Missing Data Resilient Ensemble Subspace Decision Tree Classifier
Sairam Utukuru, Radha Krishna Pisipati, Kamalakar Karlapalem · 2023
The construction of a decision tree on a given data set involves certain features. In case these features have NULL values during the production environment, the decision tree performance suffers. In this work, we develop a methodology to generate subspace decision tree classifiers, where each decision tree uses non-overlapping subsets of feature sets. We build an ensemble classifier over these subspace classifiers to get better performance. We consider different levels of missing data in our ensemble classifier, to show that it is resilient to missing data and can also give better performance even in cases of incomplete data (that is, data with missing values). We show the viability of our methodology using real-life and synthetic data sets. Our approach delivers a simple yet effective missing data resilient decision tree classifier.