Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

12-2024

Abstract

This paper addresses the challenge of optimal retail expansion in competitive urban environments through a novel approach to the Competitive Facility Location (CFL) problem. Traditional methods for solving CFL problems often struggle with large-scale scenarios, relying on manual pre-selection of candidate sites and imposing limitations on the number of new locations. Our approach leverages Adaptive Large Neighborhood Search (ALNS) enhanced with data enrichment techniques, including community detection on road networks and population weighting based on mobility data. We developed two ALNS variants: Community Geometric Centroid (CGC-ALNS) and Population Weighted Centroid (PWC-ALNS). These methods automate site selection, eliminating manual pre-selection while enabling the evaluation of numerous potential store locations. Benchmarking against ArcGIS, a widely used commercial CFL software, reveals significant performance improvements. CGC-ALNS outperforms ArcGIS with up to a 2% increase in consumer capture, while PWC-ALNS achieves an average increase of 4.6% to 13.1% across diverse store distribution scenarios. Key contributions include an automated, data-driven site selection process unrestricted by the number of new sites and notable performance enhancements over existing commercial solutions.

Keywords

competitive facility location, retail expansion, Adaptive Large Neighborhood Search, data-driven optimization, community detection, population weighting, mobility data, site selection, ArcGIS benchmarking, urban planning

Discipline

Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

Proceedings of the 2024 IEEE International Conference on Big Data (IEEE BigData 2024)

Publisher

IEEE

City or Country

Piscataway, New Jersey, USA

Download

Share

COinS