Inside Google's Black Box

A bit slow to mention this article that came out while I was at SMX, but it is worth mentioning. The NYT ran an article about Google's relevancy algorithms titled Google Keeps Tweaking Its Search Engine, which talks about how Google reacts to relevancy problems. The article should be required reading for all SEOs and search lovers. Rand offered a great overview of the article, highlighting that Google noticed their age weighting was too heavy when Google Finance was not ranking where they thought it should, Google changes their matching algorithms to place more weight on phrase matching for some queries, and that Google has created a query deserves freshness (QDF) algorithm which determines how well to mix in new and old results.

Matt Cutts, who was quoted in the New York Times article, also commented on it on his blog, confirming that

The search-quality team makes about a half-dozen major and minor changes a week to the vast nest of mathematical formulas that power the search engine.

Google is not the only search engine heavily focused on the human elements of search. In one of Tim Mayer's slides he showed a Yahoo! search result which said something along the lines of Yahoo! employees see bad results? Report spam.

The two things Google does more aggressively than the other engines are:

• Drive traffic: they send Wikipedia 12x as much traffic as Yahoo! does

• Impart intent upon the publisher

Build as many quality signals as you can, such that if they ever impart intent on your sites you can get away with more dirty stuff than a spammy sounding unbranded site can.