Let Lady Gaga, Kim Kardashian, And Millions Of Strangers Tell You How They Feel About The Stock MarketBy Matt Levine
If you work at a big bank you probably don’t have access to much in the way of social media at work, which makes sense, since you would probably use Facebook mostly to insider trade and Twitter to prank the Compton sheriff’s department or tweet fake elevator conversations.
But now you have a better excuse for condensing your market research into 140-character:
A hedge fund that uses Twitter data to drive its trading strategy returned 1.85% in its first month of trading, according to an investor in the fund, in the first sign that social media data can be used successfully to enhance electronic trading techniques.
Derwent Capital, which finished its first month of trading at the end of July, beat the S&P 500 which fell 2.2% in July, while the average hedge fund made 0.76%, according to Hedge Fund Research.
The fund, which declined to comment, uses sentiment data mined from millions of Twitter messages, or ‘tweets’, to predict market movements. The strategy is based on research published by the University of Manchester and Indiana University in October which demonstrated that the number of emotional words on Twitter could be used to predict daily moves in the Dow Jones Industrial Average.
The Twitter strategy is based on a paper (pdf) by three computer scientists that found that indicators of “calmness” in tweets predicted movements in the Dow 3 – 4 days later. It’s one of several recent papers tracking public mood and the stock markets – another found that business articles in newspapers all use the same wording in the run-up to the bursting of stock market bubbles.
We know at least one stat arb fund that was looking into using Twitter as a signal in their trading model well before this paper came out. But they didn’t announce it publicly. Relying on the calmness, or lack thereof, of a million Justin Bieber fans to time your stock purchases seems like the sort of strategy whose excess returns will pretty quickly dissipate. If Derwent is buying stocks 3 days before they go up because Twitter tells them to, and their results are robust and announced in the press and their method is described in published papers, then it seems likely that others will pile in until Twitter calmness no longer provides a useful signal.
On a related note, we just saw an interview that Ed Thorp – who invented, among other things, card counting, convertible arbitrage, and maybe the Black-Scholes formula, so he’s worth listening to – gave to The Journal of Investment Consulting earlier this year (recently posted online, via Infectious Greed):
Meir Statman: I wonder if you would speak about the difference between the reward system of the academic world and the world of money management. I don’t know if there’s some wistfulness that I hear in your voice about the fact that you made money but never received the recognition that should have accompanied your intellectual accomplishments.
Edward Thorp: I realized in retrospect that there was no chance I was going to get any recognition for an options formula because I was not part of the economic academic community, and that was extremely important. … To me, the thing to do seemed to be to protect my investors and their interests and do theh best I could for them and just stay ahead in research as well as I could. So that’s what I focused on. If you don’t publish, you’re not going to get credit.
Geoff Gerber: But you were able to make money for your clients?
Edward Thorp: Yes. There was sort of a branch point. If I had been brought up in the traditional economic academic community, then I think that I would have gone the “get credit” route and probably succeeded in doing that. But I didn’t come up that way, so I went toward practical application.
Which worked out okay for him.
Twitter Hedge Fund Beats Market [Financial News]