The main objective of this project is to develop a method which evaluates distinctness of a clustering structure in data (clusterability). It is supposed to operate on raw data only, with no requirement of any prior partition. Based on a combination of advanced formal analysis and compute-intensive simulations, the resulting method should be theoretically well-established and efficient in its performance. Besides the actual method for clusterability assessment, also its operational open source implementation is expected to conclude the project.