Abstract: A front-end system collects user attribute value data and organizes the data into one or more training data sets and one or more test data sets. The front-end system provides at least some of the test data sets to an input layer of a machine learning system. Within the machine learning system, one or more predictive models are constructed. At an output layer, the predictive models provide output data that includes at least a value indicative of whether a user will upgrade service levels based at least in part on the attribute values logically associated with the respective user. A back-end system generates upgrade offers for subsequent communication to those users identified as being likely to upgrade.

Abstract: Information related to apparently successful matches between two entities is collected, and culled based on a later indication that the match failed. Matches between two entities may be generated based on comparative information with other entities who appear to share some characteristics or preferences. Matches may be based on actual actions, in contrast to expressed preferences. Actual actions may be taken into account in addition to expressed preferences. Generation of matches may take into account geographical and/or temporal proximity and/or likelihood of receiving a response, in addition to other attributes of an entity. Matching algorithms may be updated based on entity input. Potential matches may be presented to third party entities for evaluation.