MODEL-BASED PREDICTION OF AN OPTIMAL CONVENIENCE METRIC FOR AUTHORIZING TRANSACTIONS

摘要

The present disclosure describes systems and methods for authorization. The method may include accessing, by an authorization engine for a transaction by a user, an activity pattern model of the user from a database. The activity pattern model of the user may be indicative of a geospatial behavior of the user over time. The authorization engine may determine a set of sensors available for facilitating the transaction, each of the sensors assigned with a usability value prior to the transaction. The authorization engine may access an activity pattern model of the sensors, the activity pattern model of the sensors indicative of geospatial characteristics of one or more of the sensors over time. The authorization engine may determine a convenience metric for each of a plurality of subsets of the sensors, using the activity pattern model of the user, the activity pattern model of the sensors, and usability values of corresponding sensors. Each of the plurality of subsets may include corresponding sensors that can be used in combination to facilitate the transaction. The authorization engine may select, using the determined convenience metrics, a subset from the plurality of subsets to use for the transaction.