About a-team Marketing Services
The knowledge platform for the financial technology industry
The knowledge platform for the financial technology industry

A-Team Insight Blogs

Trading on Unstructured Data 101 at SXSW

Subscribe to our newsletter

SXSW – for South by Southwest – is a massive festival of music, film and web-related technology that just got going here in Austin, TX. I’ve been attending now for a few years for the music shows, where the event got its start, 25 years ago. But nowadays the ‘Interactive’ side is bigger, and this year I was pleasantly surprised to find a session on “Machines Trading Stocks on News” was on the program. So, after my usual Sunday brunch at Mulberry (brioche french toast and a couple of mimosas), I stopped by.

The panel session was moderated by Adam Honore, research director at Aite Group, and included: RavenPack CEO Armando Gonzalez; Jacob Sisk, senior research scientist at Thomson Reuters; and John Kittrell, who is a quantitative analyst at Knightsbridge Asset Management.

Unstructured data encompasses many sources, include textual news feeds, news and company websites, company and personal blogs, social networks and micro-blogging services like Twitter. A number of companies – including Dow Jones, Deutsche Boerse’s Need To Know News unit, RavenPack, Selerity and Thomson Reuters – take this unstructured data and parse it using semantic analysis to create structured feeds with XML tags.

Trading using unstructured data is growing. Aite Group reckon that back in 2008, just two percent of trading firms were involved in it. Today, that estimate has grown to nearly a third of firms are evaluating adopting it.

Collecting and analysing unstructured data allows a firm to determine so-called sentiment as it pertains to a company. Sentiment – as defined by the panel – being “emotional language” relating to an event that drives a stock price either up or down.

Events might be news items related to company results, products, regulatory approvals and credit ratings. Understanding the context in which words are used is important, for example: “900 layoffs at AOL” as a news story headline has very different context, and likely impact, from a blog post that relates “… and layoffs are down in the auto sector.”

And latency also plays a role, such as in relaying data related to economic bulletins from government departments in Washington DC to futures traders in Chicago, where the impact of such news is usually significant, said Honore.

Recent action in that endeavor includes CoreSite’s hosting of collection and relay systems from Need to Know News and Rapidata at its date centre, located just one mile from the United States Department of Labor, Department of Commerce and Department of The Treasury. Also relevant is the Intellifiber Networks low-latency optical network from DC to Chicago.

Along with a screening of Senna, this session was a nice diversion from the music that will take up the rest of my week. Check out my other blog for some day parties I’m hosting, and other coverage. #donttellmybossshethinksimworking.

Subscribe to our newsletter

Related content

WEBINAR

Upcoming Webinar: Data platform modernisation: Best practice approaches for unifying data, real time data and automated processing

Date: 17 March 2026 Time: 10:00am ET / 3:00pm London / 4:00pm CET Duration: 50 minutes Financial institutions are evolving their data platform modernisation programmes, moving beyond data-for-cloud capabilities and increasingly towards artificial intelligence-readiness. This has shifted the data management focus in the direction of data unification, real-time delivery and automated governance. The drivers of...

BLOG

Bloomberg BQuant Wins A-Team AICM Best AI Solution for Historical Data Analysis Award

When global markets were roiled by the announcement of massive US trade tariffs, Bloomberg saw the amount of financial and other data that runs through its systems surge to 600 billion data points, almost double the 400 billion it manages on an average day. “These were just mind-blowingly large volumes of data,” says James Jarvis,...

EVENT

TradingTech Summit New York

Our TradingTech Briefing in New York is aimed at senior-level decision makers in trading technology, electronic execution, trading architecture and offers a day packed with insight from practitioners and from innovative suppliers happy to share their experiences in dealing with the enterprise challenges facing our marketplace.

GUIDE

Managing Valuations Data for Optimal Risk Management

The US corporate actions market has long been characterised as paper-based and manually intensive, but it seems that much progress is being made of late to tackle the lack of automation due to the introduction of four little letters: XBRL. According to a survey by the American Institute of Certified Public Accountants (AICPA) and standards...