Effects of Different Types of New Attribute on Constructive Induction

This paper studies the eeects on decision tree learning of constructing four types of attribute (conjunc-tive, disjunctive, M-of-N, and X-of-N representations). To reduce eeects of other factors such as tree learning methods, new attribute search strategies, evaluation functions, and stopping criteria, a single tree learning algorithm is developed. With diierent option settings, it can construct four diierent types of new attribute, but all other factors are xed. The study reveals that conjunctive and disjunctive representations have very similar performance in terms of prediction accuracy and theory complexity on a variety of concepts. Moreover , the study demonstrates that the stronger representation power of M-of-N than conjunction and disjunc-tion and the stronger representation power of X-of-N than these three types of new attribute can be reeected in the performance of decision tree learning.