Recommendation engine using action node mapping
AssigneeAmazon Technologies, Inc.
InventorsPrakash Bulusu, Pragyana K. Mishra
Life of this patent
Estimating the term…
Abstract
Described herein are a system and methods for providing action recommendations to a user that are likely to result in performance of a high-value action. In some embodiments, the user is compared to one or more other users in order to identify high-value actions for that user. Once at least one high-value action has been identified, a sequence of actions may be generated to include that high-value action using prediction model data that includes probability information. The sequence of actions is then assessed to determine a gateway action within the sequence of actions that is likely to be performed by the user and has a high likelihood of resulting in subsequent performance of the high-value action. The gateway action may then be presented to the user.
Claims20
A computer-implemented method performed by a computer system of a service provider, comprising:
- receiving a request to present an action recommendation to a user;
- identifying, with respect to the user, a set of actions based on historical data associated with the user;
- identifying, within the set of actions, a high-value action desired by the service provider for the user to perform, the high-value action having a first probability of being performed by the user as a next action;
- generating prediction model data that indicates relationships between actions among a plurality of actions, the prediction model data including an action that corresponds to the high-value action;
- determining, using the prediction model data, a sequence of actions likely to result in execution of the high-value action by the user;
- identifying, within the sequence of actions, an action with a higher probability of execution by the user as the next action than the first probability of the high-value action being performed by the user as the next action, and wherein, upon being executed by the user as the next action, has a high probability of inducing the user to subsequently perform the high-value action;
- and
- providing for presentation the action recommendation as a notification including the action with the higher probability of execution to the user.
A system of a service provider, comprising:
- a processor;
- and
- a memory including instructions that, when executed with the processor, cause the system to at least:
- receive a request to present an action recommendation to a user;
- identify, with respect to the user, a set of actions based on historical data associated with the user;
- identify, within the set of actions, a high-value action desired by the service provider for the user to perform, the high-value action having a first probability of being performed by the user as a next action;
- generate prediction model data that indicates relationships between actions among a plurality of actions, the prediction model data including an action that corresponds to the high-value action;
- determine, using the prediction model data, a sequence of actions likely to result in execution of the high-value action by the user;
- identify, within the sequence of actions, an action with a higher probability of execution by the user as the next action than the first probability of the high-value action being performed by the user as the next action, and wherein, upon being executed by the user as the next action, has a high probability of inducing the user to subsequently perform the high-value action;
- and
- provide for presentation the action recommendation as a notification including the action with the higher probability of execution to the user.
A non-transitory computer readable medium storing specific computer-executable instructions that, when executed with a processor, cause a computer system of a service provider to, at least:
- receive a request to present an action recommendation to a user;
- identify, with respect to the user, a set of actions based on historical data associated with the user;
- identify, within the set of actions, a high-value action desired by the service provider for the user to perform, the high-value action having a first probability of being performed by the user as a next action;
- generate prediction model data that indicates relationships between actions among a plurality of actions, the prediction model data including an action that corresponds to the high-value action;
- determine, using the prediction model data, a sequence of actions likely to result in execution of the high-value action by the user;
- identify, within the sequence of actions, an action with a higher probability of execution by the user as the next action than the first probability of the high-value action being performed by the user as the next action, and wherein, upon being executed by the user as the next action, has a high probability of inducing the user to subsequently perform the high-value action;
- and
- provide for presentation the action recommendation as a notification including the action with the higher probability of execution to the user.
Dependencies are inferred from the claim text.