Apparently following and measuring internet chatter may have predictive abilities in the movement of stocks according to a post by The Daily Stat
Researchers were able to do 7.9% better than the S&P 500 stock index by (virtually) investing in brands that generate high volumes of online chatter. In studying four years' worth of product reviews of 15 brands, Seshadri Tirunillai of the University of Houston and Gerard J. Tellis of USC's Marshall School found that sheer volume of reviews and negative chatter have a strong predictive relationship with stock returns; positive chatter and five-star ratings have no predictive value. The stock-return effects are rapid but not immediate: They follow bursts of user-generated comments by a few days, the researchers say.
Do you think this is a legitimate strategy and would you try it? Perhaps a new arsenal for technical analysts?
I've already heard of hedge funds using algorithms that track media (blogs, news outlets, etc).
Obviously, Google would be at a huge advantage if say for example they started to say track Goldman Sachs employee inquires. I'm pretty sure the boys in Palo Alto could easily put together a list of potential deals based off of certain inquiries.
You could make macro predictions of future economic cycles and consumer preferences based off of current data. I remember reading about how Bass sent guys to interview germans on their feelings about bailing out the greeks, and using that information to bet that they would have a more limited willingness to help in the future. It seems reasonable to me that you could potentially get a lot more subtle than that and make predictions about expected growth in specific sectors based off of unconscious trends and their logical psychological impacts on societies purchasing habits. Take for instance the increase in impregnation and sexual drives when people think there will be wars involving them in the near future.
Presently, the firm may not have the expertise. However, they have a VC fund, which I think is a little more fitting.
Problem is this works on paper but if you look at the stocks that get the chatter it's usually because they're already in the process of making big moves, and there's really no time in real life to build up a position on those stocks, but when you can place an order in a simulation for 2% of the company and have it fill in 1 second it's pretty damn easy to shit on the market.
I thought google was setting up a hf.
Hedgefund are already taking advantage of 'big data'
:) its cool stuff
most of them suck
eeeeeeffffffff
Maiores consequatur et nobis reprehenderit. Est ut occaecati reprehenderit praesentium vero. Delectus asperiores ea voluptatem animi. A reiciendis vero et animi.
Nam quia odio ipsa sunt. Saepe nisi iste amet enim sit qui vel. Deserunt eius accusantium est aut impedit facilis. Impedit animi qui maxime dolores possimus autem corporis. Aliquam autem doloribus et.
See All Comments - 100% Free
WSO depends on everyone being able to pitch in when they know something. Unlock with your email and get bonus: 6 financial modeling lessons free ($199 value)
or Unlock with your social account...