1477. Enhancing Social Aid Delivery with Public Transport: A Learning-based Optimization Framework
Invited abstract in session WD-55: Decision Support for Complex Humanitarian Crises, stream Humanitarian Operations.
Wednesday, 14:30-16:00Room: Liberty 1.09
Authors (first author is the speaker)
| 1. | Vedat Bayram
|
| Kent Business School, Department of Analytics, Operations and Systems, University of Kent | |
| 2. | Barış Yıldız
|
| Industrial Engineering, Koç Üniversity | |
| 3. | VAHID Akbari
|
| Business School, University of Nottingham | |
| 4. | Ali Dogru
|
| School of Management, University of Southern Mississippi | |
| 5. | Pinar Keskinocak
|
| Georgia Tech |
Abstract
Social aid programs require regular distribution of aid in non-disaster conditions to beneficiaries living in urban areas where poverty and hunger concentrate. Effective social aid distribution in large urban areas faces critical logistical challenges, including high transportation costs, inefficient resource allocation, and limited fleet capacity. In this study, we propose a novel two-echelon distribution system that integrates public transportation networks (PTNs) and volunteer couriers to enhance efficiency, cost-effectiveness, and sustainability. Our approach employs a learning-based decomposition methodology, which partitions the problem into a PTN-based backbone model and last-mile routing subproblems, leveraging machine learning to optimize delivery flows. We collaborate with the Ankara Metropolitan Municipality to benchmark our system against current social aid distribution practices. Our findings underscore the potential of integrating PTNs into urban social logistics, offering a scalable, cost-efficient, and environmentally sustainable solution for aid distribution in metropolitan areas.
Keywords
- Humanitarian Applications
- Transportation
- Machine Learning
Status: accepted
Back to the list of papers