Let me fix the title: <i>Hedge fund claims to use Twitter to predict stock market in an effort to attract attention from investors.</i><p>Other variations on this theme that I've encountered:<p><i>Hedge fund uses all-Apple architecture to gain competitive advantage.</i> (Translation: a platform-independent runtime [1] on top of XServe + imac/mac pros for workstations. )<p><i>Hedge fund uses NoSQL solutions to predict the market, minimize risk.</i> (Translation: flat files for quote-level data, same as everyone else [2].)<p>I'm sure they throw twitter sentiment into their machine learning program as one piece of data. The learning system might even give it a non-constant coefficient. But I'd be really surprised if it plays a major role.<p>[1] I won't name the system, but it's something along the lines of (and might even be one of) the JVM, CLR or Smalltalk image.<p>[2] I'm being unkind - some banks use ADABAS and other such systems from the 70's.
Notice the caption in the picture of the metro article
"A broker looks on in horror as the news that Justin Bieber has a mild cold brings about a global economic collapse (AP)"<p>The article you really want is the one linked to
<a href="http://thenextweb.com/uk/2010/12/16/investment-fund-set-to-use-twitter-to-judge-emotion-in-the-market/" rel="nofollow">http://thenextweb.com/uk/2010/12/16/investment-fund-set-to-u...</a><p>I'm still pretty skeptical of this concept in general. That the fund doing this is a "family-owned investment boutique" sets off even more flags for me. I think this is just marketing for their asset management business.
Let me be the first to predict this will fail miserably. How much money and time have people wasted the past 100 years on "systems" to beat the stock market?.<p>Need proof that there is <i>no</i> system to predict the market? There's no person on the earth that owns everything. Theoretically, if someone could predict the market even somewhat effectively, he wouldn't just make lots of money, he'd make <i>ALL</i> of it.