Stock market predictions with Twitter

Posted to Statistics  |  Tags: ,  |  Nathan Yau

Apparently moods on Twitter can be used to predict the ups and downs of the stock market, according to work from Johan Bollen and Huina Mao of Indiana University-Bloomington: “Measuring how calm the Twitterverse is on a given day can foretell the direction of changes to the Dow Jones Industrial Average three days later with an accuracy of 86.7 percent.”

I can’t wait until Twitter is used to predict when I want to eat and sleep, and my robot can cook me gourmet meals and provide turn down service accordingly. And it better be accurate to the minute. Anything less is failure.

4 Comments

  • Did you hear the story of the Hong Kong-based brokerage that said the stock market this year will be “up and down” because this is the Chinese Year of the Rabbit?
    http://www.npr.org/2011/01/31/133356396/a-hoppy-new-year-for-hong-kong-stocks

  • i’ve been an online stock trader before, and we used twitter as medium for a game of predicting the daily direction of a stock of choice (e.g., keying in “PFE up, GOOG down, WMT up”). i believe there were quite a number of players there. then, the game host (a stocks blogging service) tallies up our scores weekly and monthly. it’s kind of fun, really

  • The most amazing thing about this article is that people are still talking about it. A quick read reveals the authors are idiots.

    • sorry, that was an uncharitable characterization. To be more precise, the statistical methodology is questionable at best. The authors are testing multiple hypotheses without adjusting for family-wise error rate, and thus the statistical significance of their results is highly questionable.

Favorites

How We Spend Our Money, a Breakdown

We know spending changes when you have more money. Here’s by how much.

The Best Data Visualization Projects of 2014

It’s always tough to pick my favorite visualization projects. Nevertheless, I gave it a go.

A Day in the Life of Americans

I wanted to see how daily patterns emerge at the individual level and how a person’s entire day plays out. So I simulated 1,000 of them.

How You Will Die

So far we’ve seen when you will die and how other people tend to die. Now let’s put the two together to see how and when you will die, given your sex, race, and age.