Fraudulent Delivery Detection with Multimodal Courier Behavior Data in Last-Mile Delivery

The rapid growth of e-commerce has made last-mile delivery a critical service in daily life. Despite regulations mandating doorstep delivery, the pressure of penalties for delays can lead to fraudulent delivery behaviors, where couriers may report package receipt without actually deliver the package to assigned locations. Existing studies on fraud behavior detection focus on exploring user (courier) behaviors for fraud behavior detection. However, due to the inaccuracy of GPS positioning and the variability of user behavior patterns caused by dynamic environmental factors, relying solely on behavior data remains insufficient for detecting fraudulent deliveries. In this paper, we present a Multimodal Fraudulent Delivery Detection framework (MFDD), which integrates heterogeneous data from multiple agents (courier-side and user-side)-including couriers' physical behavior, digital behavior, and conversations containing customer feedback-for detecting fraudulent deliveries in the last-mile delivery. We employ attention mechanisms to extract features from each modality and use cross-modal fusion to capture complex and varied relationships between multimodal data. To further mitigate modality imbalance during training, we introduce a dynamic gradient-modulation strategy that balances learning across all modalities. We implement and evaluate MFDD on real-world, human-annotated data, achieving a 9.6% improvement in precision and a 5.8% increase in accuracy over the state-of-the-art methods. We also deploy the model in the production environment of JD Logistics, and results show that compared to existing methods, MFDD improves accuracy by 15.3%, reducing estimated annual costs by over 18.5 million CNY.

• Publication year

  2025

• Venue

  International Conference on Information and Knowledge Management

• Publication date

  2025-11-10

• Fields of study

  Business, Computer Science

• Identifiers
  DOI 10.1145/3746252.3761560
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• CoAlign: Uncertainty Calibration of LLM for Geospatial Repartition

  2025cited by this paper
• InCo: Exploring Inter-Trip Cooperation for Efficient Last-mile Delivery

  2025cited by this paper
• Scalable Area Difficulty Assessment with Knowledge-enhanced AI for Nationwide Logistics Systems

  2025cited by this paper
• MoCo: Urban User Mobile Contact Detection Based on Cellular Signaling Trace

  2025cited by this paper
• LLM4HAR: Generalizable On-device Human Activity Recognition with Pretrained LLMs

  2025cited by this paper
• VecAug: Unveiling Camouflaged Frauds with Cohort Augmentation for Enhanced Detection

  2024cited by this paper
• Aligned Side Information Fusion Method for Sequential Recommendation

  2024influential reference
• CrossHAR: Generalizing Cross-dataset Human Activity Recognition via Hierarchical Self-Supervised Pretraining

  2024cited by this paper
• Hierarchical Structure Sharing Empowers Multi-task Heterogeneous GNNs for Customer Expansion

  2024cited by this paper
• A Behavior-aware Cause Identification Framework for Order Cancellation in Logistics Service

  2024cited by this paper
• Complex-Path: Effective and Efficient Node Ranking with Paths in Billion-Scale Heterogeneous Graphs

  2024cited by this paper
• Paths2Pair: Meta-path Based Link Prediction in Billion-Scale Commercial Heterogeneous Graphs

  2024cited by this paper
• IMF: Interactive Multimodal Fusion Model for Link Prediction

  2023cited by this paper
• On Uni-Modal Feature Learning in Supervised Multi-Modal Learning

  2023cited by this paper
• UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning

  2023cited by this paper
• MultiEMO: An Attention-Based Correlation-Aware Multimodal Fusion Framework for Emotion Recognition in Conversations

  2023cited by this paper
• Sequence As Genes: An User Behavior Modeling Framework for Fraud Transaction Detection in E-commerce

  2023cited by this paper
• Group-based Fraud Detection Network on e-Commerce Platforms

  2023cited by this paper
• Dynamic Multimodal Fusion via Meta-Learning Towards Micro-Video Recommendation

  2023cited by this paper
• VeLP: Vehicle Loading Plan Learning from Human Behavior in Nationwide Logistics System

  2023cited by this paper
• AUC-oriented Graph Neural Network for Fraud Detection

  2022cited by this paper
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers

  2022cited by this paper
• Balanced Multimodal Learning via On-the-fly Gradient Modulation

  2022cited by this paper
• H2-FDetector: A GNN-based Fraud Detector with Homophilic and Heterophilic Connections

  2022cited by this paper
• CoMiner: nationwide behavior-driven unsupervised spatial coordinate mining from uncertain delivery events

  2022influential reference
• Impact of smart locker use on customer satisfaction of online shoppers in Vietnam

  2022cited by this paper
• Live-Streaming Fraud Detection: A Heterogeneous Graph Neural Network Approach

  2021cited by this paper
• PolyViT: Co-training Vision Transformers on Images, Videos and Audio

  2021cited by this paper
• Online Credit Payment Fraud Detection via Structure-Aware Hierarchical Recurrent Neural Network

  2021cited by this paper
• Nationwide Deployment and Operation of a Virtual Arrival Detection System in the Wild

  2021cited by this paper
• Early vs Late Fusion in Multimodal Convolutional Neural Networks

  2020cited by this paper
• Fraud Transactions Detection via Behavior Tree with Local Intention Calibration

  2020cited by this paper
• Spatio-Temporal Attention-Based Neural Network for Credit Card Fraud Detection

  2020influential reference
• On the Benefits of Early Fusion in Multimodal Representation Learning

  2020cited by this paper
• Feature-level Deeper Self-Attention Network for Sequential Recommendation

  2019cited by this paper
• SAFE: A Neural Survival Analysis Model for Fraud Early Detection

  2018cited by this paper
• Attention is All you Need

  2017cited by this paper
• Convolutional Neural Networks for Sentence Classification

  2014cited by this paper
• LIBSVM: A library for support vector machines

  2011cited by this paper

• No citing papers are available for this paper.