Generalized similarity measure for categorical data clustering
Shruti Sharma, Manoj K. Singh · 2016
Categorical data needs special treatment before it can be clustered using popular methods of pattern analysis. Or separate methods to deal with categorical data have to be devised. All such methods use some kind of similarity metric to judge how similar two data objects are. There are several popular similarity measures and switching between them requires much effort. This paper presents a Generalized Similarity Metric (GSM) which inculcates five popular measures into a single parameterized formulation. Its implementation in famous ROCK algorithm is also presented to show the efficiency of proposed metrics.