Back to All Related Articles
From WSJDN
#Trend: Trading on Social Media
Hedge funds and proprietary-trading shops are working to automate trading on information and sentiment from the blogosphere and Twitter, an effort that could make social media even more influential.
The move reflects the continued evolution of automated trading through computer algorithms, with social media being targeted as the latest potential gold mine that could give trading firms an edge.
Companies have already been selling feeds for several years that deliver news data directly to automated trading programs. But efforts to do the same with information from blogs haven’t been as successful.
Some leading hedge funds and proprietary trading shops are believed to be doing some amount of automated trading on information from social media already. But Alacra Inc., an aggregator of data from traditional media and blogs, has a product that could make the practice much easier and more widespread.
Alacra on Tuesday will launch its PulsePro, a technology suite geared to help humans make more informed business and trading decisions. Meanwhile, there are half a dozen firms, mostly hedge funds, testing a feed of sentiment ratings generated through the product for automated trading.
“This is part of a larger trend to utilize unstructured content as an input for various types of trading signals,” said Paul Rowady, senior analyst at Tabb Group, a financial-markets research firm. He said while the trend began primarily with content from news organizations, social media represent “a natural extension of the trend.”
However, the idea of using social media in automated trading is raising some eyebrows over whether it could raise the influence of social media to a dangerous level.
“A lot of these blogs are one-person editorial teams. They don’t have the benefits of a 500-person news team fact-checking everything they say, and yet they have this incredible influence on a company’s direction,” said Ben Cathers, social media manager at Lightspeed Financial, a provider of trading technology and brokerage services.
Mr. Cathers noted some traders use Google Insights—which monitors buzz across the Internet—”as another item in their arsenal.” Message boards and StockTwits are other tools firms sometimes use to get a handle on the buzz for stocks they are trading.
But buzz can be good or bad, and not all buzz is relevant.
“There is a signal-to-noise ratio problem,” Mr. Rowady said. “There’s far more so-called noise on the Web than there would be in a newswire.”
Alacra’s PulsePro tries to tackle the issue in several ways. First, it looks only at blogs the company deems credible. The blogs are combined with articles from traditional media companies for a total of about 3,000 sources.
Rather than trying to codify all the text within each source, it focuses on specific items such as quotes from well-reputed Wall Street analysts and top-level executives. Sentiment ratings are assigned based on the language used.
Through backtesting, Alacra has found the ratings generated by its product can lead movements in stock prices by about one to three weeks for large-capitalization stocks. In turn, hedge funds and proprietary traders are interested in the feed despite that it won’t work anywhere near the lightning-fast speeds they’ve been achieving for much of their other computer-based trading.
“Our mandate is to basically create any systematic, automated trading strategy that we think will generate alpha, whether it be through high-frequency market making or lower-frequency fundamental systems,” said a quantitative researcher at a hedge fund testing the PulsePro, referring to investing parlance for risk-adjusted return on an investment.
StreamBase Systems Inc., which provides software for building systems that analyze and act on real-time streaming data, began offering free technology in June that provides the tools to trade on information in Twitter posts. But while clients do use it to make more informed trading decisions, StreamBase isn’t sure if any use it for completely automated trading. The idea has raised even more concern than that of automated trading on blog data.
Nevertheless, Mr. Rowady believes the number of firms trading on social media will grow with time. “As this segment matures over the coming decade,” he said, “it will have broad and in many ways an even more significant impact on how traditional asset management is conducted.”
