US 10,853,735 B1Granted

Maximizing quantifiable user interaction via modification of adjustable parameters

AssigneeAmazon Technologies, Inc.

InventorsYu Gan, Cédric Philippe Archambeau, Rodolphe Jenatton, Jim Huang, Fabian Lutz-Frank Wauthier

Life of this patent

Estimating the term…

Loading patent…

Abstract

Systems, methods, and computer-readable media are disclosed for maximizing quantifiable user interaction via modification of adjustable parameters. In one embodiment, an example method may include determining a first output to maximize, where the first output is a function of a first adjustable parameter and a second adjustable parameter, determining first data comprising a first actual value of the first output when the first adjustable parameter is set to a first value and the second adjustable parameter is set to a second value, and determining a first predictive model that generates a first predicted value of the first output. Example methods may include determining, using the first predictive model, a third value for the first adjustable parameter and a fourth value for the second adjustable parameter to maximize the first predicted value, and sending the third value and the fourth value.

Claims20

Dependent claims

A method comprising:

determining, by one or more computer processors coupled to at least one memory, a first output to maximize, wherein the first output is a function of a first adjustable parameter and a second adjustable parameter;
determining first data comprising a first actual value of the first output when the first adjustable parameter is set to a first value and the second adjustable parameter is set to a second value;
determining a first predictive model that generates a first predicted value of the first output;
determining, using the first predictive model, a third value for the first adjustable parameter and a fourth value for the second adjustable parameter to maximize the first predicted value;
determining a first confidence score indicative of a correlation between the third value and the fourth value and maximization of the first output;
determining that the first confidence score satisfies a first minimum confidence threshold;
sending the third value and the fourth value, wherein the first adjustable parameter is set to the third value and the second adjustable parameter is set to the fourth value;
delivering first content based at least in part on the first adjustable parameter and the second adjustable parameter, wherein the first data further comprises first user interaction data indicative of user interaction responsive to the first content;
determining a first set of product identifiers associated with the first content;
determining a first browse node hierarchy for the first set of product identifiers, wherein the first browse node hierarchy is a first alphanumeric value based at least in part on the first set of product identifiers;
determining a second set of product identifiers associated with the second content;
determining a second browse node hierarchy for the second set of product identifiers, wherein the second browse node hierarchy is a second alphanumeric value based at least in part on the second set of product identifiers;
determining a distance between the first browse node hierarchy and the second browse node hierarchy;
determining that the distance meets the similarity metric;
receiving second data comprising second user interaction data indicative of user interaction responsive to the second content;
and
generating a set of content comprising the first content and the second content.

14 more elements

A device comprising:

at least one memory that stores computer-executable instructions;
and
at least one processor configured to access the at least one memory and execute the computer-executable instructions to:
determine a first output to maximize, wherein the first output is a function of a first adjustable parameter and a second adjustable parameter;
determine first data comprising a first actual value of the first output when the first adjustable parameter is set to a first value and the second adjustable parameter is set to a second value;
determine a first predictive model that generates a first predicted value of the first output;
determine, using the first predictive model, a third value for the first adjustable parameter and a fourth value for the second adjustable parameter to maximize the first predicted value;
determine a first confidence score indicative of a correlation between the third value and the fourth value and maximization of the first output;
determine that the first confidence score satisfies a first minimum confidence threshold;
send the third value and the fourth value;
deliver first content based at least in part on the first adjustable parameter and the second adjustable parameter, wherein the first data further comprises first user interaction data indicative of user interaction responsive to the first content;
determine a first set of product identifiers associated with the first content;
determine a first browse node hierarchy for the first set of product identifiers, wherein the first browse node hierarchy is a first alphanumeric value based at least in part on the first set of product identifiers;
determine a second set of product identifiers associated with the second content;
determine a second browse node hierarchy for the second set of product identifiers, wherein the second browse node hierarchy is a second alphanumeric value based at least in part on the second set of product identifiers;
determine a distance between the first browse node hierarchy and the second browse node hierarchy;
determine that the distance meets the similarity metric;
receive second data comprising second user interaction data indicative of user interaction responsive to the second content;
and
generate a set of content comprising the first content and the second content.

17 more elements

A computer-readable medium storing computer-executable instructions which, when executed by a processor, cause the processor to perform operations comprising:

determining, by one or more computer processors coupled to at least one memory, a first output to maximize, wherein the first output is a function of a first adjustable parameter and a second adjustable parameter;
determining first data comprising a first actual value of the first output when the first adjustable parameter is set to a first value and the second adjustable parameter is set to a second value;
determining a first predictive model that generates a first predicted value of the first output;
determining, using the first predictive model, a third value for the first adjustable parameter and a fourth value for the second adjustable parameter to maximize the first predicted value;
determining a first confidence score indicative of a correlation between the third value and the fourth value and maximization of the first output;
determining that the first confidence score satisfies a first minimum confidence threshold;
sending the third value and the fourth value, wherein the first adjustable parameter is set to the third value and the second adjustable parameter is set to the fourth value;
delivering first content based at least in part on the first adjustable parameter and the second adjustable parameter, wherein the first data further comprises first user interaction data indicative of user interaction responsive to the first content;
determining a first set of product identifiers associated with the first content;
determining a first browse node hierarchy for the first set of product identifiers, wherein the first browse node hierarchy is a first alphanumeric value based at least in part on the first set of product identifiers;
determining a second set of product identifiers associated with the second content;
determining a second browse node hierarchy for the second set of product identifiers, wherein the second browse node hierarchy is a second alphanumeric value based at least in part on the second set of product identifiers;
determining a distance between the first browse node hierarchy and the second browse node hierarchy;
determining that the distance meets the similarity metric;
receiving second data comprising second user interaction data indicative of user interaction responsive to the second content;
and
generating a set of content comprising the first content and the second content.

14 more elements

Dependencies are inferred from the claim text.