The use of parcel-pickup points (PPPs) is an effective approach for solving the last-mile problem. However, few studies provide specific guidance for the optimal organization of PPPs. Here, a geographic information system(GIS)-based hybrid model was developed combining the widely used analytic hierarchy process (AHP) multi-criteria analysis method with the Huff model that predicts the number of visiting customers to determine the optimal facility for collaboration and service as a PPP. Using this model, a decision-maker can select the highest-ranking facility or use the fluctuation ranking graph to determine a priority list of candidate facilities according to the appropriate PPP service distance. Our findings suggest that the optimal candidate facility should be located near high population density areas, a dense road network, and few geographic barriers. The facility should have a high attractiveness value, long business hours, and convenient access to public transportation, cover a large, high-population area, and should be a retail chain store. Based on these findings, the AHP method can improve the accuracy of obtaining the facility attractiveness value using the Huff model. Facility attractiveness has a strong effect on the resulting number of customers in the case of acceptably long distances to residential buildings.

The site-suitability analysis (SSA) of parcel-pickup lockers (PPLs) is becoming a critical problem in last-mile logistics. Most studies have focused on the site-selection problem to identify the best site from given potential sites in specific areas, while few have solved the site-search problem to determine the boundary of the suitable area. A GIS-based bivariate logistic regression (LR) model using the supervised machine-learning (ML) algorithm was developed for suitability classification in this study. Eight crucial factors were selected from 27 candidate variables using stepwise methods with a training dataset in the best LR model. The variable of the proximity to residential buildings was more important than that to various commercial buildings, transport services, and roads. Among the four types of residential buildings, the most crucial factor was the proximity to residential quarters. A test dataset was employed for the validation process, showing that the best LR model had excellent performance. The results identified the suitable areas for PPLs, accounting for 8% of the total area of Guangzhou (GZ). A decision-maker can focus on these suitable areas as the site-selection ranges for PPLs, which significantly reduces the difficulty of analysis and time costs. This method can quickly decompose a large-scale area into several small-scale suitable areas, with relevance to the problem of selecting sites from various candidate sites.