhofer ITWM
We present two models that can be used in order to incorporate news effects in the computation of the volatility of companies stocks. Through results of an empirical study we also present the improvement of the volatility measurement that is obtained by including the market sentiment in the computations. The news sentiments are provided by ViewerPro, the sentiment analyzer of Semlab.

14:15-14:25 Comfort Break

14:25—15:10 Quant 3.0: Harnessing the mood of the web in alpha strategies
Rochester Cahan, CFA, Director | Head of US Quantitative Strategy, Deutsche Bank Securities Inc. New York
The web is a challenge and an opportunity for quantitative investors. For a data-driven discipline like ours, the vast volume of data available online is a potential gold mine. But like all mining, getting at the treasure is harder than it looks. In this research we use a new database of internet and social media sentiment to try to untangle the web into something useful for systematic investors. Specifically we show that (1) web-based sentiment signals decay more slowly than those based on financial news, and (2) that momentum and reversal signals can be usefully conditioned based on news/web flow.

15:10-16:10 Panel 3: Social media metadata, trust, information leakage: impact on trading and compliance
Chairperson: Richard Peterson, MarketPsych, Rochester Cahan, Deutsche Bank Securities Inc,  Dan diBartolomeo, President, & Founder,Northfield Information Services Inc; James Cantarella, Thomson Reuters; Bram Stalknecht, CEO, SEMLAB; 

16:10—16:30  Tea & Coffee and closing of Conference

 

 

 

 


Speakers

Professor Gautam Mitra, MD OptiRisk Systems

Professor Gautam Mitra

MD OptiRisk Systems 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. He has published three books and over hundred refereed research articles. He was Head of the Department of Mathematical Sciences, Brunel University between 1990 and 2001. In 2001 he has established CARISMA: The Centre for the Analysis of Risk and Optimisation Modelling Applications. CARISMA specialises in the research of Risk and Optimisation and their combined paradigm in decision modelling. Professor Mitra is a Director of OptiRisk Systems UK and OptiRisk India. Many of the research results of CARISMA are exploited through these companies

Peter van Kleef, Managing Director Lakeview Capital Market Services GmbH

Peter van Kleef

Prior to his role at Lakeview, Peter managed significant hedge fund type investment portfolios and quantitative trading departments for among others Cooper Neff, Salomon Brothers, HypoVereinsbank and Credit Lyonnais. He has nearly 20 years of experience in the development and running of sophisticated automated trading operations. He holds a MBA degree from the Owen Graduate School at Vanderbilt University, Nashville, USA. He is a frequent speaker on complex arbitrage strategies with a focus on volatility arbitrage and high frequency algorithmic trading. He is also a well known consultant to the investment community with regards to trading, risk management, operational and strategic issues. Lakeview provides a large range of trading and risk management related services.

Peter Hafez, Director of Quantitative Research, RavenPack

Peter Hafez

Peter is an award-winning expert in the field of applied news analytics and has consulted for numerous leading trading and investment firms on how to take advantage of news analytics in financial markets. Peter has more than 10 years of experience in quantitative finance with companies such as Standard & Poor's, Credit Suisse First Boston, and Saxo Bank. He is a recognized speaker at conferences on behavioral finance and algorithmic trading and a regular contributor of www.SentimentNews.com blog, where he shares his research findings and views on the news analytics industry. Peter holds a Master's degree in Quantitative Finance from City University's Cass Business School along with an undergraduate degree in Economics from Copenhagen University.

Marco Dion, Managing Director, Head of Equity Quant Strategy, J.P. Morgan

Marco Dion

Marco is the Global Head of the Quant Strategy team at JP Morgan. Marco joined J.P. Morgan in May 2007, after working at MSI Securities in London, where he was a senior trader responsible for managing the company's proprietary long/short equity book according to a fundamental and systematic framework. Prior to that, Marco worked in a similar role at Jaguar Funds in Australia and Mako Global, trading derivatives in Europe and Asia. Marco and team have been top-ranked by investors in numerous surveys since 2008 including Extel and Institutional Investors where they ranked #1 Quant team in Europe in the 2008 & 2010 and #2 in 2009, 2011 and 2012.

Miss Xiang Yu is a PhD candidate at Brunel University

Xiang Yu

Miss Xiang Yu is a PhD candidate at Brunel University, West London. Her research interests lie in the fields of news analytics and high frequency trading, with particular emphasis on liquidity and asset behaviour. She graduated from University of Manchester in 2010 with a degree in BSc (Hons) Mathematics with Finance.

Rochester Cahan, U.S. head of Deutsche Bank’s Quantitative Strategy team

Rochester Cahan

Rochester Cahan is the U.S. head of Deutsche Bank’s top-ranked Quantitative Strategy team. Rochester’s research focuses on discovering new stock-selection signals, finding better portfolio construction methodologies, and testing risk management techniques. His recent research has focused on using new data sources - for example options data, news sentiment data, securities lending data, and fixed income data - to develop innovative alpha strategies for equity investors. Before joining Deutsche Bank in 2009, Rochester spent seven years working as a quantitative analyst for Citigroup and Macquarie in both New York and Sydney, Australia. Rochester holds a joint Bachelor of Business Studies/Bachelor of Science (Finance/Mathematical Physics) degree from Massey University in New Zealand, and is a CFA charter holder.

Giles-Arnaud Nzouankeu Nana is a PHD student at the University of Kaiserslautern in Germany

Giles-Arnaud Nzouankeu Nana

Giles-Arnaud Nzouankeu Nana is a PHD student at the University of Kaiserslautern in Germany. Conducting his research in Fraunhofer ITWM (Institut für Techno und Wirtschaftsmathematik) in Kaiserslautern in the field of financial mathematics, especially in the improvement of risk management through news analytics, he is interested in both theoretical research and practical applications. He has given many talks in his research field and is involved in some research projects

Armando Gonzalez is President & CEO of RavenPack

Armando Gonzalez

Armando Gonzalez is President & CEO of RavenPack, the leading provider of real time news analysis in finance. Armando is an expert in the field of text analytics and applied semantic technologies. He has designed systems that turn textual news into data that can be easily consumed by quantitative models and trading programs. These state of the art systems can process content from thousands of sources with low latency and automatically read and analyze tens of thousands of news stories in real-time. Armando is widely regarded as one of the most knowledgeable authorities on automated text and sentiment analysis. His commentary and research has appeared in leading business media such as the Wall Street Journal, Financial Times, CNBC, among many others. Armando holds degrees in Economics and International Business Administration from the American University in Paris and is a recognized speaker at conferences on behavioral finance across the globe.

Mr. diBartolomeo, President & founder of Northfield Information Services, Inc.

Dan diBartolomeo

Mr. diBartolomeo is President and founder of Northfield Information Services, Inc. Based in Boston since 1986, Northfield develops quantitative models of financial markets. He is also a Visiting Professor at the CARISMA research institute of Brunel University in London. Dan has published more than two dozen books, book chapters and research studies in refereed journals. He regularly lectures at universities such as MIT, Harvard and Northwestern and has been admitted as an expert witness in litigation matters regarding investment management practices and derivatives in both US Federal and state courts.

Richard Peterson, CEO, MarketPscych

Richard Peterson

Dr. Peterson is CEO of MarketPsych Data which produces psychological and macroeconomic data derived from text analytics of news and social media. MarketPsych's data is consumed by the world's largest hedge funds. Dr. Peterson is an award-winning financial writer, an associate editor of the Journal of Behavioral Finance, has published widely in academia, and performed postdoctoral neuroeconomics research at Stanford University.

Professor Klaus Reiner Schenk-Hoppé, Centenary Chair in Financial Mathematics at the University of Leeds

Professor Klaus Reiner Schenk

Professor Klaus Reiner Schenk-Hoppé holds the Centenary Chair in Financial Mathematics at the University of Leeds and is visiting professor in finance at the Norwegian School of Economics. His current research interests include market microstructure and its relation to portfolio management as well as the regulation of limit order markets. Klaus has a PhD in mathematics.

Sanjiv Das, Professor of Finance at Santa Clara University's Leavey School of Business

Sanjiv Das

is the William and Janice Terry Professor of Finance at Santa Clara University's Leavey School of Business. He previously held faculty appointments as Associate Professor at Harvard Business School and UC Berkeley. He is a senior editor of The Journal of Investment Management, co-editor of The Journal of Derivatives, and Associate Editor of other academic journals. Prior to being an academic, he worked in the derivatives business in the Asia-Pacific region 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 eighty articles in academic journals, and has 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.

Fees

Thanks to the generous support of our sponsors, we are offering special price of £425 +VAT for combined booking of Conference + Pre-conference workshop

To register online click here.

Conference Fee: £300 + VAT

Online Attendance: £90 + VAT

Workshop Fee: £150 + VAT

Combined Price (Conference +Workshop)

Thanks to the generous support of our sponsors, we are offering special price of £425 +VAT for combined booking of Conference + Pre-conference workshop

 

Brochure Download
Sponsored by:
OptiRisk Logo
Ravenpack
Partners:

1410 Market Psych PRMIA

CQF