CLUSTERING-BASED METHODS FOR DATA-DRIVEN OPTIMIZATION IN URBAN COURIER LOGISTICS

With the rapid development of cities and their infrastructure, the demand for high-quality urban deliveries is increasing at the same rate. This work explores the possibilities of dynamically allocating delivery zones for courier deliveries based on data provided by the courier company. Traditional manually created delivery zones often do not ensure that the picture is relevant to the real situation in the city (weather, traffic, roads, etc.). This study presents the results of how K-Means and DBSCAN clustering algorithms can contribute to the dynamic distribution of delivery zones in clusters. The comparative analysis includes consideration of such indicators as Silhouette value and computational complexity of Big-O Notation. The results show that the K-Means algorithm creates structured and uniform clusters, while DBSCAN shows results in defining flexible clusters based on the density of data in the region. Multi-level DBSCAN provides an opportunity to reduce the concentration of “noise”, thereby increasing the coverage of all delivery points. The results obtained highlight the advantages of using clustering algorithms in creating dynamic delivery zones to improve the distribution of orders between couriers and reduce operating costs. Further research should include obtaining continuous real-time data flow to monitor the operation of algorithms in a dynamic environment.

1. Kinelski G. Smart-city trends in the environment of sustainability as support for decarbonization processes // Polityka Energetyczna. – 2022. – Vol. 25. – No. 2.

2. Janjevic M., Winkenbach M. Characterizing urban last-mile distribution strategies in mature and emerging e-commerce markets // Transportation Research Part A: Policy and Practice. – 2020. – Vol. 133. – P. 164–196.

3. Russo F., Comi A. Urban courier delivery in a smart city: the user learning process of travel costs enhanced by emerging technologies // Sustainability. – 2023. – Vol. 15. – No. 23. – P. 16253.

4. Monferdini L., Bottani E. Examining the Response to COVID-19 in Logistics and Supply Chain Processes: Insights from a State-of-the-Art Literature Review and Case Study Analysis // Applied Sciences. – 2024. – Vol. 14. – No. 12. – P. 5317.

5. Li Z., Gu W., Meng Q. The impact of COVID-19 on logistics and coping strategies: a literature review // Regional Science Policy & Practice. – 2023. – Vol. 15. – No. 8. – P. 1768–1795.

6. Yang J. et al. Optimization of real-time traffic network assignment based on IoT data using DBN and clustering model in smart city // Future Generation Computer Systems. – 2020. – Vol. 108. – P. 976–986.

7. Rahman M. A. et al. Logistics Hub Location Optimization: A K-Means and P-Median Model Hybrid Approach Using Road Network Distances // arXiv preprint arXiv:2308.11038. – 2023.

8. Mandal M.P., Archetti C. A Decomposition Approach to Last Mile Delivery Using Public Transportation Systems // arXiv preprint arXiv:2306.04219. – 2023.

9. Barreto S. et al. Using clustering analysis in a capacitated location-routing problem //European journal of operational research. – 2007. – Vol. 179. – No. 3. – P. 968–977.

10. Mandal M.P., Archetti C. A Decomposition Approach to Last Mile Delivery Using Public Transportation Systems // arXiv preprint arXiv:2306.04219. – 2023.

11. Hess A., Spinler S., Winkenbach M. Real-time demand forecasting for an urban delivery platform // Transportation Research Part E: Logistics and Transportation Review. – 2021. – Vol. 145. – P. 102147.

12. Sawik B. Optimizing Last-Mile Delivery: A Multi-Criteria Approach with Automated Smart Lockers, Capillary Distribution and Crowdshipping // Logistics. – 2024. – Vol. 8. – No. 2. – P. 52.

13. Google Sites. K-means clustering algorithm. URL: https://sites.google.com/site/dataclusteringalgorithms/k-means-clustering-algorithm (Retrieved January 31, 2025).

14. DataCamp. DBSCAN clustering algorithm URL: https://www.datacamp.com/tutorial/dbscanclustering-algorithm (Retrieved January 31, 2025).

15. KDnuggets. DBSCAN clustering algorithm in machine learningю – 2020, апрель. URL: https://www.kdnuggets.com/2020/04/dbscan-clustering-algorithm-machine-learning.html (Retrieved January 31, 2025).

16. Shahapure K.R., Nicholas C. Cluster quality analysis using silhouette score // 2020 IEEE 7th international conference on data science and advanced analytics (DSAA). – IEEE, 2020. – С. 747–748.

17. Ogbuabor G., Ugwoke F. N. Clustering algorithm for a healthcare dataset using silhouette score value // Int. J. Comput. Sci. Inf. Technol. – 2018. – Vol. 10. – No. 2. – P. 27–37.

18. Analytics Vidhya. K-means: Getting the optimal number of clusters. – 2021, май. URL: https://www.analyticsvidhya.com/blog/2021/05/k-mean-getting-the-optimal-number-of-clusters/ (Retrieved January 31, 2025).

19. GeeksforGeeks. Elbow method for optimal value of k in K-means. URL: https://www.geeksforgeeks.org/elbow-method-for-optimal-value-of-k-in-kmeans/ (Retrieved January 31, 2025).

20. GeeksforGeeks. DBSCAN clustering in ML: Density-based clustering. URL: https://www.geeksforgeeks.org/dbscan-clustering-in-ml-density-based-clustering/ (Retrieved January 31, 2025).

21. Srilekha S., Priyadharshini P., Adhilakshmi M. Comparative evaluation of K-Means, hierarchical clustering, and DBSCAN in blood donor segmentation // International Journal for Multidisciplinary Research. – 2024. – Vol. 6. – No. 4. – P. 1–5. https://doi.org/10.36948/ijfmr.2024.v06i04.26755.