A predictive framework for last-mile delivery routes considering couriers’ behavior heterogeneity

Abstract

Last-mile route prediction is a powerful tool for freight delivery companies that can be essential in the development of new features such as arrival time prediction or accurate workload allocation. Existing methodologies propose prediction models that, on the one hand, require external information, such as traffic data or a prior division of work areas, and, on the other hand, assume courier homogeneity in the search for travel patterns. However, this assumption may introduce noise in the predictions since different couriers may be subject to different routing habits. This study proposes a comprehensive predictive framework for delivery routes, which allows identifying the routing profiles that best suit each courier and work area, and which starts from basic information available for any carrier, ensuring the scalability of the tool. The analysis is supported by a case study, where the results obtained bring to light the heterogeneity in the routing decisions of the different drivers and show that the proposed approach produces consistent and accurate predictions for the vast majority of them.