Social Media Collective Wisdom Predicts Tech Stock Performance

"What Keynes recognized is that ... investors are concerned not only just with what the average investor thinks but with what the average investor thinks the average investor thinks. And the truth is: Why stop there? Maybe what you need to think about is what the average person thinks the average person thinks the average person’s view is."
-- James Surowiecki : The Wisdom of Crowds, p484.


At MarketPsych Data we've begun to analyze longer term predictive patterns in our social media data.  We've created indices that aggregate the perceptions of investors about companies and stocks expressed in their conversations, discussions, and (of course) rants in social media such as Facebook, Twitter, chat rooms, and blogs.

The index I'd like to discuss today is called "Innovation Perceptions" and it is self-explanatory.  Investors' perceptions of a company's innovativeness are measured using our proprietary linguistic analysis tools and then smoothed over time.  You can see the innovation perceptions of eight randomly selected (my personal brainstorm) tech stocks for the past decade (mid-1998 through Feb 1, 2011).  It's pretty fascinating on its own:

What's even better is when you run our backtesting software (developed for our hegde fund) on the data, and we see that the top one standard deviation of high-innovation tech stocks have a 10bps (0.10%) daily = 30+% annual outperformance of the rest of the tech stocks in our sample over 37,000+ stock-days.  Interestingly, the average tech stock outperforms the S&P500 by 10 bps daily since 1998:

In behavioral finance terms, this may be a sign of investor underreaction to the level of perceived innovation at a company.

The next step is to expand the sample size.  We'll continue to examine this effect and keep you posted.

Happy Investing!
Richard  Peterson M.D.
+1.310.573.8523
http://www.marketpsychdata.com/