Administrative Regions Discovery Based on Human Mobility Patterns and Spatio-Temporal Clustering

Currently, the understanding of the human mobility is an important challenge that has a large number of applications, especially in the study of a nation's ability to thrive economically and socially. Some works have shown that, it is possible to observe developed and developing countries reviewing their administrative regions borders, in order to reduce costs, or to solve ethnic claims and/or independence movements. In this context, the present work leverages mobile phone data to analyze human mobility patterns. Specifically, we propose a new method to detect administrative regions and paths of interaction between regions, both relying on subscribers mobility patterns extracted from Call Detail Records (CDR). Thus, our method offers a different point of view to redefine administrative boundaries.