Multivariate Decision Trees Using Different Splitting Attribute Subsets for Large Datasets

In this paper, we introduce an incremental induction of multivariate decision tree algorithm, called IIMDTS, which allows choosing a different splitting attribute subset in each internal node of the decision tree and it processes large datasets. IIMDTS uses all instances of the training set for building the decision tree without storing the whole training set in memory. Experimental results show that our algorithm is faster than three of the most recent algorithms for building decision trees for large datasets.