Year: 2024
Type: conference-paper
Abstract: Demand prediction in the context of food delivery platforms, is the process of forecasting future food order volumes to help food delivery platforms allocate resources more effectively.Accurate demand prediction in online food delivery platforms is vital for optimizing resource management, lowering operational costs, and reducing the environmental impact associated with over-deployment of delivery agents.By anticipating fluctuations in order volumes, platforms can better plan delivery routes, delivery agent requirement, reduce drivers' idle time, and minimize fuel consumption, making the operation more sustainable.Despite its importance, the research on demand prediction specifically aimed at optimizing food delivery platforms remains limited.Our study addresses this gap by leveraging Graph Neural Networks (GNNs) to forecast demand in food delivery services, focusing on enhancing efficiency and sustainability in delivery operations.Tested on a real-world dataset from the Meituan platform, our model captures complex demand patterns, with an aim to improve the overall performance of food delivery systems.
Authors: Rabia Latief Bhat, Iqra Altaf Gillani
Institution: National Institute of Technology Srinagar
Language: English
Subfield: Building and Construction
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4411624611