A clustering model for flow data: an application to international student mobility

A new clustering model for skew-symmetric matrices is introduced to analyse flow data. This model aims to find clusters of objects that have a significant flow, interpreted as exchange intensity. The model analyses the within-clusters effects between objects and provides the directions of the flows within clusters. Formally, it is based on the decomposition of the data skew-symmetric matrix into within-cluster components, i.e. the skew-symmetric matrix is decomposed into a sum of diagonal block skew-symmetric matrices. The model is estimated in a least-squares sense through the SVD of the skew-symmetric matrices. An application to the international student mobility is discussed.