Authors : Michael Oppong; Mathias Vera; Paul Onyekwuluje

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/5b7h8xpm

Scribd : https://tinyurl.com/yv7xy67s

DOI : https://doi.org/10.38124/ijisrt/26apr477

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Last-mile delivery — the final leg from a Regional Distribution Center (RDC) to an individual store — represents the costliest and most operationally complex segment of the retail supply chain, accounting for an estimated 41% of total logistics expenditure in large-format retail. This study presents a predictive analytics and operations research framework, implemented across six RDC regions using over 54 million rows of operational data, to simultaneously optimize delivery routing, store-level product allocation, and compliance monitoring. The methodology integrates time-series forecasting, KMeans demand segmentation, linear programming (PuLP), and unsupervised anomaly detection (Isolation Forest, Z-score) within a Google BigQuery data infrastructure, with results surfaced through Tableau and Power BI executive dashboards.

Keywords : Last-Mile Delivery, Distribution Optimization, Linear Programming, K-Means Segmentation, Isolation Forest, Anomaly Detection, Supply Chain Compliance, U.S. Logistics Economics

References :

1. Adewole, A., & Tettey, W. (2020). Anomaly detection in retail inventory management using machine learning. Journal of Retail Analytics, 14(2), 88–104.
2. Aglin, G., Perakis, G., & Trichakis, N. (2020). Dynamic pricing and assortment under a contextual linear bandit demand model. Operations Research, 69(1), 126–142.
3. Bertsimas, D., & Tsitsiklis, J. N. (1997). Introduction to Linear Optimization. Athena Scientific.
4. Bureau of Labor Statistics (BLS). (2023). Operations Research Analysts: Occupational Outlook Handbook. U.S. Department of Labor.
5. Chopra, S., & Meindl, P. (2016). Supply Chain Management: Strategy, Planning, and Operation (6th ed.). Pearson.
6. Council of Supply Chain Management Professionals (CSCMP). (2023). State of Logistics Report. CSCMP Research.
7. Dantzig, G. B., & Ramser, J. H. (1959). The Truck Dispatching Problem. Management Science, 6(1), 80–91.
8. Department of Transportation (DOT). (2022). National Freight Strategic Plan: Last-Mile and Urban Logistics. U.S. DOT Bureau of Transportation Statistics.
9. Federal Reserve Board. (2023). Supply Chain Distortion and Core Goods Inflation: A Decomposition. Finance and Economics Discussion Series.
10. Gevaers, R., Van de Voorde, E., & Vanelslander, T. (2011). Characteristics and typology of last-mile logistics. Nectar Logistics, 8, 2–12.
11. IHL Group. (2023). Retail's $1.77 Trillion Inventory Distortion Problem. IHL Research Report.
12. Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008). Isolation Forest. Proceedings of the 8th IEEE International Conference on Data Mining, 413–422.
13. Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2018). Statistical and Machine Learning Forecasting Methods: Concerns and Ways Forward. PLOS ONE, 13(3).
14. National Retail Federation (NRF). (2024). Retail Security Survey and Annual Sales Data. NRF Research Center.
15. White House. (2021). Building Resilient Supply Chains, Revitalizing American Manufacturing, and Fostering Broad-Based Growth. 100-Day Review Report. Executive Office of the President.