Recently I attended the Forum on News Analytics in London, organized by Carisma from Brunel University. In fact, Brian Sentance wrote a good summary of the event on his blog.
As part of the forum, a panel discussion was held with attendance from Northfield Information Services, Macquarie Equity Research, RavenPack, Thomson-Reuters, Semlab, and Capital IQ ClariFI.
What I mostly found interesting was that the different news analytics providers had chosen to approach the market from different angles. For instance, RavenPack and Reuters offered data feeds and "ready-made" analytics, while Semlab required the end-user to define their own set of rules. From my experience, trying to build the lingusitic models and NLP algorithms yourself is a daunting task and definitely a fulltime job. As a quant, I prefer to focus on the analysis of the news data.
Carisma, Northfield and Macquarie briefly discussed some of their research involving news analytics (all studies were based on RavenPack data). Generally, it seems that most of the practical research out there is based on RavenPack data.
The forum was well attended with people coming from both academia and industry including high and low frequency traders, risk managers, and people focusing on algorithmic execution. I had a chance to talk to people from both camps and there is no doubt that news analytics has surely caught people's attention, and is becoming a hot topic. Especially, it seemed as if people were very much interested in discussing the different techniques that one can use to extract sentiment, but also to use such information to construct triggering events and sentiment factors.
It was definitely an interesting event, and I am looking forward to attending Carisma’s next event "The Interface of Behavioral Finance and Quantitative Finance" and the pre-conference workshop "News Analytics Applied to Trading, Fund Management, and Risk Control" taking place in London early next year.
Subscribe to:
Post Comments (Atom)
Posts
A recent virtual conference also dealt with news and sentiment. It can be viewed with registration, the agenda is here: http://tinyurl.com/yj87vbf
ReplyDeleteIn keeping with the name "Accelerating Wall Street", most of the talks were about low latency systems for HF trading. The last session, had talks by Mani Chandy (Caltech) and David Leinweber (me, Berkeley) on news and event analysis.
The slides feature event studies relating S&P1500 stock returns to news analytics built on sentiment, intensity and metadata.
There are some teaser screen grabs from the Event Study Explorer (ESE), an interactive exploratory data analysis system built using the Spotfire visualization tool. It allows sliders to be adjusted setting aggregation parameters, sector, and cap class - and gives instant feedback by showing the corresponding event studies.
Going even further in the "Overview first, filter, drill down to details" visualization mantra, the ESE can show the details of news content (both data and metadata) that can be used for hand or machine learned NLP filters.
It looks like comments are write-only once posted, so here are the details regarding the event studies described above:
ReplyDeletePeriod: 2003-2008 (new results available YTD09)
Data: Thomson Reuters NewsScope
Universe: Survivor-bias free SP1500