Towards an Acceptance Probability-Aware Order Bundle in Crowdsource Food Delivery Service
Feihong Huang, Wei Jiang · 2024
With the increasing popularity of mobile internet, on-demand food delivery platforms such as Meituan, Ele.me, and DoorDash have experienced significant growth both domestically and internationally. Crowdsourcing, as a delivery method that can mobilize idle labor in society and reduce operating costs for businesses, has become the preferred choice for these platforms. However, the high order rejection rate by crowdsourced riders poses a challenge. To address this issue, this paper proposes a method for order bundling based on the probability of riders accepting orders. Firstly, the orders are grouped based on their similarity, and then a set of order package is generated with the objective of maximizing the probability of order acceptance. The experimental results confirm the effectiveness of this method in improving riders’ willingness to accept orders and enhancing system efficiency.