Hedge Fund Bets $40 Million That Twitter Can Predict The Stock Market
Last October, Johan Bollen and Huina Mao, professors of informatics and computing at Indiana University-Bloomington, caused a stir in the business world when they said Twitter could be used to predict the Dow Jones.
Paul Hawtin, a 28-year-old hedge fund manager, liked the idea so much that he's now dedicating an entire hedge fund to it.
The original paper, entitled "Twitter mood predicts the stock market," investigated whether "collective mood states derived from large-scale Twitter feeds" like OpinionFinder and Google-Profile of Mood States correlated with the value of the Dow Jones Industrial Average. What they found was that their algorithm not only paralleled market changes, it predicted them, with startling 87.6 percent accuracy.
Derwent Capital Markets, a London-based hedge fund set to open for public investment on April 1, has pooled together $40 million to obtain exclusive rights to the Twitter predictor, according to the Indiana Daily Student. Bringing on Bollen and Mao as personal consults, they plan to create a trading model based on the findings of the paper.
Hawtin, co-owner of new hedge fund, ran with the idea after seeing the findings reported on television. "The only risk for us is if Twitter falls away," Hawtin told Bloomberg. "But we believe that it can only get bigger and better."
It's not surprising Professor Bollen decided to join the upstart hedge fund. He's been itching to test his algorithm in the marketplace since the paper's publication, telling Wired in October that it was time to "put some of our money where our mouths are, and try to do this in real time."
Bollen, however, wouldn't call his research groundbreaking. "[P]eople have been using [methods like] this," Bollen told the Indiana Daily Student, citing extensive use of blog and news analysis for similar purposes. "It could... be that we were the only fools that published their results."
https://www.huffingtonpost.com/2011/03/21/hedge-fund-twitter-stock-market_n_838497.html