A Data-Driven Optimisation Approach to Urban Multi-Site Selection for Public Services and Retails

Abstract

Urban lifestyle depends on public services and retails, of which site locations matter to convenience for residents. We introduce a novel approach to the systematic multi-site selection for public services and retails in an urban context. It takes as input a set of data about an urban area and generates an optimal configuration of two-dimensional locations for urban sites on public services and retails. We achieve this goal using data-driven optimisation entangling deep learning. The proposed approach can cost-efficiently generate a multi-site location plan considering representative site selection criteria, including coverage, dispersion and accessibility. It also complies with the local plan and the predicted suitability regarding land-use zoning.