Personalized recommendations based on item usage

摘要

This disclosure describes systems and associated processes for generating recommendations for users based on usage, among other things. These systems and processes are described in the context of an interactive computing system that enables users to download applications for mobile devices (such as phones) or for other computing devices. Users' interactions with applications once they are downloaded can be observed and tracked, with such usage data being collected and provided to the interactive computing system. The interactive computing system can include a recommendation system or service that processes the usage data from a plurality of users to detect usage patterns. Using these usage patterns, among possibly other data, the recommendation system can recommend applications to users for download.

主权项

1. A method of recommending personalized computer applications to users, the method comprising:
accessing usage data associated with a mobile computing device of a user, the usage data reflecting a degree of usage by the user of a plurality of user applications installed on the mobile computing device; identifying related applications that are related to the user applications in a usage associations data set, the usage associations data set comprising a graph having nodes that represent the related applications and weighted edges having first weights that are based at least on a degree of similar usage of the related applications by a plurality of users; weighting the related applications with second weights that are based at least in part on the degree of usage by the user of each of the user applications to which the related applications are related in the usage associations data set, wherein said weighting causes the related applications that are related to the user applications used more frequently by the user to have greater second weights than the related applications related to the user applications used less frequently by the user; and selecting a subset of the related applications for presentation as recommendations to the user based at least in part on the second weights; wherein at least said identifying is performed by one or more processors.