In a few weeks, big data analytics provider RavenPack, will be holding its premier one day event on big data and machine learning in London. Speakers at this year’s conference will include top buy and sell-side professionals, as well as high profile academics. They will cover the most promising areas of machine learning and AI in finance, what’s real and what’s hype, as well as many real world examples of how alternative data is adding value to the investment process.
Expect a full day event with several standalone speaking sessions, a few lightning talks, a machine learning panel and a panel on alternative data, starting at 9:00 AM and ending at 5:00 PM GMT. A cocktail reception will follow at the venue.
The event will take place on April 24, 2018 at the Banking Hall, one of the most exquisite venues in Central London. It is free to attend for financial professionals with an invitation.
9:00 am Registration & Coffee
9:30 am Welcoming Remarks – Armando Gonzalez, CEO, RavenPack
9:40 am Quant Trading 101 – Nitish Maini, General Manager, Virtual Research Center / Vice President, Portfolio Management, WorldQuant LLC
Nitish will focus on the similarities and differences between quantitative and discretionary investing with an emphasis on the importance of data. He will also host a demonstration of quantitative alpha using a web based simulator.
10:10 am News Sentiment Everywhere! – Peter Hafez, Chief Data Scientist, RavenPack
In order to maintain an edge in the marketplace, asset managers are to a larger extend turning to unstructured content for alpha creation, using NLP and text analysis techniques. In addition, more and more managers are expanding their mandate, trading global portfolios, to ensure more scalable strategies. As part of his presentation, Peter will showcase how news sentiment can be a valuable input to such process.
10:30 am Straight talk about AI and Big Data: What is real? What is marketing hype? – Manoj Saxena, Chairman, CognitiveScale
Artificial Intelligence (AI) is rapidly moving from a mesmeric technology to a powerful teammate and a foundation for consumer and business decision making. However, AI is a young field full of amazing potential. It’s mystery and lack of understanding is also allowing for hype to grow unchecked. Unrealistic claims of an “AI singularity” and portrayals of an “AI apocalypse” are creating a hype machine that is unparalleled in recent history. The reality is somewhere in between these two extreme scenarios. This session will focus on some of the good practices around practical and high value applications of data and AI across healthcare, insurance, financial services, and digital commerce.
10:50 am News in Diffusion Index Modelling – Asger Lunde, Director, Copenhagen Economics and Professor of Economics, Aarhus University
Asger will cover forecasting of Chinese macroeconomic time series using a large number of prediction variables. He investigates what is the extent of improvement of forecasts when news sentiment indexes are included among the predictors. The results suggest that forecasts obtained with this method outperform univariate autoregressions and in shorter prediction horizon news indexes improve the forecasts.
11:10 am “Mapping” the Financial market context, thanks to alternatives data and machine intelligence – Dimitri Huwyler, Head of Quantitative Strategy and Aleksandar Pramov, Quantitative Researcher, Next Gate Capital
Successful market timing is a tantalizing holy grail for investors. On both side, investors and researchers have discovered that the market timing is harder than it might seems. At Next Gate Capital they think that this is a perfect research playground for new machine intelligence techniques and new alternative dataset. They use classic variables to build economic climate and global sentiment indicators, enhanced with news sentiments, particularly on politics and monetary policy (two fields very difficult to handle with classic dataset) and economy. They will cover a practical example of enhancement of a trend following strategy.
11:30 am Panel: Is Machine Learning The New Alpha Generator? – Moderator: Roland Fejfar, Executive Director , Morgan Stanley Fintech IB Division
- Mark Salmon, Professor, Cambridge University
- John “Morgan” Slade, CEO, CloudQuant
- Andrej Rusakov, Co-founding Partner, Data Capital Management
The financial sector is making a massive shift towards big data and machine learning technologies. Panelists will share their experience in using data science and domain expertise in understanding data context.They will address how machine learning can be useful in creating new alpha signals, as well as in the data generation/preparation process, in portfolio construction or risk management.
12:30 pm Lunch
13:30 pm Improving Systematic Strategies with Big Data and Machine Learning – Ada Lau, Quantitative Strategist, J.P. Morgan Securities (Asia Pacific)
We use two examples to demonstrate how big data and machine learning can add value to systematic strategies. The first strategy is on equity mean-reversion in Japan, where we find that news volume and news sentiment can be a useful overlay due to behavioral bias. The second example covers a Global value strategy based on Machine Learning algorithms. We show that Machine Learning models can outperform simple linear benchmarks, and news sentiment could further enhance the strategy.
13:50 pm Understanding and overcoming the weak points of Big Data and Machine Learning investing – Andrej Rusakov, Co-founding Partner, Data Capital Management
Practitioner’s point of view on what in big data and machine learning investing is challenging and what to do about it. Demystifying the “magic box”, sharing best practices and real-life examples of machine learning application to investing including NLP with RavenPack.
14:10 pm The Dangers of Machine Learning and How to Overcome Them – Mark Salmon, Professor, Cambridge University; Director of Research, Centre for Advanced Financial Engineering and Advisor, Old Mutual Global Investors
This talk will review recent academic literature that attempts to ensure causation rather than correlation in the use of machine learning. Applications of ML in Genome/Cancer research have recognized this critical issue for some time and the case is obviously equally strong in Finance where money may be allocated on the basis of completely spurious data driven models. We will look at developments in “Post Model Selective Inference” and “Counter-factual Causal Prediction” with examples. If time permits we will also discuss recent statistical literature that questions the notion of “Big” data where the value of incremental data may tend to zero and how inference should be adapted.
14:30 pm Machine Learning and Alternative Data in Long/Short Equity Portfolios – Richard Bateson, Director, Bateson Asset Management
Combining alternative news and sentiment data with traditional signals can provide increased risk-adjusted returns in long/short equity portfolios. In this presentation we consider the application of Machine Learning techniques to capture these effects and explore non-linear approaches to alternative data.
14:50 pm Factor Returns and Sentiment – Louis Scott, Founder, Kiema Advisors and Consultant, Style Research
Do factors perform differently under news driven sentiment? Using Style Research and RavenPack sentiment data, Louis constructs regional factors and sentiment indices in the spirit of Hafez and Xie 2016. Results show strong differences under periods of high and low sentiment. The design of a quarterly moving average is distinct from most findings that reveal intra-day to a few days efficacy for sentiment. In particular, a strong difference in underlying distribution of factor returns is revealed and the Sortino ratios are distinct under sentiment regimes.
15:10 pm Break
15:40 pm Lessons from Facebook for the Alternative Data Industry – Michael Mayhew, Principal, Integrity Research
Lightning talk: Facebook has recently come under significant scrutiny from customers, the press, and US Congress about how it allowed firms to siphon personal information from millions of user accounts. While this case is interesting in its own right, it highlights a number of lessons for vendors and users of alternative data about the risks of selling or using data that could provide personally identifiable information.This presentation discusses these risks and the steps firms should take to mitigate these risks.
15:50 pm Latest Innovations in Market-Moving Event Detection – Jason Cornez, Chief Technology Officer, RavenPack
Lightning talk: RavenPack automatically detects thousands of different types of market moving events in unstructured text documents. An enriched event captures more context from the document to provide more color about what the event means. We take a quick look at how events are detected now and what innovations are happening to help enrich the events the system can detect moving forward.
16:00 pm The Evolution of Discretionary Investing in Data Science – Dan Furstenberg, Head of Data Strategy, Jefferies
Lightning talk: Dan will discuss alternative data integration on the buy-side, with an emphasis on quantifying strategy. He’ll be highlighting how nearly 50 fundamental investors are actively building these efforts and are approaching alternative data from a talent, infrastructure and resourcing perspective. He will also cover the data science landscape across investment managers.
16:10 pm Panel: How to avoid the Alternative Data Pitfalls? – Moderator: Dan Furstenberg, Head of Data Strategy, Jefferies
- Peter Hafez, Chief Data Scientist, RavenPack
- Leigh Drogen, CEO, Estimize
- Rich Brown, Managing Director, Schonfeld Strategic Techworx
- Michael Mayhew, Principal, Integrity Research
This panel addresses what key areas financial institutions should have in mind when looking at alternative data to avoid wasting resources on alternative datasets doomed not to provide value. Panelists will share their experience highlighting what pitfalls they should try to avoid as quant or fundamental investors, and how to be successful with alternative data. They will also discuss what attributes are required of a potentially performing alternative dataset.
17:00 pm Cocktail Reception