« Home | Yahoo! Time Capsule: An Electronic Anthropology Pr... » | Play Hundreds of Nintendo Games in Your Browser » | The Rise of Specialized Social Networks (Plus a Re... » | Streamripping: A Guide to Recording Streaming MP3s » | It's Official: Google Buys YouTube for $1.65 Billion » | adaptiveblue: Creating a Smarter Browser » | Clipboard Security Hole in Internet Explorer: Atta... » | Google Blog Hacked Via Blogger Security Bug » | Songbird: The Firefox of Music Players? » | About Digital Alchemy »

Tuesday, October 10, 2006

Does Stock Spam Work?


Leonard Richardson over at Crummy.com has put together a Stock Spam Effectiveness Monitor that mashes together stock charts from Yahoo! Finance and stock spam. The amount of spam is indicated by the red lines. While for many stocks, the spam is sent before the market opens so it's hard to connect it to any movement in the stock, there are some where spam can be correlated to movement in the stock that is being touted.

An academic study on stock spam found
that stocks experience a significantly positive return on days when they are heavily touted via spam, and on the day preceding such touting. Volume of trading also responds positively and significantly to heavy touting. Indeed, on a day when no tout has been detected in our database, the likelihood of a touted stock being the most actively traded stock that day is only 6%. On the other hand, on days when there is touting activity, the probability of a touted stock being the single most actively traded stock is 81%. Returns in the days following touting are significantly negative.
Richardson's been doing this for two years now so there is a wealth of data to crunch. There's also a handy list of spam-contaminated stocks to be on the lookout for.

(via Monkey Bites)

Related Posts:
The Rise of Specialized Social Networks (Plus a Review of SocialPicks)
SETI@Home for Stocks
How to Invert Data: Excel Tutorial Using Google Stock Prices

Labels:

Send to a Friend!       Subscribe!      

    Stumble Upon Toolbar    

Comment Archive

Reader Comments:


I think the problem with the analysis is that stock spam isn't going to have an instant impact on the volume of a stock nor do we know the scope of the spam being committed. If something is being touted on a weekend, I bet volume on a Monday is much more likely to be higher, but during the day who knows when someone might read that email. There would also be a different effect from someone sending out 10 million emails vs maybe 100,000 and how targeted those emails are.

Why anyone would buy a stock that trades on the pink sheets is beyond me, but if someone gets burned by trying to flip in and out of a penny stock, it's hard for me to have too much sympathy even if they are a victim.



Davis,

You make a good point. There are ways to account for the lag between spam and effect, but an eyeball analysis really isn't too accurate. Then there's the issue of the differential impact of spam on investor action that you mentioned (actually buying the stock). Some investors check their email obsessively while others only sporadically so the impact is going to be diffused over a matter of, say, hours (it needs to be a short enough time frame for there to actually be enough of an artificially high demand to move the stock up).

Still, the paper I linked to above offers some convincing evidence that stock spam works.

Of course, spam works because it relies somewhat on the law of large numbers. Throw enough out there, and some people are going to respond to it within the right time frame.


Previous Posts

« Home