COCO+: A Behavior-Aware Cause Identification Framework for Order Cancellation in Logistics Service

Shuxin Zhong, Hongyu Lin, Yahan Gu, Wenjun Lyu, Yunhuai Liu, Wang Lu, Tian He, Kaishun Wu, Desheng Zhang

Abstract: Logistics platforms increasingly offer real-time door-to-door order pickup services to enhance customer convenience. However, a high volume of unexpected order cancellations negatively impacts both customer experience and logistics profitability. Accurately identifying whether these cancellations stem from customers' decisions or couriers' non-compliant behaviors is essential for implementing targeted operational improvements. Simply interpreting customer-courier dialogues, however, risks being one-sided. The primary challenge lies in adaptively correlating dialogue content with the varying behaviors of couriers. To address this, we develop COCO, a cause identification framework for order cancellation in logistics that consists of: i) Multi-modal features exploration, which analyzes dialogues and couriers' behaviors (both historical and current); ii) Multi-modal features aggregation, which uses a hierarchical attention mechanism to adaptively capture the dynamic correlations within dialogues and behaviors; iii) LLM-enhanced refinement, which leverages Large Language Models to accurately process a large number of unlabeled dialogues, significantly enhancing COCO's generalization and performance. To further enhance COCO's effectiveness, we introduce COCO+, which incorporates customers' behaviors to better identify customer-related causes. Our extensive evaluation with data collected from JD Logistics demonstrates COCO+'s exceptional performance, achieving an 12.2% increase in precision and a 9.1% improvement in recall over existing methods. Furthermore, after deploying COCO+ in real-world scenarios, we observed an adoption rate of 89.5% and improved on-time pickups even under high-demand conditions, as confirmed through A/B testing.

External IDs:doi:10.1109/tmc.2026.3652201