Abstract

Yasser El Sonbaty
multiway decision tree induction using projectionmerging (mpeg)
decision trees are one of the most popularcommonly used classification models. many algorithms have been designed to build decision trees in the last twenty years. these algorithms are categorized into two groups according to the type of the trees they build, binarymultiway trees. in this paper, a new algorithm, mpeg, is designed to build multiway trees. mpeg uses dbms indicesoptimized query to access the dataset it works on, hence it has few memory requirementsno restrictions on sizes of datasets. projection of examples over attribute values, merging of generated partitions using class values, applying gini index to among different attributesfinally post pruning using ebp method, are the basic steps of mpeg. the trees built by mpeg have the advantages of binary trees as being accurate, small in sizethe advantages of multiway trees as being compacteasy to be comprehended by humans