Amazon Technologies, Inc.

Eric R Vadon

Ronald M Whitman

Benjamin W S Redman

Ron Kohavi

Gautam K Jayaraman

Randal Henne

Brent Russell Smith

Jeffrey Alan Holden

Dennis Lee

Jeffrey D Few

David Hsu

A system and method are disclosed for automatically detecting associations between particular sets of search criteria, such as particular search strings, and particular items. Actions of users of an interactive system, such as a web site, are monitored over time to generate event histories reflective of searches, item selection actions, and possibly other types of user actions. An analysis component collectively analyzes the event histories to automatically identify and quantify associations between specific search strings (or other types of search criteria) and specific items.

Detection of behavior-based associations between search strings and items

An electronic catalog system monitors browsing actions of users to generate user activity data. A data mining component analyzes the user activity data to generate conditional probability data that is presented to users contextually to assist users in selecting items from the electronic catalog. The conditional probability data reflects the frequencies with which users that have performed specific actions, such as viewing a particular item, set of items or web page, or conducting a specific search, have thereafter acquired specific items from the catalog. For example, in one embodiment, when a user selects a first item for viewing in the catalog, the user is notified, for at least one second item, of a frequency with which users who have viewed the first item and then made a purchase have acquired the second item.

Generation and contextual presentation of statistical data reflective of user selections from an electronic catalog

A system and method are disclosed for automatically detecting associations between particular sets of search criteria, such as particular search strings, and particular items. Actions of users of an interactive system, such as a web site, are monitored over time to generate event histories reflective of searches, item selection actions, and possibly other types of user actions. An analysis component collectively analyzes the event histories to automatically identify and quantify associations between specific search strings (or other types of search criteria) and specific items. As part of this process, a decay function reduces the weight given to a post-search item selection event based on intervening events that occur between the search event and the item selection event.

The results of search queries are augmented with behaviorally related items. Items that are behaviorally related to a particular search query may be identified by analyzing the item selection actions of users who submit the particular search query. For example, if a relatively large number of users who submit a particular search query eventually select a particular item (e.g., during subsequent searching or browsing), that item may subsequently be included in the search results for the search query, even though the item may not match the search query.

Augmenting search query results with behaviorally related items

A computer-implemented process identifies useful alternative spellings of search strings submitted to a search engine. The process takes into consideration spelling changes made by users, as detected by programmatically analyzing search string submissions of a population of search engine users. In one embodiment, an assessment of whether a second search string represents a useful alternative spelling of a first search string takes into consideration (1) an edit distance between the first and second search strings, and (2) a likelihood that a user who submits the first search string will thereafter submit the second search string, as determined by monitoring and analyzing actions of users.

Growing community of inventors

Seattle, WA, United States of America

Eric R Vadon