A MASS ASSIGNMENT BASED ID3 ALGORITHM FOR DECISION TREE INDUCTION

A mass assignment based ID3 algorithm for learning probabilistic fuzzy decision trees is introduced. Fuzzy partitions are used to discretize continuous feature universes and to reduce complexity when universes are discrete but with large cardinalities. Furthermore, the fuzzy part itioning of classification universes facilitates the use of these deci sion trees in function approximation problems. Generally the incorpora tion of fuzzy sets into this paradigm overcomes many of the problems a ssociated with the application of decision trees to real-world problem s. The probabilities required for the trees are calculated according t o mass assignment theory applied to fuzzy labels. The latter concept i s introduced to overcome computational complexity problems associated with higher dimensional mass assignment evaluations on databases. (C) 1997 John Wiley & Sons, Inc.