A data-driven optimization of large-scale dry port location using the hybrid approach of data mining and complex network theory

Abstract

The paper proposes a two-stage approach that combines data mining and complex network theory to optimize the locations and service areas of dry ports in a large-scale inland transportation system. In the first stage, candidate locations of dry ports are weighted based on their eigenvector centrality in the complex network of association rules mined from a large amount of international transaction data. In the second phrase, dry port locations and their service areas are optimized using the gravity-based community structure. The method is validated in a real case study which optimizes a large-scale dry port network in Mainland China in the context of the Belt and Road Initiatives (BRI). As a result, optimal dry port locations include key transportation hubs that closely reflect the real BRI development plan, hence, the proposed approach is validated.