Google starts with a shortlist that contains around thousand results. For that list, Google uses pages that have relevant and topical content for the query. Google then applies many ranking signals to the shorter list. Each document in the list gets scores and numbers. The search results page is the result of that calculation.
Gary Illyes also said that the HTTPS ranking signal would never rearrange the search results. It is only making a difference if two pages have the same score in the other factors.
How does Google prevent spam?
Google uses machine learning models to deal with obvious spam. That allows the Google search quality team to focus on more important work such as hacked spam, scams and other things the machine learning model cannot detect.
As Google’s machine learning models have a lot of years of data, Google is very confident that it works well.
How can you optimise your web pages for Google?
Contact us >>