Innovation of such clusters of data is essential in illuminating main links in categorical data regulatory networks. There are lot of problems exists in the previous clustering methods especially while grouping the data with mixed data types. This experiment analyzes those existing methods and comes with the new approach for clustering the mixed data items. There are many methods occur for clustering the parallel kind of data, whereas only very few methods exists for clustering mixed data items and it leads to the need of better clustering technique for classification of mixed data. For investigative data, the clustering with the help of Gaussian mixture models is widely used.