A Novel Initial Clusters Generation Method for K-means-based Clustering Algorithms for Mixed Datasets

Mixed datasets consist of both numeric and categorical attributes. Various K-means-based clustering algorithms have been developed to cluster these datasets. Generally, these algorithms use random partition as a starting point, which tend to produce different clustering results in different runs. This inconsistency of clustering results may lead to unreliable inferences from the data. A few initialization algorithms have been developed to compute initial partition for mixed datasets; however, they are either computationally expensive or they do not produce consistent clustering results in different runs. In this paper, we propose, initKmix, a novel approach to find initial partition for K-means-based clustering algorithms for mixed datasets. The initKmix is based on the experimental observations that (i) some data points in a dataset remain in the same clusters created by k-means-based clustering algorithm irrespective of the choice of initial clusters, and (ii) individual attribute information can be used to create initial clusters. In initKmix method, a k-means-based clustering algorithm is run many times, in each run one of the attribute is used to produce initial partition. The clustering results of various runs are combined to produce initial partition. This initial partition is then be used as a seed to a k-means-based clustering algorithm to cluster mixed data. The initial partitions produced by initKmix are always fixed, do not change over different runs or by changing the order of the data objects. Experiments with various categorical and mixed datasets showed that initKmix produced accurate and consistent results, and outperformed random initialization and other state-of-the-art initialization methods. Experiments also showed that K-means-based clustering for mixed datasets with initKmix outperformed many state-of-the-art clustering algorithms.