Publication Type

PhD Dissertation

Version

publishedVersion

Publication Date

10-2025

Abstract

This study develops a data-driven framework for optimal retail store location planning that integrates road network analysis, mobility data and optimization techniques. By addressing the limitations of traditional approaches that rely on outdated census data and manual site selection, this research offers a scalable and adaptable solution for retail expansion in diverse urban environments. Chapters 1 and 2 establish the foundational context and theoretical underpinnings of this research. Chapter 1 introduces the research problem and motivation, highlighting the limitations of existing approaches and defining three key research objectives: automating candidate site identification, improving footfall estimation, and developing a scalable multi-site selection method. Chapter 2 provides a critical review of literature across relevant domains, identifying significant gaps in community identification methods, store footfall prediction techniques and competitive facility location models. Chapter 3 proposes a framework for spatial partitioning of large-scale road networks and identifying communities. A community is defined as a distinct geographical area identified through road network analysis, representing a cluster of interconnected roads that serves a common population group. To this end, we have developed a three-stage procedure that first partitions the road network using the Louvain method, then outlines each partition’s boundary using Uber H3 grids before classifying each partition using K-means clustering. Experimental results in Da Nang, Vietnam, show that the proposed method can partition and organize a large-scale road network into various communities. Chapter 4 explores the augmentation of footfall estimation with the integration of mobility data to create population-weighted centroids for the communities. Our findings are then used to enhance the Huff Model, commonly used in site selection and footfall estimation. Our approach demonstrated the vast potential residing within big data where we harness the power of mobility data and road network information, offering a cost-effective and scalable alternative. Our approach obviates the reliance on outdated census data and government urban planning records. Chapter 5 outlines a data-driven methodology that automates facility allocation over large search spaces such as a city without relying on pre-selection of candidate sites by humans. Using the Adaptive Large Neighborhood Search (ALNS) algorithm, we want to achieve near-optimal solutions without requiring an exhaustive evaluation of large solution space. Each community, distinguished by its unique connectivity and demographics, is considered a candidate location. Population data is integrated with road network to provide a proxy of population count each community, eliminating the reliance on census data. In Chapter 6, the framework developed in earlier chapters is integrated into a practical application to enable data-driven decisions for retail expansion. The application transforms traditional location planning while retaining human expertise in final decision-making. The framework developed combines community detection, enhanced Huff Model and ALNS optimization into a cohesive, data-driven approach. This research not only contributes methodological innovations to the academic literature but also offers practical solutions to business challenges in retail expansion, allowing for more efficient, accurate and scalable decisions that adapt to diverse urban contexts.

Keywords

Retail location planning, Competitive facility location, Adaptive Large Neighborhood Search, Community detection, Huff Model

Degree Awarded

Doctor of Engineering

Discipline

Asian Studies | Databases and Information Systems | Numerical Analysis and Scientific Computing | Sales and Merchandising

Supervisor(s)

TAN, Kar Way; LAU, Hoong Chuin

First Page

1

Last Page

137

Publisher

Singapore Management University

City or Country

Singapore

Copyright Owner and License

Author

Download

Share

COinS