Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Google Search Terms Can Predict the Stock Market

blogs.smithsonianmag.com

Post reply on HN
Print view View original

21–30 of 57 posts

Re: Google Search Terms Can Predict the Stock Market

#21

Post by ISL »

PaulHoule wrote: post #9
rm999 wrote: post #3

Cool paper, but the fact that a silly keyword like 'color' is so significant without an author explanation makes me question their results. I really wish they dug deeper and explained unintuitive results like that. There may be a bug in their experiment. Also, why would they use the Dow Jones Industrial Average? It is a ridiculously bad average of stock market performance for many reasons. This planet money podcast g…

Lots of people use the Dow precisely because it is a bad indicator. If they don't like the conclusion they get with something better, like the W5000 or the S&P500, they can try it again with the Dow for a "second opinion." The whole methodology is a joke anyway. If you evaluate a huge number of search terms, some of them are going do better than others. So terms that might mean something ("debt") get mixed up with te…

Relevant technical terms: 'look-elsewhere effect' and 'false alarm rate'

http://en.wikipedia.org/wiki/Look-elsewhere_effect http://en.wikipedia.org/wiki/False_positive_rate

There are more similar considerations. Statisticians have been very busy for the last century or so.

Re: Google Search Terms Can Predict the Stock Market

#22

Post by bdg »

This concept is very similar to the "Twitter can predict the stock market" from a long time back: http://www.wired.com/wiredscience/2010/10/twitter-crystal-ba...

See also, a collection of other related links (helpful if you want to try your hand at making something like this): https://news.ycombinator.com/item?id=2055857

Re: Google Search Terms Can Predict the Stock Market

#26

Post by nobbis »

rm999 wrote: post #3

Cool paper, but the fact that a silly keyword like 'color' is so significant without an author explanation makes me question their results. I really wish they dug deeper and explained unintuitive results like that. There may be a bug in their experiment. Also, why would they use the Dow Jones Industrial Average? It is a ridiculously bad average of stock market performance for many reasons. This planet money podcast g…

"Color" is slang for opinion or prediction in finance, e.g. a trader could ask an analyst for some "color" on a company before he goes and buys its stock.

Re: Google Search Terms Can Predict the Stock Market

#27

Post by someben »

hammock wrote: post #10
dawilster wrote: post #2

I was thinking of something very similar the other day but in regards to bitcoins. They are very volatile at this stage and whenever they're in the public eye they either seem to increase or decrease in value. Perhaps somebody could perform a study as to a relation between the volume of bitcoin related search terms and it's market value.

As soon as someone figures out bitcoin derivatives (e.g. options), you'll be able to buy or sell the volatility. More broadly, such a development may also stabilize those price fluctuations.

What is your source for the ole' "derivatives reduce volatility in the spot market" assumption?

Re: Google Search Terms Can Predict the Stock Market

#28

Post by someben »

bdg wrote: post #22

This concept is very similar to the "Twitter can predict the stock market" from a long time back: http://www.wired.com/wiredscience/2010/10/twitter-crystal-ba... See also, a collection of other related links (helpful if you want to try your hand at making something like this): https://news.ycombinator.com/item?id=2055857

That Twitter paper has been torn to shreds over the last couple of years. Here is me snarking: http://blog.someben.com/2011/05/sour-grapes-seven-reasons-wh...

Re: Google Search Terms Can Predict the Stock Market

#29

Post by someben »

PaulHoule wrote: post #9
rm999 wrote: post #3

Cool paper, but the fact that a silly keyword like 'color' is so significant without an author explanation makes me question their results. I really wish they dug deeper and explained unintuitive results like that. There may be a bug in their experiment. Also, why would they use the Dow Jones Industrial Average? It is a ridiculously bad average of stock market performance for many reasons. This planet money podcast g…

Lots of people use the Dow precisely because it is a bad indicator. If they don't like the conclusion they get with something better, like the W5000 or the S&P500, they can try it again with the Dow for a "second opinion." The whole methodology is a joke anyway. If you evaluate a huge number of search terms, some of them are going do better than others. So terms that might mean something ("debt") get mixed up with te…

Logistic regression and other parametric, non-regularized linear learners tend to do poorly with NLP forecasting -type modeling. (They usually overfit.)

Re: Google Search Terms Can Predict the Stock Market

#30

Post by tgrass »

Symmetry wrote: post #20
tgrass wrote: post #15

Earlier quoted context omitted.

An economist and his friend are walking down the street when the friend sees a ten dollar bill on the sidewalk. “Look,” he says, “it’s a ten dollar bill”. “Nonsense,” says the economist. “If that was a ten dollar bill, someone would have picked it up by now.”

I'm (and economists) aren't saying that there are never $10 bills on the sidewalk, just that they don't stay there for long after someone notices them. Stock prices went down on the weekends for decades before someone noticed. But once it was noticed it stopped pretty quickly.

Understood. No offense, just being goofy.
Post reply on HN