Google’s Search Gurus Spill Algorithm Beans
Ok, so the New York Times doesn’t exactly get Google’s top algorithm execs to tell us how the search engine calculates search results, but they do get fresh insight as to how Google decides to update it’s technology.
The article includes interviews with Amit Singhal, Matt Cutts and Udi Manber.
Insights include details of Google’s internal system for evaluating search queries, called Debug.
At other times, complaints highlight more complex problems. In 2005, Bill Brougher, a Google product manager, complained that typing the phrase “teak patio Palo Alto” didn’t return a local store called the Teak Patio.
So Mr. Singhal fired up one of Google’s prized and closely guarded internal programs, called Debug, which shows how its computers evaluate each query and each Web page. He discovered that Theteakpatio.com did not show up because Google’s formulas were not giving enough importance to links from other sites about Palo Alto.
Boy, wouldn’t you like to get your hands on that little beauty?
Also, for the longest time, we’ve known that Google uses more than 100 variables in its algorithm. Since search has become more complex, that number has now been updated.
Mr. Singhal has developed a far more elaborate system for ranking pages, which involves more than 200 types of information, or what Google calls “signals.” PageRank is but one signal. Some signals are on Web pages — like words, links, images and so on. Some are drawn from the history of how pages have changed over time. Some signals are data patterns uncovered in the trillions of searches that Google has handled over the years.
What caught your attention?