Estimating the Location of Off-Street Infrastructure for Delivery and Pick-Up Operations in Dense Urban Areas

Recent trends such the growth of e-commerce and parcel deliveries are stressing freight transportation in dense urban areas. At the same time, a historical lack of integration of the freight transportation system into city planning efforts has left local governments unprepared. Under these circumstances, there is growing need for best practices for freight planning and management at U.S. cities.

There is anecdotal evidence that the lack of delivery areas is one of the main causes of inefficient urban freight parking infrastructure, which leads to illegal parking and more congestion. The problem of lack of delivery areas has been studied with a focus on on-street spaces. Meanwhile, the contribution of delivery areas out of the public right of way such as loading bays in buildings has not benefited from research. More importantly, the location and features of private delivery areas are often unknown by local governments due to their private character.

For these reasons, this paper aims to answer the following research question: Can cities use data readily available to know the location of off-street freight loading/unloading parking in dense urban areas?

This paper presents the first predictive tool to estimate the presence of private truck spaces for delivery and pick-up operations based on observable characteristics of property parcels and their buildings. Our results show that it is possible to estimate the location of private delivery areas in property parcels mainly used for commercial purposes within a reasonable level of error.

This research uses a quantitative approach. The predictive model classifies parcels with and without private delivery areas using random forest, a supervised machine learning algorithm. The model was developed based on a rich geodatabase of private truck load/unload spaces in the City of Seattle and the King County tax parcel database.

This research helps to overcome the lack of data regarding the location of private delivery areas in urban areas. Future research can benefit from this contribution by including private delivery areas in occupancy studies to document and analyze the operations in this facilities. This research would allow to better document the impacts of the lack of delivery areas in urban areas considering both public and private facilities.