back to article 'Big data' predicts stock movements, boffins claim

Researchers from the Warwick University's business school reckon they can predict the next crash, by watching Google searches and Wikipedia. The supposed power of Google as a predictive tool has been popular in academia ever since The Chocolate Factory unveiled Google Flu Trends back in 2008. Its usefulness for real-world …

  1. Charles Manning

    Trends

    1999: Britney Spears debut "Baby One More Time", 6 months later... dotcom crash.

    2007: Britney Spears come-back debut "Gimme More", 6 months later ... GFC.

    Whenever Britney asks for more, bad shit happens.

  2. Anonymous Coward
    Anonymous Coward

    Big Nothing

    Another case of stating the obvious using the scientific buzzwords of the day to make it sound like a major breakthrough...

    Ever seen a shoal of fishes suddenly shifting directions in the water because harry (the drunk herring) "thought he saw something"?

    Well that's the Stock Market for you, it too can be driven by "herd" reactions.

    A crash is a mass panic reaction where an increasing large number of investors rush to sell before everything crashes - and thus generate the very thing they feared.

    In other words twitchy, nervous investors are the material of which crashes are made.

    Doesn't take a genius to guess that periods of unrest and fear about key political/economic issues are going to make investors more fretful and likely to stampede like lemmings into a crash....

    Crashes happen when people are twitchy, People are twitchy when they have major concerns about short term political or economical stability issues, when people have concerns they are more likely to do searches about it.This is all this research is saying - wow impressive!

    Beyond this basic correlation, the research is only relying on hindsight (no verified predictions) and does not provide any critical analysis: search peaks are correlated to crashes, but do they always lead to crashes or do we have instances when this does not happen? When they lead to crashes, is there a clear "trigger level" that could be used as a reliable signal? If so how much warning would that give us? (are we talking days or minutes?)......

    enough grumbling for a monday morning, gotta go join the stampede :-)

  3. John Smith 19 Gold badge
    Unhappy

    Oh great you can now do automated "pump and dump" schemes.

    Yay for that.

    If these results actually mean anything of course.

  4. mr.K

    semantic topics within this corpus

    First, I can not take anybody serious that writes sentences like this: “First, we take a large online corpus, Wikipedia, and use a well-known technique from computational linguistics to identify lists of words constituting semantic topics within this corpus,”

    Second, this is yet another one of these prediction methods that are based upon on the assumption that history repeats itself. It doesn't. Yes, there are a few somewhat repeating patterns out there, quite a few in fact. But this is a system with a memory and the last outcome will carry with and ensure that you never have the same set of conditions required for the same outcome.

    Third, the funny thing about economics is that it is a man made system, but not a fixed system. The rules change constantly, but also the knowledge of the participants (us) which influence how they behave. This leads to the fact that any new method to describe the system will change the system*. Thus if this method actually worked with any certainty then it would seize to do so as soon as people started to believe it can.

    *It is required that the description is known to at least one that will change his behaviour due to it. It is not required that description or method actually has any validity whatsoever.

    1. Michael Wojcik Silver badge

      Re: semantic topics within this corpus

      I can not take anybody serious that writes sentences like this

      Yet I can take you seriously (at least enough so to point out your inability to present an articulate, cogent argument) despite your inability to write "cannot" as a single word, or understand the difference between adjectives and adverbs. Perhaps you should seek professional help for this neurosis.

      Then you can explain what's wrong with the sentence you quoted.

      this is yet another one of these prediction methods that are based upon on the assumption that history repeats itself

      No, it isn't, in any meaningful sense. Obviously if future events are completely random and there is no correlation between past events and future ones, any "prediction method" is doomed. But so is causality, so that's not a very useful assumption.

      the funny thing about economics is that it is a man made system, but not a fixed system

      Is that funny "ha ha" or funny "strange"? What "man made" [sic] systems are "fixed"?

      it would seize to do so

      Homonyms are fun, aren't they?

  5. Anonymous Coward
    Anonymous Coward

    Here's your basic free stock market lesson.

    The moment anyone develops any means of predicting market changes, the market itself changes as a result of that development. Either because everyone starts using the method or because their predictability makes players stay away from that market. Or both.

    Even if the development is kept secret the market also changes because there is now a consistently winning player. which makes other players go elsewhere with their money where the perceived chance to win is higher.

    Somehow one thinks that these stat bods should benefit a lot from a bit of game theory before embarking on their epic efforts.

    Anyway, here's my free stock market tip: stocks will rise and then go down. The difficult part is knowing by how much and when, but that's something nobody really knows.

  6. Fungus Bob
    Trollface

    stock movements, BAH!

    The real question is can this be used to predict BOWEL movements!

  7. Wazzupp

    This might have been relevant when the paper was published... back in August 2013. I don't get why this would be news now. Also, the article avoids one crucial manner this technique can be potentially applied: Hedge betting against S&P members.

POST COMMENT House rules

Not a member of The Register? Create a new account here.

  • Enter your comment

  • Add an icon

Anonymous cowards cannot choose their icon