MSJEP Classifier: “Modified Strong Jumping Emerging Patterns” for Fast Efficient Mining and for handling attributes whose values are associated with taxonomies

Abstract

Modified Strong Jumping Emerging Patterns (MSJEPs) are those itemsets whose support increases from zero in one data set to non-zero in the other dataset with support constraints greater than the minimum support threshold (ζ). The support constraint of MSJEP removes potentially less useful JEPs while retaining those with high discriminating power. Contrast Pattern (CP)-tree-based discovery algorithm used for SJEP mining is a main-memory-based method. When the data set is large, it is unrealistic to assume that the CP-tree can fit in the main memory. The main idea to handle this problem is to first partition the data set into a set of projected data sets and then for each projected data set, we construct and mine its corresponding CP-tree. Trees of the projected data sets are called Separated Contrast Pattern Tree “SCP-trees” and Patterns generated from it are Called MSJEPs” Modified Strong Jumping Emerging Patterns”. Our proposal also investigates the weakness of emerging patterns in handling attributes whose values are associated with taxonomies and proposes using an MSJEP classifier to achieve better accuracy, better speed, and also handling attributes in taxonomy.