Google as a Recommendation System

I’ll be presenting later today at the Search Engine Strategies at San Jose, and the session I’m talking at involves Search Algorithms and the patents and whitepapers that describe them.

My presentation will focus upon Google as a recommendation system. With some fortunate timing, Google had a new patent granted today, which describes how Google could be used as a recommendation system when it comes to ecommerce.

Interface and system for providing persistent contextual relevance for commerce activities in a networked environment

Invented by Donald R. Turnbull and Hinrich Schuetze
Assigned to Google
United States Patent 7,089,237
Granted August 8, 2006
Filed: January 26, 2001


A search and recommendation system employs the preferences and profiles of individual users and groups within a community of users, as well as information derived from categorically organized content pointers, to augment electronic commerce related searches, re-rank search results, and provide recommendations for commerce related objects based on an initial subject-matter query and an interaction history of a user.

The search and recommendation system operates in the context of a content pointer manager, which stores individual users’ content pointers (some of which may be published or shared for group use) on a centralized content pointer database connected to a network.

The shared content pointer manager is implemented as a distributed program, portions of which operate on users’ terminals and other portions of which operate on the centralized content pointer database.

A user’s content pointers are organized in accordance with a local topical categorical hierarchy. The hierarchical organization is used to define a relevance context within which returned objects are evaluated and ordered.

The original filing was made by employees of Groupfire, which Google acquired in September of 2001.

4 thoughts on “Google as a Recommendation System”

  1. Thanks, Sébastien

    I’ll probably be posting a version of the presentation sometime over the next few days – translating it from bullet points to prose.

    I had a number of folks come up and quickly introduce themselves to me and provide some positive comments and feedback on the presentation, which was really nice. Thanks to those who did.

    Along with the presentations by Rand and Jon, I’m really happy with the way that our presentation on Search Engine Algorithms came out.

  2. Hi Adam,

    Yes, as in taking an original set of search results that appeared in response to a query and moving some of the results up and others down. I’ve written about a number of possible re-ranking processes that the search engines might use here before. A couple of my posts focused exclusively on identifying re-ranking processes (it’s probably time for another one).


    20 Ways Search Engines May Rerank Search Results


    20 More Ways that Search Engines May Rerank Search Results

Comments are closed.