Metrics for Mining Multisets

Abstract. We propose a new class of distance measures (metrics) designed for multisets, both of which are a recurrent theme in many data mining applications. One particular instance of this class originated from the necessity for a clustering of criminal behaviours. These distance measures are parameterized by a function f which, given a few simple restrictions, will always produce a valid metric. This flexibility allows these measures to be tailored for many domain-specific applications. In this paper, the metrics are applied in bio-informatics (genomics), criminal behaviour clustering and text mining. The metric we propose also is a generalization of some known measures, e.g., the Jaccard distance and the Canberra distance. We discuss several options, and compare the behaviour of different instances.

• Type: Conference
• Year: 2007
• Where: SGAI
• Authors: Walter A. Kosters, Jeroen F. J. Laros
• Keywords: Criminal Behaviour, Data Mining Applications, Distance Measures, SGAI 2007