The present invention provides a language, method and system to formulate and evaluate relational Bayesian networks in an e-commerce environment. The present invention employs a specific language for constructing synthetic variables used to predict events in the Bayesian networks. The present system and language allow for efficient and accurate representation, inference, and discovery of the synthetic variables used to model web visitor behavior.

 
Web www.patentalert.com

< Methods for multi-objective optimization using evolutionary algorithms

> Dynamical brain model for use in data processing applications

~ 00408