Hedge Fund Will Track Twitter to Predict Stock Moves
Derwent Capital Markets, a family- owned hedge fund, will offer investors the chance to use Twitter Inc. posts to gauge the mood of the stockmarket, said co-owner Paul Hawtin.
The Derwent Absolute Return Fund Ltd., set to start trading in February with an initial 25 million pounds ($39 million) under management, will follow posts on the social-networking website. A trading model will highlight when the number of times words on Twitter such as “calm” rise above or below average.
A paper by the University of Manchester and Indiana University published in October said the number of emotional words on Twitter could be used to predict daily moves in the Dow Jones Industrial Average. A change in emotions expressed online would be followed between two and six days later by a move in the index, the researchers said, and this information let them predict its movements with 87.6 percent accuracy.
“Sentiment and mood dramatically change the impact of positive and negative news stories,” said Hawtin in a telephone interview. “If the market’s in a very positive and bullish mood, it can shrug off bad news -- bad news comes out and you expect the Dow to fall, and it doesn’t.”
Twitter now has 175 million users and sees 95 million posts per day, according to its website. That has risen from 50 million per day as of February, and researchers are finding new uses for this rapidly growing source of real-time data.
Derwent Capital Markets, based in London’s West End, signed an exclusive deal this month with Xiao-Jun Zeng, a doctor of computer science at the University of Manchester, to develop the research into trading models. Derwent will also meet with associate professor Johan Bollen and colleague Huina Mao of Indiana University this week to discuss the possibility of them working on the new fund, Hawtin said.
The fund will use algorithms based on the data extracted from Twitter posts and other factors to trade the FTSE 100, FTSE 250 and Dow Jones Industrial Average indexes as well as oil, gold and other precious metals and currencies.
Zeng, Bollen and Mao’s research measured the public mood by searching Twitter posts from February to December 2008 for synonyms of and language related to six moods: calm, alert, sure, vital, kind and happy. The researchers then matched the time and date of these posts to closing prices of the Dow Jones Industrial Average to test their hypothesis that changes in the sentiments expressed online could predict future index values.
Their results showed that rises and falls in the number of instances of words related to a calm mood could be used to predict the same moves in the Dow’s closing price between two and six days later, with a fall in these “calm” words being followed by a fall in the index. The other moods did not have the same predictive quality, the paper said.
A chart in the researchers’ paper shows instances of “calm” words on Twitter and daily moves in the Dow’s closing price. The two lines closely follow each other’s movements, with rises and falls in the Dow lagging a few days behind the same movements in the Twitter numbers.
Derwent expects an annual return on investment of between 15 percent and 20 percent on the new fund, Hawtin said, adding that 1.5 million pounds of the initial stake will be the managers’ own money.
“The only risk for us is if Twitter falls away and people just don’t use it any more,” Hawtin said. “But we believe that it can only get bigger and better, and that more and more people will be using it to express their feelings.”
Sixty-six percent of online Americans now use social- networking websites, according to a Jun. 10 report by Experian Information Systems Inc. Facebook Inc.’s website was the most visited in the world last week with 10.1 percent of all internet page views, Experian said on its website.
To contact the editor responsible for this story: Colin Keatinge at email@example.com
Bloomberg moderates all comments. Comments that are abusive or off-topic will not be posted to the site. Excessively long comments may be moderated as well. Bloomberg cannot facilitate requests to remove comments or explain individual moderation decisions.