The financial services sector was in focus at this week’s Sentiment Analysis Symposium in New York City, which is organized and produced by Alta Plana Corp. and its founder, Seth Grimes.  Take, for example, the presentation by Rich Brown, head of Elektron Analytics at Thomson Reuters, who disclosed that the company is about to launch market response indicators in support of its Thomson Reuters News Analytics system for the financial community. That product this week also won The Technical Analyst’s 2012 award for best news analytics software.

With its software, originally discussed here, qualitative, unstructured information is turned into a quantitative data set allowing users – machines and humans – to quickly analyze thousands of news stories in less time than it takes to read a single headline, as Thomson Reuters describes it. It uses natural language processing technology to get to the end game, which is to forecast financial market response from news and social media sentiment. Some 82 fields of metadata come into play for automating the analysis of news content. That encompasses sentiment down through to the degree of positive, negative or neutral expressions and how individual companies mentioned in a piece fare in those respects – rather than just the tone of the piece at large. “The computational linguistics system measures the author’s tone as positive or negative on any given entity, which is important and the harder part of it,” Brown said. Other fields include, for example, relevance, genre, intensity of news flow, and more.

The cases for traders using machine-readable news include that “the volume of news can predict [trading] volume and volatility,” Brown said. “Our system lets you increase the signal to noise ratio. You can filter out the noise so you are not trading on stuff like [a stock being] down in late-day trading, which you already know.” The software also is distinguished by proven alpha-bearing signals, for anticipating performance on a risk-adjusted basis, across different trading horizons, he said. The addition of market response indicators to the technology will exploit the information in its output fields in powerful visualizations, using analytics and machine-learning technologies to determine how much each one matters. “If you think about the recipe of which of these matter most, we can predict in 90 minute windows what we expect from the direction of a stock, its tradiing volume and price volatility patterns,” he said.

In March, the company also extended its machine-readable news offering to include a sentiment scoring service for social media. So its source set now encompasses up to 50,000 news sites and four million social media sites. “We’re taking the problem of Big Data and turning it into an opportunity,” he said. “So we now have a broad expansion of sources scored by the system to complement Reuters news.”

How much does news sentiment matter to trading? A study by Marco Dion, European Head of Equity Quant Research at JP Morgan, provides insight into the complexities. This includes the finding that a daily strategy of buying stocks with highly positive news sentiment scores and shorting those with equally strong negative sentiment scores generated annualized returns of 95 percent, before factoring in transaction costs (read more about that study here).

Credit Sentiment Issues

At the event, Ron Papka, Global Head of Client Analytics and Market Data Distribution at Citigroup, also discussed the company’s credit sentiment monitor on CitiVELOCITY, an analytic app for the research and trading platform. It is used by about 30,000 clients and itself leverages Thomson Reuters’ news feeds to drive capabilities like news sentiment analytics for credit default swaps (CDS) and indices of credit default swaps.

“In general, on average over the long-term, you see that applying sentiment in your strategy could… improve outperformance,” he said. Some challenges remain in terms, for example, of supporting foreign exchanges, around identifying the currencies discussed and attributing proper sentiment to them, he said.

Also providing some insight into how sentiment analytics matters to the financial community was Rage Frameworks Vice President of Customer Services Srini Bharadwaj. He discussed applying the company’s semantic intelligence platform to provide real-time intelligence of credit risks for institutions to effectively monitor borrowers globally. He noted that one large bank is currently using the technology to this end.