Massive Retail Location Choice as a Human Flow-Covering Problem

TL;DR

This paper introduces a robust spatial model for retail location selection based on human flow data, improving coverage by leveraging individual trajectories instead of traditional assumptions.

Contribution

It reformulates retail location choice as a set-covering problem using human flow data, offering a novel, data-driven approach with a greedy solution method.

Findings

Significant coverage improvements over traditional methods

Effective use of real-world trajectory data in location planning

Validation through a Shenzhen case study

Abstract

In this article we reframe the classic problem of massive location choice for retail chains, introducing an alternative approach. Traditional methodologies of massive location choice models encounter limitations rooted in assumptions such as power-law distance decay and oversimplified travel patterns. In response, we present a spatial operations research model aimed at maximizing customer coverage, using massive individual trajectories as a "sampling" of human flows, and thus the model is robust. Formulating the retail location selection problem as a set-covering problem, we propose a greedy solution. Through a case study in Shenzhen utilizing real-world individual trajectory data, our approach demonstrates substantial improvements over prevailing location choices.