Page Rank Technique
Page rank is a machine learning technique that increases the effectiveness of search engines and improve their efficiency. It is used to measure the importance of a page and to prioritize pages returned from a traditional search engine using the known keyword search. The effectiveness of this technique has been shown by the success of the Google search engine. The technique takes advantage of big data by performing an analysis of all links on Web pages in the Internet. The Page Rank value for a Web page is calculated based on the number of Web pages that point to it. In other words it is really a measure based on the number of backlinks to a page while a backlink is a link pointing to a Web page rather than pointing out from a Web page.
The Page Rank technique is different from other approaches that investigate links. It is important to understand that it does not count all links the same. The measure is therefore not just a count of the number of backlinks because a weighting is used to provide more importance to backlinks coming from very important Web pages. In addition all values are normalized by the number of links in the page. The original technique was published in 1999 by L. Page et al. as a technical report at Stanford and is available here. In short the technique is driven by probability of landing on one page or another. That means of being at a certain node. The probability can be interpreted as the higher the chance the more important the page is. The big data problem is in this context the ‘whole Web of links‘. It is a memory challenge for the whole Web. This means that in order to compute the Page Rank at a given iteration we also need the Page Rank for the iteration before.
Page Rank Details
The following video provides more details: