Bing: Machine Learning Leads To More Human Like Ranking In Search

Dec 12, 2018 - 8:04 am 1 by
Filed Under Bing Search

Bing Machine Learning Human Ranking

Bing's Frédéric Dubut said on Twitter and in a quote at Search Engine Journal that machine learning helps with scaling generalizing, which is how humans would manually rank search results. So using machine learning to rank search results is a good way to get Bing's search results to look more human tailored and thus better.

Frédéric Dubut said:

A major goal of our Bing ranking team is to build an algorithm that would rank documents in the same order as humans would as they are following the guidelines. You can only do so at the scale of the web by generalizing your ranking algorithm as much as possible.

It turns out that modern machine learning is very good at generalizing, so you can expect our core ranking algorithm to get closer to that ideal Intelligent Search product view that we hold internally and which we try to capture in our own guidelines.

I am sure a ton of you will love to chew on this quote for some time.

Forum discussion at Twitter.

 

Popular Categories

The Pulse of the search community

Search Video Recaps

 
Video Details More Videos Subscribe to Videos

Most Recent Articles

Search Forum Recap

Daily Search Forum Recap: March 31, 2025

Mar 31, 2025 - 10:00 am
Google Updates

Google March 2025 Core Update Impact Multiple Poll Results

Mar 31, 2025 - 7:51 am
Google News

Google To Pay $100 Million To Settle Old Ad Lawsuit On Clicks Outside Geo Target

Mar 31, 2025 - 7:41 am
Google Ads

Google To Allow Double Serving Ads In Different Ad Locations On Same Page

Mar 31, 2025 - 7:31 am
Google Search Engine Optimization

Google News Fully Transitioned To Automatically Generated Publication Pages

Mar 31, 2025 - 7:21 am
Google Maps

Google Business Profiles Bug Resurfacing Old Fake Removed Reviews

Mar 31, 2025 - 7:11 am
Previous Story: Google News Publishers Continue To Have Indexing/Ranking Issues