Sign in with
Sign up | Sign in

Behind the Scenes Look at How Google Improves Search

By - Source: Google | B 11 comments

Peering behind the curtain at Mountain View.

Google does a lot of things. It seems it to grow a new hand to stick in yet another pot every six months or so. However, the company's first product (and arguably its most important one), goes by the name of Google Search. According to Google, more than 1000 years of labor have gone into building the Google Search algorithm. The company is constantly tweaking this but we don't really get a lot of insight into that process.

This week, Google is offering us a glimpse of how search works. The company has, for the first time, posted an uncut video documenting one of its "Quality Launch Review" meetings. Google holds the meeting on Thursdays to discuss possible algorithmic improvements and make decisions about what to launch. This meeting in particular covered improving spelling suggestions for searches with more than 10 words. It impacts just 0.1 percent of Google's traffic but even for small details like this one, aspects such as relevance, spam, latency, cost, and language impact are taken into account.

Check out the video below for a taste of what it's like to be a part of Google's Search team:

Search Quality Meeting: Spelling for Long Queries

Follow @JaneMcEntegart on Twitter!             

Display 11 Comments.
This thread is closed for comments
Top Comments
  • 11 Hide
    dimar , March 15, 2012 1:34 AM
    Many times I try to find a review for something, the search finds those sites that pretend to have reviews, but they actually try to sell the stuff.

    Could Google find a way to deal with those fake review sites?
Other Comments
  • 7 Hide
    robochump , March 15, 2012 12:18 AM
    Coulda swore the secret was a Foxconn warehouse full of pre-teen Chinese kids slaving away to answer Google search requests. Disappointed....
  • 8 Hide
    bison88 , March 15, 2012 1:06 AM
    I think it's more that they've cached everything you've ever done and then some since their beginning, across all services, and then cross referenced all that information creating a unique yet robust algorithm that is specifically targeted based off the general category you fall under as a Netizen.

    Google - There's an Algorithm for that...
  • 11 Hide
    dimar , March 15, 2012 1:34 AM
    Many times I try to find a review for something, the search finds those sites that pretend to have reviews, but they actually try to sell the stuff.

    Could Google find a way to deal with those fake review sites?
  • 4 Hide
    Anonymous , March 15, 2012 1:56 AM
    Proof that Google had as mind-numbing meetings as any company. 10 people talking and 30 people sitting being useless.
  • 7 Hide
    zachusaman , March 15, 2012 2:23 AM
    robochumpCoulda swore the secret was a Foxconn warehouse full of pre-teen Chinese kids slaving away to answer Google search requests. Disappointed....

    your thinking of isearch
  • 1 Hide
    Anonymous , March 15, 2012 2:54 AM
    which algorithm or technique google uses for its search?
  • 3 Hide
    archange , March 15, 2012 5:53 AM
    Google staff on Macs???

    That alone could make a man lose faith... One would half expect a bunch of Chromiums... :) 
  • 1 Hide
    guru_urug , March 15, 2012 8:40 AM
    Makes me feel proud to be an Indian :) 
  • -1 Hide
    iamtheking123 , March 15, 2012 10:15 AM
    It's .1% of queries and they're wasting the time of dozens of people trying to fix it? I'd have shelved it off the bat with a memo saying "not statistically significant enough to warrant resource allocation towards solution".
  • 2 Hide
    Hypertraxx , March 15, 2012 12:56 PM
    Very interesting meeting :) .
  • 2 Hide
    rosen380 , March 15, 2012 2:28 PM
    iamtheking123It's .1% of queries and they're wasting the time of dozens of people trying to fix it? I'd have shelved it off the bat with a memo saying "not statistically significant enough to warrant resource allocation towards solution".


    Well, if they have 1000+ years of labor into the algorithm, then 0.1% of the searches deserve 8760+ man-hours of attention...