Submission + - Inside Google's Black Box
Pcol writes: "Google's "ranking algorithm" — the formulas that decide which Web pages best answer each user's question is crucial part of Google's inner sanctum, a department called "search quality" that the company treats like a state secret. Google recently allowed a reporter from the New York Times to spend a day with Google Fellow Amit Singhal and his search-quality team who explained how every week they make about a half-dozen major and minor changes to the vast nest of mathematical formulas that power the search engine. Mr. Singhal has developed a far more elaborate system for ranking pages than PageRank. The system, involving more than 200 types of information, are what Google calls "signals." 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. Increasingly, Google is using signals that come from its history of what individual users have searched for in the past, in order to offer results that reflect each person's interests. "People still think that Google is the gold standard of search," says John Battelle, author of "The Search," a book about Google. "Their secret sauce is how these guys are doing it all in aggregate. There are 1,000 little tunings they do.""