Towards Efficient Discriminative Pattern Mining in Hybrid Domains
This work addresses a practical issue in data mining for researchers and practitioners dealing with mixed data types, but it appears incremental as it builds on existing discriminative pattern mining methods.
The paper tackles the problem of handling numeric values in discriminative pattern mining by proposing an algorithm for hybrid domains with both symbolic and numeric data, and demonstrates its execution on two standard benchmark datasets.
Discriminative pattern mining is a data mining task in which we find patterns that distinguish transactions in the class of interest from those in other classes, and is also called emerging pattern mining or subgroup discovery. One practical problem in discriminative pattern mining is how to handle numeric values in the input dataset. In this paper, we propose an algorithm for discriminative pattern mining that can deal with a transactional dataset in a hybrid domain, i.e. the one that includes both symbolic and numeric values. We also show the execution results of a prototype implementation of the proposed algorithm for two standard benchmark datasets.