The rapid growth of online shopping has intensified competition among logistics companies, highlighting the importance of customer expansion, i.e., identifying customers willing to establish long-term contracts. Although existing approaches frame customer expansion as a node classification task using heterogeneous graph learning to capture complex interactions between a customer and other items, it is computationally infeasible to utilize all neighboring interactions on large-scale logistics graphs. Current sub-sampling methods reduce computational load by sampling a small part of neighborhood for training. However, they introduce substantial information loss, particularly affecting high-degree nodes and decreasing predictive accuracy. To address this, we introduce NeighSqueeze, a novel approach that groups structurally and semantically similar nodes, substantially reducing the neighbors count and facilitating full-neighbor learning. NeighSqueeze consists of three modules designed to efficiently and effectively enable node grouping on billion-scale heterogeneous graphs: (1) Structure-tightness-based neighbor filtering reduces the high redundancy and complexity in similarity computations. (2) Hybrid similarity graph construction addresses the difficulty of measuring node similarity at scale; and (3) A two-level grouping strategy resolves the label dominance issue within groups. We evaluate NeighSqueeze on JD Logistics, one of the largest logistics companies in China. Compared with sub-sampling methods, our NeighSqueeze exhibits lower runtime and memory usage with full-neighbor training on the compressed graph, while simultaneously improving average precision over 28.9% in offline evaluation and increase new customer exploration rate by 18.6% in online A/B testing.

Customer expansion, i.e., growing a business's existing customer base by acquiring new customers, is critical for scaling operations and sustaining the long-term profitability of logistics companies. Although state-of-the-art works model this task as a single-node classification problem under a heterogeneous graph learning framework and achieve good performance, they struggle with extremely positive label sparsity issues in our scenario. Multi-task learning (MTL) offers a promising solution by introducing a correlated, label-rich task to enhance the label-sparse task prediction through knowledge sharing. However, existing MTL methods result in performance degradation because they fail to discriminate task-shared and task-specific structural patterns across tasks. This issue arises from their limited consideration of the inherently complex structure learning process of heterogeneous graph neural networks, which involves the multi-layer aggregation of multi-type relations. To address the challenge, we propose a Structure-Aware Hierarchical Information Sharing Framework (SrucHIS), which explicitly regulates structural information sharing across tasks in logistics customer expansion. SrucHIS breaks down the structure learning phase into multiple stages and introduces sharing mechanisms at each stage, effectively mitigating the influence of task-specific structural patterns during each stage. We evaluate StrucHIS on both private and public datasets, achieving a 51.41% average precision improvement on the private dataset and a 10.52% macro F1 gain on the public dataset. StrucHIS is further deployed at one of the largest logistics companies in China and demonstrates a 41.67% improvement in the success contract-signing rate over existing strategies, generating over 453K new orders within just two months.

An efficient last-mile delivery scheme in logistics benefits customers, couriers, and the platform. In practice, the delivery scope of a delivery station is divided into multiple areas, each of which is covered by a courier. The long distances between the delivery station and areas limit the couriers' delivery efficiency given that they need to travel back and forth multiple times a day. To solve this problem, we explore an inter-trip cooperation scheme for last-mile delivery, in which couriers traveling to the delivery station and back to corresponding areas earlier can help to take others' orders back. Coordinating the courier cooperation is challenging because we need to consider the courier's status, e.g., locations, and vehicle capacity constraint simultaneously. In this work, we design an inter-trip cooperation-based last-mile delivery system, InCo, aiming to minimize the average order delivery time. InCo includes two components: i) a time-aware spanning tree algorithm to generate the cooperation result for a group of couriers; and ii) a capacity-constrained courier grouping algorithm to optimize the courier grouping result iteratively. Extensive evaluation results with real-world order data collected from one of the largest logistics companies show that InCo improves the average saved delivery time and reduces average travel time by up to 80.2% and 28.4%, respectively, compared to baseline methods. The deployment results show InCo improves the average courier working efficiency by 21.6% to the state-of-the-practice.

Illegal parking prediction is a crucial problem to help stakeholders with better urban planning and management. Existing works advance the field by capturing complex traffic correlations from spatial and temporal perspectives using deep learning models, and achieve state-of-the-art performance. However, current works do not consider the unique perspective from the illegal parking data collection process carried out by patrol officers, which can reflect a wealth of knowledge gained from each officer's on-the-ground experiences for more effective patrol. In this paper, we propose a novel behavior-aware hypergraph convolutional network named BHIPP for city-wide illegal parking prediction. To better represent the correlations of illegal parking events from patrol officers' perspective, we construct a new patrol hypergraph integrating patrol officers' experience alongsie multi-source contextual information. Additionally, we design a behavior-aware hypergraph convolutional network, which captures the complex and high-order illegal parking event correlations with officers' patrol behaviors explicitly considered. Further, we introduce a spatial-temporal illegal parking approximation module to estimate parking violations in under-patrolled regions using both historical and multi-source contextual data. Extensive experiments on real-world datasets demonstrate the superiority of our proposed BHIPP compared with a broad range of state-of-the-art baseline models across varying spatial-temporal granularities, from both regression and ranking aspects.

Multi-modal transportation leverages the advantages of various transportation modes, leading to more efficient urban traveling services. Accurately predicting transfer times between different modes provides guidance for tasks such as trip planning and transportation management. Most existing transfer time prediction works rely on strong assumptions, e.g., predetermined routes, assumed speeds, and predefined downstream transportation timetables. However, these assumptions are hard to hold in practice due to internal factors like individual preferences and external factors like dynamic traffic conditions. These factors are dynamic and vary with location and time, presenting a significant challenge. To address this, we introduce an adaptive transfer time prediction framework, AdaTrans, to forecast personalized transfer times between upstream and downstream transportation modes. Firstly, an attribute learning module is designed to model the trends of internal factors. Then a spatial-temporal adaptive learning component is designed to learn dynamic external factors. Finally, an aggregation component with a capsule network is employed to fuse the influences of these factors. The extensive evaluation results in two real-world datasets demonstrate that AdaTrans effectively harnesses insights from internal and external factors, outperforming state-of-the-art methods by ~20%.

Logistics platforms provide real-time door-to-door order pickup services to enhance customer convenience. However, a high volume of unexpected order cancellations negatively impacts both customer satisfaction and logistics profitability. Identifying whether these cancellations are due to customers' decisions or couriers' behaviors is crucial for implementing targeted operational improvements. While traditional methods directly interpret customer-courier dialogues, incorporating situational context (e.g., couriers' historical performance and current workloads) helps us to accurately understand the hidden content. The main challenges lie in dynamically correlating couriers' varying behaviors with dialogue content. To tackle this challenge, we develop COCO, a cause identification framework for order cancellation in logistics, which includes: 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. Our extensive evaluation with 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 at JD Logistics, it has achieved an accuracy of 89.5%, further demonstrating its practical utility.

Accurate prediction of order transportation time is essential for customer satisfaction in logistics. Existing methods based on origin-destination (OD) pairs do not consider the diversity of road segments, while route-based methods may fail to account for real-time traffic conditions due to the infrequent dispatch schedules of logistics vehicles. In reality, e-commerce platforms have collaborated with multiple logistics companies for parcel delivery, providing a richer dataset that offers a more comprehensive view of real-time transportation conditions. The key insight is that data from one company can serve as internal capability detectors and data from others can act as external environment detectors. However, a significant challenge arises in inferring travel-time-correlated station pairs across different companies, especially without full disclosure of station information. To address this, we design an Adaptive cross-platform Transportation time prediction framework built upon a hypergraph structure, named AdaTrans, comprising: i) A spatial-temporal routing graph learner employs node-centric and edge-centric hyperedges to address the complex, non-pairwise correlations among stations and station pairs within and across companies; ii) A spatial-temporal graph-based transportation time predictor that utilizes multi-task learning to enhance overall transportation time prediction by leveraging the correlations between interconnected sub-tasks (i.e., dwell and travel times prediction) Extensive evaluation with real-world data collected from JD.com, a leading e-commerce platform in China, demonstrates that consolidating records from other companies reduces RMSE, MAE, and MAPE by 12.63%, 5.18%, and 16.67%, compared to state-of-the-art methods.

Individual cellular networks have been very robust to random cell tower failure due to redundant cell tower deployments. However, a large-scale clustered failure (e.g., due to fiber cut or cyber attacks) with multiple cell towers can lead to the loss of services of a cellular network. Recently, off-the-shelf smartphones can support multiple network standards, so cellular network infrastructure sharing is a promising direction to improve the service robustness under potential large-scale clustered cell tower failure. The existing work on cellular network robustness is usually limited to large-scale studies of individual networks or small-scale studies of multiple networks. In this work, we conduct the first investigation, to our knowledge, into the benefits of cross-network infrastructure sharing for enhancing robustness at a full cellular penetration rate. We design a new metric to quantify cellular network robustness with or without cross-network sharing under both random and clustered cell tower failures. We further study the impact of spatial dynamics on cellular network robustness.

Link prediction, determining if a relation exists between two entities, is an essential task in the analysis of heterogeneous graphs with diverse entities and relations. Despite extensive research in link prediction, most existing works focus on predicting the relation type between given pairs of entities. However, it is almost impractical to check every entity pair when trying to find most hidden relations in a billion-scale heterogeneous graph due to the billion squared number of possible pairs. Meanwhile, most methods aggregate information at the node level, potentially leading to the loss of direct connection information between the two nodes. In this paper, we introduce Paths2Pair, a novel framework to address these limitations for link prediction in billion-scale commercial heterogeneous graphs. (i) First, it selects a subset of reliable entity pairs for prediction based on relevant meta-paths. (ii) Then, it utilizes various types of content information from the meta-paths between each selected entity pair to predict whether a target relation exists. We first evaluate our Paths2Pair based on a large-scale dataset, and results show Paths2Pair outperforms state-of-the-art baselines significantly. We then deploy our Paths2Pair on JD Logistics, one of the largest logistics companies in the world, for business expansion. The uncovered relations by Paths2Pair have helped JD Logistics identify 108,709 contacts to attract new company customers, resulting in an 84% increase in the success rate compared to the state-of-the-practice solution, demonstrating the practical value of our framework. We have released the code of our framework at https://github.com/JQHang/Paths2Pair.

Traffic accident prediction is a crucial problem for public safety, emergency treatment, and urban management. Existing works leverage extensive data collected from city infrastructures to achieve encouraging performance based on various machine learning techniques but cannot achieve a good performance in situations with limited data (i.e., data scarcity). Recent developments in transfer learning bring a new opportunity to solve the data scarcity problem. In this paper, we design a novel cross-city transfer learning framework named CARPG for predicting traffic accidents in data-scarce cities. We address the unique challenge of predicting traffic accidents caused by its two fundamental characteristics, i.e., spatial heterogeneity and inherent rareness, which result in the biased performance of the state-of-the-art transfer learning methods. Specifically, we build cross-city region connections by jointly learning the spatial region representations for both source and target cities with an inter-city global graph knowledge transfer process. Further, we design an efficient attention-based parameter-generating mechanism to learn region-specific traffic accident patterns, while controlling the total number of parameters. Built upon that, we ensure that only relevant patterns are transferred to each target region during the knowledge transfer process and further to be fine-tuned. We conduct extensive experiments on three real-world datasets, and the evaluation results demonstrate the superiority of our framework compared with state-of-the-art baseline models.

The popularity of e-commerce has promoted the rapid development of the logistics industry in recent years. As an important step in logistics, last-mile delivery from delivery stations to customers' addresses is now mainly finished by couriers, which requires accurate workload assessment based on actual efforts. However, the state-of-the-practice assessment methods neglect a vital factor that orders with the same customer's address (i.e., Homogeneous orders) can be delivered in a group (i.e., in a single trip) or separately (i.e., in multiple trips). It would cause unfair assessment among couriers if following the same rule. Thus, grouping homogeneous order accurately in the workload assessment is significant for achieving fair courier's workload assessment. To this end, we design, implement, and deploy a nationwide homogeneous order grouping system called FHOG for improving the accuracy of homogeneous order grouping in last-mile delivery for fair courier's workload assessment. FHOG utilizes the courier's reporting behavior for order inspection, collection, and delivery to identify homogeneous orders in the delivery station simultaneously for homogeneous order grouping. Compared with the state-of-the-practice method, our evaluation shows FHOG can effectively reduce order amounts with the higher and lower assessed courier's workload. We further deploy FHOG online in 8336 delivery stations to provide homogeneous order grouping service for more than 120 thousand couriers and 12 million daily orders. The results of the two surveys show that the couriers' acceptance rate is improved by 67% with FHOG after the promotion.

Given widely adopted vehicle tracking technologies, usage-based insurance has been a rising market over the past few years. With potential discounts from insurance companies, customers voluntarily install sensing devices in their vehicles for insurance companies, which are utilized to analyze their historical driving patterns to derive the risks of future driving. However, it is challenging to characterize and predict driving patterns, especially for new users with limited data. To address this issue, we propose and evaluate a system called MoCha to accurately characterize driving patterns for usage-based insurance. The key question we aim to explore with MoCha is whether we can fully explore long-term driving patterns of new users with only limited historical data of themselves by leveraging abundant data of other users and contextual information. To answer this question, we design (i) a multi-level driving pattern modeling component to capture the spatial-temporal dependency on both individual and group level, and (ii) a multi-task learning method to utilize underlying relations of driving metrics and predict multiple driving metrics simultaneously. We implement and evaluate MoCha with real-world on-board diagnostics data from a large insurance company with more than 340,000 vehicles. Further, we validate the usefulness of MoCha by predicting driving risks based on real-world claim data in a Chinese city, Shenzhen.