Amazon Technologies, Inc.

Daniel Bruce Lloyd

Samuel A Minter

Llewellyn James Mason

Soo-Min Pantel

Sungro Yoon

Pranav Varia

Stephen Brent Ivie

Michal Maciej Bryc

Brett E Lounsbury

Jeffrey B Slosberg

Charles Lawrence Scott

Tri M Cao

Vishal M Shanbhag

Joseph Steven Mate

Jesper Mikael Johansson

Ron Kohavi

Himanshu Khurana

Justin Canfield Crites

Opeyemi Akanji

Llewllyn J Mason

Pedrito Uriah Maynard-Zhang

Valentin Radu Munteanu

Brett Patrick Canfield

Seong Jin Park

Zheng Zheng Xing

Michal M Brye

Byung Ju Lee

Arne C Knudson

In Jae Lee

Jack Lightbody

Sneha Rajana

Ben Allison

Xiaonan Zhao

Devices and techniques are generally described for generating personalized search query suggestions. In some examples, a first search query entered by a user into a search field may be determined. A first keyword associated with the first search query may be determined based at least in part on past interactions of the user with content. In various examples, first string data comprising at least a portion of the first search query and the first keyword may be generated. A data store may be searched using the first string data. A first suggested search string associated with the first string data may be determined. In some examples, the first suggested search string may be displayed on a display in association with the search field.

Personalized query suggestion

Disclosed are one or more embodiments for a unique and personalized experience for a user interacting with an electronic commerce site by identifying user-preferred item attributes using supervised machine learning and presenting items to the user in an arrangement that is based on the identified item attributes. A shopping mission is determined according to user interactions with an electronic commerce site. The shopping mission is applied to an attribute prediction model that is trained to detect user-preferred item attributes for items included the item category and estimate a likelihood that an item containing a particular attribute will be purchased or interacted with during the interactions with the electronic commerce site.

User-preferred item attributes

Systems and methods are described for analyzing one or more online shopping missions to determine an estimated stage of a user within the mission and to adjust content for display to the user based on the estimated stage of the user within the mission. The estimated stage of the user within the mission may be determined using a model, such as a machine learning model, that accepts as input signals corresponding to the online shopping mission. The signals may represent user interface interactions and/or other data relating to the user and the mission.

Modification of presented content based on historical data in a shopping mission

Systems and methods are provided for electronic catalog user experience improvements based on extracted item attributes. An example method includes obtaining information identifying items viewed during a user browsing session, the items being included in an electronic catalog, and the electronic catalog being organized according to a hierarchy, with the hierarchy comprising a plurality of categories. Information identifying attributes associated with the identified items is identified, and the attributes are ranked according to attribute relevance score. Items are determined for recommendation to the user based on the ranked attribute relevance scores, with the determined items being selected from items included in the electronic catalog which are also associated with a same category as the identified items.

Automated identification of item attributes relevant to a browsing session

Systems and methods are provided for selecting components to include in portions of a displayable file. Selecting the components may include determining an order of the components for each portion of the displayable file. The components' order for a given portion may be based on a score for each component, where a component's score is based on an estimated value and standard error associated with the component. The component to include in each portion of the displayable file may be selected based at least in part on the determined component order for each portion and a predetermined priority of each portion.

Systems and methods for selecting components for inclusion in portions of a displayable file

A method for permissions based communication in an example includes receiving an electronic communication from a sender to a recipient at a domain server. The electronic communication may include a permission request for permission to send subsequent electronic communications to the recipient. The electronic communication may be analyzed at the domain server to determine whether to deliver the subsequent electronic communications from the sender to the recipient.

Permissions based communication

Techniques for automated targeting of content components to users are described. Content components are selected and exposed through renderable pages for viewing by a population of users. User activity following exposure is tracked in an effort to identify which types of users (as characterized by certain attributes) are likely to act on the content components. The users are segmented into groups according to the attributes and the segments are fed back to aid in selection of content components to be exposed to the users. This enables more granular targeting of the content components to those users who exhibit the attributes that define the specific groups.

Automated targeting of content components

Campaign messages may be prioritized for a given potential recipient by generating one or more learning structures associated with the campaign message. The learning structure(s) is then evaluated relative to the potential recipient to determine potential effectiveness of the campaign messages for the potential recipient. One such learning structure is a decision tree comprising a hierarchy of attributes associated with past recipients of the campaign message. Attributes associated with the potential recipient are then applied to the decision tree to obtain a metric of potential value of the campaign message to the potential recipient.

Personalized campaign planner

The controversiality of an offering in a computer implemented system is computed based on user satisfaction feedback. A controversiality index can be provided to indicate the extent to which the offering is controversial.

Method and system for determining whether an offering is controversial based on user feedback

A decision tree is provided as a machine learning classifier to predict a user attribute, such as a geographical location of a user, based on a network address. More specifically, the decision tree is constructed via machine learning on a set of sample data that reflects a relationship between a network address and a user attribute of a 'known user' whose profile information is recognizable. For a given network address, the decision tree can be used as a machine learning classifier to predict the most likely user attribute of a potential user. With the predicted attribute, a network service can target a group of potential users for various campaigns without recognizing the identities of the potential users.

Predicting geographic location associated with network address

Growing community of inventors

Mercer Island, WA, United States of America

Daniel Bruce Lloyd