New research announced by Google describes a new way to improve how web pages will be ranked. This algorithm claims significant improvements to deep neural network algorithms that calculate relevance.
The new algorithm includes a method of ranking web pages called, Groupwise Scoring Functions.
Does Google Use Published Algorithms?
Google has mentioned in the past that “Google research papers, in general, shouldn’t be assumed to be something that is happening in search.” Google rarely tells which algorithms described in patents or research papers are in use. It’s the same for this algorithm.
Why this Algorithm is Important
Google starts the research paper by noting that machine learning algorithms provide values to web pages individually, each web page in isolation from other web pages. Then the algorithms score the web pages in competition with the other web pages to understand which web page is most relevant.
Is this Algorithm related to the March 2019 Core Update?
According to this research, Google is focusing on understanding search queries and learning what web pages are about. It has recently introduced a broad core update that is reported to be among the biggest in years. We don’t know whether this algorithm is a part of that change or not, because Google rarely discusses specific algorithms.
This is the way the research paper discusses the new algorithm:
The majority of the existing learning-to-rank algorithms model such as relativity at the loss level using pairwise or listwise loss functions. However, they are restricted to pointwise scoring functions, i.e., the relevance score of a document is computed based on the document itself, regardless of the other documents in the list.
…the relevance score of a document to a query is computed independently of the other documents in the list. This setting could be less rational for ranking problems for multiple reasons.
The New Algorithm Works
When a research paper states significant improvements coupled to minimal cost, then these kinds of algorithms have a higher likelihood of being included in Google’s algorithms.
The researchers concluded that this new method makes Deep Neural Network and tree-based models more effective.
How this Can Push Your SEO
Ranking in Google is increasingly less related to traditional ranking components. Twenty-year-old ranking factors like anchor text, heading tags, and links are less important.
This research paper discusses how considering commonalities between relevant pages may provide clues to what users want. Even if Google isn’t using this algorithm to rank web pages, the concept is still important to you.
Knowing what users want can help you better understand the user’s information needs and to create web pages that better meet those needs. And that may increase your ability to rank.
Read the report: Learning Groupwise Scoring Functions Using Deep Neural Networks
Google Updates Travel Searches to Help Find Budget-Friendly Options
Google: Don’t Worry About Malicious Backlinks, We Ignore Them
Google: Changing Image URLs Will Affect Rankings in Image Search