Recently, last-mile distribution in cities has been constrained by fast-delivery options, hard time windows, and no-show-up customers. The promotion of automated parcel locker (APL) systems is seen as a way to mitigate the aforementioned problems. Thus, this paper analyzes APL users in the city of Pamplona (Spain), and proposes the use of hybrid modeling for APL network design. Moreover, agent-based modeling is used to estimate future demand based on a number of socio-economic parameters, i.e., population as well as the rates of online users, e-commerce growth, e-shoppers, APL usage, and others. Likewise, the APL location optimization model is dynamically executed within the simulation framework to minimize the operational and service costs to meet the expected demand. Promising results are obtained, encouraging the use of simulation and optimization tools to leverage the use of APLs as a last-mile distribution scheme.