Abstract: The present invention employs data processing systems to handle debt collection by formulation the collections process as a Markov Decision Process with constrained resources, thus making it possible automatically to generate an optimal collections policy with respect to maximizing long-term expected return throughout the course of a collections process, subject to constraints on the available resources possibly in multiple organizations. This is accomplished by coupling data modeling and resource optimization within the constrained Markov Decision Process formulation and generating optimized rules based on constrained reinforcement learning process comprising applied on the basis of past historical data.

Abstract: The present invention employs data processing systems to handle debt collection by formulation the collections process as a Markov Decision Process with constrained resources, thus making it possible automatically to generate an optimal collections policy with respect to maximizing long-term expected return throughout the course of a collections process, subject to constraints on the available resources possibly in multiple organizations. This is accomplished by coupling data modeling and resource optimization within the constrained Markov Decision Process formulation and generating optimized rules based on constrained reinforcement learning process comprising applied on the basis of past historical data.

Abstract: A technique for enhanced data mining of large scale relational databases is described. User defined functions (UDF) are created by a user and distributed by a managing node of a database to each node of the database. Upon the issuance of a prespecified SQL command, the UDF is executed by each node relative to the data controlled by each node. Specifically, targeted tuples in the data controlled by each node are scored based on criteria contained in the UDF. A new data field is added to each target tuple, and the score is placed therein. The score is then used to determine whether, for example, a customer which is represented by the tuple should be included in an advertising campaign or to tailor a mailing to a customer based on the score contained in the new data field.