Towards Statistical Comparison and Analysis of Models

Model comparison is an important challenge in model-driven engineering, with many application areas such as model versioning and domain model recovery. There are numerous techniques that address this challenge in the literature, ranging from graph-based to linguistic ones. Most of these involve pairwise comparison, which might work, e.g. for model versioning with a small number of models to consider. However, they mostly ignore the case where there is a large number of models to compare, such as in common domain model/metamodel recovery from multiple models. In this paper we present a generic approach for model comparison and analysis as an exploratory first step for model recovery. We propose representing models in vector space model, and applying clustering techniques to compare and analyse a large set of models. We demonstrate our approach on a synthetic dataset of models generated via genetic algorithms.