Hedge Funds Using Twitter Traffic – Can You Exploit This?

by Darwin on December 23, 2010

There’s been a lot of chatter lately about sophisticated software that uses Twitter and other social networking chatter about particular stocks to predict future moves.  This takes the Efficient Market Theory to a whole new level since usually news becomes public during the course of a press release, a posting to a website or a conference call.  As news, insider information or speculation hits Twitter accounts instantaneously, as opposed to over the course of minutes or hours through conventional means, there does appear to be a means to exploit this advanced notice of tradable information.  However, just how useful is data from a bunch of Twitter accounts?  That’s the question that has a high enough level of confidence to garner support from a software company selling its Twitter analysis algorithm, as well as the birth of a hedge fund focusing on the chatter.

Twitter Investing Outfits

There’s been a lot on CNBC about this Twitter investing story today.  First, there’s a London Hedge Fund, Derwent Capital Markets,which has already attracted millions to start up.  They claim to anticipate returns of 15-20% returns using data gleamed from Twitter (story).  Next, there’s an article today on using numbers, data and traffic from Twitter to do essentially the same thing – but this is geared toward traders and individual investors.

Can You Exploit This?

Hypothetically, it wouldn’t be insurmountable to try to exploit firms that rely on Twitter chatter to trade.  On one hand, this kind of reminds me of when the news broke about the MIT students that learned how to count cards and took the casinos for millions, people rushed out, bought card-counting books, and probably gave the casinos millions more that year than normal because they didn’t really know what they were doing.  Could we see the same here?  Possibly, there may be some winners and many losers.  Here’s a way this could be exploited by even a typical retail investor with relatively little up-front cost:

  • Set up hundreds of twitter accounts.
  • Make a few tweets from each to ensure they’re viewed as “legit” and not flagged as spam or disabled.
  • Wait until the day before options expiry.
  • Pick up a ton of at-the-money call options (see how stock options work).
  • Blast out hundreds of tweets on the underlying symbol.
  • If the algorithms pick it up and shares start moving, you sell when you’re happy with the return.
  • This exercise could probably even be outsourced to an Indian or Chinese firm for a few bucks.

Is this securities fraud? I don’t know, possibly, you’d need to talk to a securities lawyer about that – so don’t take this as advice to do so.  The reason I even posted this is I don’t know that using Twitter with messages like “I like company X” and “company X is looking good!” is the same thing as the old phone and internet pump and dump schemes – but those were prosecuted, so maybe taking it to this extreme would subject one to scrutiny.  But it’s a fine line.  How could it be proven what your intention was?  You have no assurance this would even work.  And if you didn’t have other retail investors following your accounts, how could it be proven they were manipulated into buying shares while you sold?  It sure would make for an interesting case law study.  It’s just twitter and you’re sharing an opinion, right?  Either way, tread lightly, but it’s a thought.  Chances are, someone else is already conjuring up a scheme like this, which if anything, will render the current algorithms useless as they try to parse out the scammers from legit Tweeters.

Thoughts?

Can Twitter Be Used for Stock Market Returns?

Would This Constitute Securities Fraud?

You're Not Following Darwin's RSS? Check out Why You Have to Subscribe to Darwin's Finance!

If you enjoyed this post, you can get free updates through RSS Feed or via Email whenever a new post is published. Rest assured that you can unsubscribe at any time via the automated system and your information will not be sold, archived or utilized for any other "nefarious" purposes.

{ 5 comments… read them below or add one }

1 Investor Junkie December 23, 2010 at 7:26 pm

I’ve thought about this idea before.. I think eventually the market would become “efficient”again as everyone is also doing this.

Though the signal to noise ratio on Twitter is too high IMHO. I think 90% of my followers are bots are people who want to be followed. They could care what I tweet.

[Reply]

2 Evan December 23, 2010 at 8:33 pm

This sounds a lot like when the everyday investor learned out to use yahoo message boards….did anyone get in trouble for that?

[Reply]

3 Broke Professional December 27, 2010 at 10:36 pm

Just another example of why people who are not in the know should probably just invest in no-load (Bogglehead type) mutual funds. In my opinion, we will never have a fair chance….even most people in finance/government probably do not understand. It’s like that scene in the original Wall Street when Gekko asks: “why do you think most of the top managers in the S&P 500 can’t beat the market?” Interesting idea though.

[Reply]

4 Roger Wohlner January 10, 2011 at 7:53 pm

Interesting post, I read something else about this. As an advisor who is SEC registered, I know that I try never to give anything that even resembles investment advice on my blog, Twitter, or elsewhere on social media. Even so, I’m dubious about the reliability of the information that could be gleaned on Twitter. I would also suspect that information could be manipulated based on whether the generator of the information was long or short the stock. Perhaps I’m wrong, but I’m not jumping in here on behalf of my clients.

[Reply]

5 Udayan Chattopadhyay May 25, 2011 at 8:26 am

If it doesn’t work, you are naive. If it does work, then it is no different than a pump and dump scheme and is securities fraud according to the SEC. So let’s not waste any more time on this.

[Reply]

Leave a Comment

You can use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>