Integrating clustering data mining into the multidimensional modeling of Data Warehouses with UML profiles

Clustering can be considered the most important unsupervised learning technique finding similar behaviors (clusters) on large collections of data. Data warehouses (DWs) can help users to analyze stored data, because they contain preprocessed data for analysis purposes. Furthermore, the multidimensional (MD) model of DWs, intuitively represents the system underneath. However, most of the clustering data mining are applied at a low-level of abstraction to complex unstructured data. While there are several approaches for clustering on DWs, there is still not a conceptual model for clustering that facilitates modeling with this technique on the multidimensional (MD) model of a DW. Here, we propose (i) a conceptual model for clustering that helps focusing on the data-mining process at the adequate abstraction level and (ii) an extension of the unified modeling language (UML) by means of the UML profiling mechanism allowing us to design clustering data-mining models on top of the MD model of a DW. This will allow us to avoid the duplication of the time-consuming preprocessing stage and simplify the clustering design on top of DWs improving the discovery of knowledge.