Locally-Adaptive Naïve Bayes Framework Design via Density-Based Clustering for Large Scale Datasets

Abstract

In this chapter, local conditional probabilities of a query point are used in classification rather than consulting a generalized framework containing a conditional probability. In the proposed locally adaptive naïve Bayes (LANB) learning style, a certain amount of local instances, which are close the test point, construct an adaptive probability estimation. In the empirical studies of over the 53 benchmark UCI datasets, more accurate classification performance has been obtained. A total 8.2% increase in classification accuracy has been gained with LANB when compared to the conventional naïve Bayes model. The presented LANB method has outperformed according to the statistical paired t-test comparisons: 31 wins, 14 ties, and 8 losses of all UCI sets.