Data Mining with Extended Symbolic Models

Symbolic modeling of data with decision trees or decision rules has a certain appeal to data mining application developers. The computationally e cient nature of the modeling methodology, and the inbuilt explanatory nature of the models that are generated, are two often cited reasons for the preferred use of these methods. Traditionally, the applications of these methods had been restricted to classi cation modeling. Recent extensions to these methods employing ideas from statistics and machine learning have resulted in more general frameworks that continue to exhibit the underlying characteristics but apply to a much wider class of applications. These extended symbolic modeling methodologies permit exciting new application avenues, including probabilistic modeling, text mining, and integrating data mining into knowledge-based frameworks. Highlights of work in this area in the data abstraction research group at IBM's T.J. Watson Research Center will be presented.