Amazon Technologies, Inc.

Jody David Biggs

Rahul H Bhagat

Michael Lee Loritsch

Phillip A Kahrl

Brent Russell Smith

Vinod Murli Mamtani

Avishkar Misra

Srijith Ravikumar

Systems and methods are disclosed to update ads on user devices that may connect to a network only intermittently by predicting and tracking various metrics associated with ads delivered to the user devices. An example method may include determining a first set of ads that were presented at a first semi-connected device while the first semi-connected device was disconnected from a network, determining a first device identifier associated with the first semi-connected device, and determining, based at least in part on the first device identifier, a first estimated number of ad impressions for a first ad. Example methods may include determining, based at least in part on the first estimated number of ad impressions, that the first semi-connected device is to be updated with the first ad, causing the first ad to be sent to the first semi-connected device, and causing at least one ad of the first set of ads to be removed from the first semi-connected device.

Advertisement metric prediction

Disclosed are various embodiments for predicting repeated behavior by an entity with respect to a particular item. In some embodiments, an entity requesting results to a search query may be redirected to an alternative network page associated with the particular item instead of a search results page according the expectation of repeated behavior.

System and method for personalized network content generation and redirection according to repeat behavior

Systems and methods are provided for generating a signed identifier associated with an item offer and a user account. When the identifier is submitted to a computing system to redeem an associated offer, a signature within the identifier may be analyzed to confirm that the identifier has not been modified. An item discount associated with an item offer identified in the identifier may then be applied within the identified user's account based on offer details retrieved from an electronic data store.

Signed identifiers for confirming offer eligibility

Systems and methods are disclosed to update ads on user devices that may connect to a network only intermittently by predicting and tracking various metrics associated with ads delivered to the user devices.

Systems, methods, and computer-readable media are disclosed for identifying a set of images of child variants of a parent item, identifying a set of colors in the set of images, categorizing the set of colors into color subgroups, identifying a set of representative color(s) for the color subgroups, generating a color value distribution representation for an image of a child variant that indicates a respective number of pixels in the child variant image corresponding to each of one or more representative colors, identifying a color cluster in the color value distribution representation, scoring the color cluster, and selecting a particular color from the color cluster for inclusion in a sample image of the child variant if the color cluster score meets or exceeds a threshold value.

Sample color selection for online retail items

Disclosed are various embodiments for predicting repeated behavior by an entity with respect to a particular item. In some embodiments, a network page including a recommendation for the particular item may be generated according to an expectation of repeated behavior. In some embodiments, an entity requesting results to a search query may be redirected to an alternative network page associated with the particular item instead of a search results page according the expectation of repeated behavior.

Personalized network content generation and redirection according to repeat behavior

The dimensionality of user data can be reduced in order to allow cross-category data to be used to determine recommendations, advertising, or other supplemental content within a specific category. A first reduction in dimensionality results from rolling up category nodes to higher-level nodes. User data for the higher-level nodes can be used to train a neural network, with a user signature being generated using node values from a hidden layer of the trained model. The user signature can then be used to train a category specific model in order to obtain category-specific recommendations, determine category-specific advertising, or select other supplemental content based at least in part upon cross-category data.

Growing community of inventors

Seattle, WA, United States of America

Jody David Biggs