2653. A hybrid optimization approach for bulk order allocation in fulfillment centers in Trendyol
Invited abstract in session TA-47: Retail Inventory Management, stream Retail Operations.
Tuesday, 8:30-10:00Room: Parkinson B08
Authors (first author is the speaker)
| 1. | Fikret Batu Sagay
|
| Data Science - Core Ops, Trendyol | |
| 2. | Mehmet Orhan YILDIRIM
|
| 3. | Betül Ahat
|
| Data Science, Trendyol | |
| 4. | Ahmet Çınar
|
| Data Science, Trendyol | |
| 5. | Meltem Sanisoğlu
|
Abstract
In e-commerce fulfillment, B2C orders are traditionally allocated in real-time, one by one, as they are placed. While this ensures immediate processing, it disregards potential efficiency gains from bulk order allocation—where multiple orders are assigned simultaneously within a predefined time window or after reaching a threshold. By clustering orders, fulfillment centers can reduce travel distances, enhance picking efficiency, and optimize resource utilization.
This study presents a metaheuristic approach using Simulated Annealing for bulk order allocation, designed to optimize the picking process in a limited amount of time. We also introduce a mixed-integer programming model to monitor the efficiency of the proposed metaheuristic. The model accounts for key constraints, including order proximity, picking efficiency, and warehouse capacity, ensuring an optimized allocation process. While bulk allocation introduces computational complexity, the proposed approach leverages advanced optimization techniques to balance solution speed and effectiveness.
The findings demonstrate that strategic bulk allocation can significantly enhance fulfillment efficiency up to 10%, reducing operational costs and improving order processing workflows in high-volume e-commerce environments.
Keywords
- Metaheuristics
- Inventory
- Programming, Mixed-Integer
Status: accepted
Back to the list of papers