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.

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.

In last-mile logistics, couriers are typically assigned fixed zones to perform door-to-door deliveries. In practice, packages in some delivery zones might not be fulfilled on time due to couriers taking irregular leave for sickness or higher-priority task assignments, e.g., services for VIPs and regulatory training. Beyond the costly real-world practice, i.e., hiring temporary workers, analysis of historical data reveals that a daily delivery task rescheduling among on-duty couriers can be a cost-effective and efficient alternative. It involves individual workload assessments and delivery task assignments, both of which existing methods can not address adequately: (i) Existing courier workload assessment methods are not tailored for downstream optimization tasks, leading to poor performance. (ii) Efficiency-oriented task assignment methods may lead to unfair workload among the couriers. To address the above two limitations, in this paper, we propose D3-TR, a data-driven method for task reassignment among present couriers. Firstly, we design a consistency-guided predictor that can quickly and precisely predict the workload of couriers. Secondly, based on this predictor, we design a workload-aware genetic algorithm to solve the optimal task allocation problem. Experimental results underscore the superiority of our method over several baselines. Furthermore, real-world deployment on millions of orders demonstrates the effectiveness of our solution, yielding an average of 3.9% improvement in the on-time delivery rate.

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.

A long-standing challenge for pushing sensor-based human activity recognition (HAR) to industrial usage is the distribution shift between training data and testing data: significant variations in data distribution lead to a notable decline in performance. Recently, Large Language Models (LLMs) have demonstrated exceptional generalization capability, which provides a new opportunity to mitigate the distribution shift problem of HAR. However, since LLMs are inherently designed and trained on textual data, their potential to enhance generalization in HAR applications remains an open question. In this paper, we introduce LLM4HAR, a novel LLM-based model to improve cross-domain HAR. LLM4HAR consists of three main modules: (i) the Sensor Data Adaptation module, which aligns IMU signals with LLMs via sensor embedding(ii) the Sensor Knowledge Learning module, which injects sensor knowledge into LLMs for activity recognition, and (iii) the Efficiency Enhancement module, which employs a partial training strategy and reduces the model size by more than 10 times. Extensive evaluations show that LLM4HAR outperforms the existing methods by 13.82% in average F1 score, demonstrating the feasibility and effectiveness of transferring knowledge from pretrained LLMs to enhance HAR. Further, LLM4HAR has been adopted by JD Logistics to support downstream applications such as Courier Welfare Improvement and Map Data Generation.

Textual description of a physical location, commonly known as an address, plays an important role in location-based services(LBS) such as on-demand delivery and navigation. However, the prevalence of abnormal addresses, those containing inaccuracies that fail to pinpoint a location, have led to significant costs. Address rewriting has emerged as a solution to rectify these abnormal addresses. Despite the critical need, existing address rewriting methods are limited, typically tailored to correct specific error types, or frequently require retraining to process new address data effectively. In this study, we introduce AddrLLM, an innovative framework for address rewriting that is built upon a retrieval augmented large language model. AddrLLM overcomes aforementioned limitations through a meticulously designed Supervised Fine-Tuning module, an Address-centric Retrieval Augmented Generation module and a Bias-free Objective Alignment module. To the best of our knowledge, this study pioneers the application of LLM-based address rewriting approach to solve the issue of abnormal addresses. Through comprehensive offline testing with real-world data on a national scale and subsequent online deployment, AddrLLM has demonstrated superior performance in integration with existing logistics system. It has significantly decreased the rate of parcel re-routing by approximately 43%, underscoring its exceptional efficacy in real-world applications.

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.

With the development of the logistics industry, the user base of logistics services has expanded swiftly. This rapid increase in user scale presents significant challenges for logistics business management. A fundamental issue in such scenarios is audience expansion, which aims to find users willing to sign long-term services with logistics companies to foster business growth. Existing methods in addressing audience expansion mainly assume user modeling is entangled and neglects the inherent community structure among users. Due to these limitations, the effectiveness of traditional methods in achieving accurate user expansion is often restricted. Our work introduces a novel heterogeneous graph-based model, named Hi-DGN, which concentrates on the Hierarchical information propagation and aggregation in Disentangled Graph Networks for audience expansion. It consists of three main components: (i) the disentangled embedding layer to decouple user representations into different aspects, enabling the extraction of differentiated features; (ii) the hierarchical information propagation module partitions individual nodes into distinct groups and propagates information from group nodes to individual nodes hierarchically to capture diverse granularity representations; and (iii) the aggregation module to fuse all relation-specific embeddings to generate global node embeddings. Extensive experiments on two real-world datasets demonstrate the effectiveness of our method in various evaluation settings.

Recommendation systems play a crucial role in both industrial applications and research fields, which target to understand user preferences and intentions to provide personalized services. Compared to conventional recommendations, repurchase recommendations aim to suggest suitable products to users that they used to buy based on their intention evolution. Existing research on product recommendation can mainly be divided into behavior sequence-based methods and graph-based methods. Although these methods represent user interests and preference features effectively, they still fail to model repurchase behaviors because (i) the environment causing repurchase intention change is neglected and (ii) the lack of feedback after purchasing makes it difficult to learn the impacts of diverse behaviors. To comprehensively consider these limitations, we design a D ual I ntention-aware F usion N etwork framework (DIFN) to understand the effects of environment and after-purchasing feedback on users' intentions. Firstly, a hierarchical graph-based multi-level relational attention module is designed to effectively extract basic user features and spatial features from complex environmental information. Then, we introduce a behavior intention module and a usage intention module for different types of feedback data. Finally, we propose a dual intention fusion network that effectively fuses user basic features with spatial attributes and user intention features with temporal attributes for recommendation. Comprehensive evaluations on real-world datasets show that our method exceeds state-of-the-art baselines, which show an average of 8.2% improvements in different metrics.

In on-demand delivery,online orders are delivered by couriers from merchants to customers within a short time (e.g., 45 minutes). An important task is to provide an efficient order dispatching solution. Existing studies focus on scenarios with stable routing behavior using pre-determined courier-order matching before delivery while ignoring real-time dynamics during delivery. In this work, we leverage courier-courier encounter events as an opportunity to enable cooperative order dispatching (i.e., conducting order transfers among couriers during delivery) for better delivery efficiency. However, it is non-trivial to conduct encounter-aware cooperative order dispatching in real-time dynamics due to two major challenges: (i) the dynamic nature of encounters in diverse real-world scenarios, and (ii) global delivery efficiency optimization by local order transfers. To address the above challenges, we design a detection-driven cooperative dispatching framework, called DECO. Specifically, we design (i) a Received Signal Strength Indicator (RSSI) variance-based state encoder to model encounter dynamics, (ii) an encounter event selector to choose encounter scenarios, (iii) a time-constrained order mask module to filter unsuitable orders, and (iv) an encounter-aware order transfer scheduler to make detailed order transfer decisions. Extensive experiments on real-world data from two large companies (i.e., JD Logistics, Eleme) show that DECO outperforms other baselines.Real-world deployment results at JD Logistics show that DECO improves the order overdue rate by 4.8%.

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.

Urban traffic is subject to disruptions that cause extended waiting time and safety issues at signalized intersections. While numerous studies have addressed the issue of intelligent traffic systems in the context of various disturbances, traffic signal malfunction, a common real-world occurrence with significant repercussions, has received comparatively limited attention. The primary objective of this research is to mitigate the adverse effects of traffic signal malfunction, such as traffic congestion and collision, by optimizing the control of neighboring functioning signals. To achieve this goal, this paper presents a novel traffic signal control framework (MalLight), which leverages an Influence-aware State Aggregation Module (ISAM) and an Influence-aware Reward Aggregation Module (IRAM) to achieve coordinated control of surrounding traffic signals. To the best of our knowledge, this study pioneers the application of a Reinforcement Learning(RL)-based approach to address the challenges posed by traffic signal malfunction. Empirical investigations conducted on real-world datasets substantiate the superior performance of our proposed methodology over conventional and deep learning-based alternatives in the presence of signal malfunction, with reduction of throughput alleviated by as much as 48.6%.

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.

As location-based services (LBS) have grown in popularity, more human mobility data has been collected. The collected data can be used to build machine learning (ML) models for LBS to enhance their performance and improve overall experience for users. However, the convenience comes with the risk of privacy leakage since this type of data might contain sensitive information related to user identities, such as home/work locations. Prior work focuses on protecting mobility data privacy during transmission or prior to release, lacking the privacy risk evaluation of mobility data-based ML models. To better understand and quantify the privacy leakage in mobility data-based ML models, we design a privacy attack suite containing data extraction and membership inference attacks tailored for point-of-interest (POI) recommendation models, one of the most widely used mobility data-based ML models. These attacks in our attack suite assume different adversary knowledge and aim to extract different types of sensitive information from mobility data, providing a holistic privacy risk assessment for POI recommendation models. Our experimental evaluation using two real-world mobility datasets demonstrates that current POI recommendation models are vulnerable to our attacks. We also present unique findings to understand what types of mobility data are more susceptible to privacy attacks. Finally, we evaluate defenses against these attacks and highlight future directions and challenges.

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.

Empowered by the widespread adoption of Internet of Things (IoT) devices and smartphones, last-mile delivery services have evolved to accommodate both delivery and pickup tasks. An essential challenge in last-mile delivery is efficiently planning routes for couriers to handle pre-scheduled delivery requests as well as stochastic pickup requests. Existing work approaches this problem by either adjusting routes on the fly when new requests arise or preplanning routes based on predicted future pickup requests. However, these methods either compromise the optimality of planned routes or heavily rely on the accuracy of predictions. In this work, we take conformal prediction as an opportunity to address the issue of prediction uncertainty. We design ROPU, a novel courier route planning framework for logistics systems that incorporates conformal prediction into reinforcement learning. Our work advances the existing work from two aspects: (i) Pickup request prediction utilizes spatial-temporal conformal prediction to capture historical pickup request patterns, providing a unified spatial-temporal conformal interval with high confidence (ii) A spatial-temporal attention network assesses location importance from various perspectives and enables the actor to perceive time and integrate the spatial-temporal conformal interval. We implement and evaluate ROPU on one of the largest logistics platforms. Extensive experiment results demonstrate that our method outperforms other state-of-the-art methods with improvements of at least 30.49% in the pickup overdue rate, 25.00% in the delivery overdue rate, and 5.49% in the traveling distance metric.

Node ranking in heterogeneous graphs, which quantifies the relative importance of nodes, can often be improved by incorporating information from relevant paths. Graph database and heterogeneous graph neural network (HGNN) are two main approaches to better solve this problem. Graph databases support efficient path queries for flexible path types but require manual design to combine results for node ranking. Conversely, current HGNNs can automatically integrate semantic information from multiple linear path types for accurate node ranking. However, our experiments show that they fail to outperform a multi-layer perceptron model that utilizes features extracted from multiple nonlinear conditional paths, which can be handled by graph databases. Therefore, we aim to enable HGNN to take advantage of these path types for better performance. However, HGNNs require a generalized path schema to define the structure of input paths, and incorporating each additional path type will significantly increase the required system memory and sampling time for HGNNs. To address these limitations, we introduce CompNode, a novel framework based on a new unified path schema definition called Complex-path, which is used to describe all the required path types, including nonlinear conditional path types. Then, we design a pre-aggregation method to reduce the required system memory and sampling time by pre-aggregating the same type of complex-path. Furthermore, we develop a model that combines semantic information from all aggregated complex-paths for accurate node ranking. Real-world experiments on identifying top potential high-value customers show CompNode outperforms state-of-the-art HGNNs by 20% in average precision and the previously deployed graph database method by 252% in success rate.

Geocoding, associating textual addresses with corresponding GPS coordinates, is vital for many location-based services (e.g., logistics, ridesharing, and social networks). One of the most common Geocoding solutions is using commercial map services such as Google Maps. However, this is typically not practical for some location-based service providers due to real-world challenges like commercial competition and high costs (recurring fees). In this paper, we design a new cost-effective Geocoding framework to automatically infer the geographic coordinates from textual addresses. To achieve this, we take the E-Commerce logistics service as a concrete scenario and designCoMiner, an unsupervised coordinate inference framework based on textual address data, delivery event data, and courier trajectory data.CoMinerincludes three main components, (1) A POI-level clustering model, (2) A Delivery Mobility Graph (DMG), and (3) A behavior-driven address ranking model. Furthermore, we designCoMiner-W, a coordinates mining algorithm based on WiFi data, to further enhance the effectiveness ofCoMiner. We conduct extensive experiments on three large-scale datasets whereCoMineroutperforms the state-of-the-art methods by 20.3%. Moreover, we have designed an abnormal delivery event detection system based onCoMinerand deployed it at JD Logistics, which brings a significant reduction in abnormal delivery event rates.

Fine-grained community-building information, such as building names and accurate geographical coordinates, is critical for a range of practical applications like navigation and door-to-door services (e.g., on-demand delivery and last-mile delivery). A common practice of traditional methods to gather community-building information usually relies on manual collection, which is typically labor-intensive and time-consuming. To address these issues, we utilize the massive data generated from e-commerce delivery services and design a framework, AutoBuild, for fine-grained large-scale community-building labeling. AutoBuild consists of two main components: (i) a Location Candidate Detection Module that identifies potential building names and coordinates from multi-source delivery data, and (ii) a Progressive Building Matching Model that employs trajectory modeling, human behavior analysis, and heterogeneous graph alignment to match building names and coordinates. To evaluate the performance of AutoBuild, we applied it to two real-world multi-modal datasets from Beijing City and Chengdu City. The results reveal that AutoBuild significantly outperforms multiple baseline models by 50-meter accuracy of 81.8% and 100-meter accuracy of 95.9% in Beijing City. More importantly, we conduct a real-world case study to demonstrate the practical impact of AutoBuild in last-mile delivery.

Points of Interest (POIs), such as entertainment, dining, and living, are crucial for urban planning and location-based services. However, the high dynamics and expensive updating costs of POIs pose a key roadblock for their urban applications. This is especially true for developing countries, where active economic activities lead to frequent POI updates (e.g., merchants closing down and new ones opening). Therefore, POI updating, i.e., detecting new POIs and different names of the same POIs (alias) to update the POI database, has become an urgent but challenging problem to address. In this paper, we attempt to answer the research question of how to detect and update large-scale POIs via a low-cost approach. To do so, we propose a novel framework called UrbanPOI, which formulates the POI updating problem as a tagging and detection problem based on multi-modal logistics delivery data. UrbanPOI consists of two key modules: (i) a hierarchical POI candidate generation module based on the POINet model that detects POIs from shipping addresses; and (ii) a new POI detection module based on the Siamese Attention Network that models multi-modal data and crowd intelligence. We evaluate our framework on real-world logistics delivery datasets from two Chinese cities. Extensive results show that our model outperforms state-of-the-art models in Beijing City by 26.2% in precision and 10.7% in F1-score, respectively.

Logistics audience expansion, the process for logistics companies to find potential long-term customers, is one of the most important tasks for business growth. However, existing methods for conventional audience expansion fall short due to two significant challenges, the intricate interplay of multiple complex factors in the logistics scenario and the emphasis on long-term logistics service usage instead of one-time promotions. To address the above limitations, we design LOGAE-TKG, a logistics audience expansion method based on a temporal knowledge graph, which consists of three components: (i) a temporal logistics knowledge graph pre-trained model to model the effect of multiple complex factors and build a solid logistics knowledge base for contracting and usage prediction; (ii) an intention learning model with data augmentation-based comparison to capture the contracting intention; (iii) a future pattern discovery model to uncover post-contract patterns. We evaluate and deploy our method on the JingDong e-commerce platform. Extensive offline experiment results and real-world deployment results demonstrate the effectiveness of our method.

Identifying regional driving risks is important for real-world applications such as driving safety warning applications, public safety management, and insurance company premium pricing. Previous approaches are either based on traffic accident reports or vehicular sensor data. They either fail to identify potential risks, such as near-miss collisions, which would need other important measurements (e.g., hard break, acceleration, etc.), or fail to generalize to cities without vehicular sensor data, severely limiting their practicality. In this work, we address these two challenges and successfully identify regional driving risks in a target city without vehicular sensor data via cross-city transfer learning. Specifically, we design a novel framework RiskTrans by optimizing both the predictor and the relationship between cities to achieve transfer learning. We advance the existing works from two aspects: (i) we achieve it in a transductive manner without accessing labeled data in the target cities; (ii) we identify and address the problem of negative transfer in cross-city transfer learning, a prominent issue that is often (surprisingly) neglected in previous works. Finally, we conduct extensive experiments based on data collected from 175 thousand vehicles in six cities. The results show RiskTrans outperforms baselines by at least 50.2% and reduces negative transfer by 49.4%.

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.

Warehouse-distribution integration has been adopted by many e-commerce retailers (e.g., Amazon, TAOBAO, and JD) as an efficient business mode. In warehouse-distribution integration e-commerce, one of the most important problems is to estimate the full-link delivery time for better decision-making. Existing solutions for traditional warehouse-distribution separation mode are challenging to address this problem due to two unique features in the integration mode including (i) contextual influence caused by neighbor units in heterogeneous delivery networks, (ii) uncertain delivery time caused by the dynamic temporal data (e.g., online sales volume) and heterogeneity of delivery units. To incorporate these new factors, we propose Heterogeneous Spatial-Temporal Graph Transformer (HST-GT), a novel full-link delivery time estimation method under the warehouse-distribution integration mode, where we (i) develop heterogeneous graph transformers to capture hierarchical heterogeneous information; and (ii) design a set of spatial-temporal transformers based on heterogeneous features to fully exploit the correlation of spatial and temporal information. We extensively evaluate our method based on one-month real-world data consisting of hundreds of warehouses and sorting centers, and millions of historical orders collected from one of the largest e-commerce retailers in the world. Experimental results demonstrate that our method outperforms state-of-the-art baselines in various metrics.

Last-mile delivery from delivery stations to customers’ places is now mainly finished by dedicated couriers. In practice, each courier generally collects orders destined for one delivery area at the delivery station and delivers orders to customers. However, the long distance between the delivery station and the delivery area due to practical reasons, e.g., expensive delivery station rental fee in the downtown area, increases the delivery courier’s travel time and decreases the efficiency of the state-of-the-practice last-mile delivery scheme. In this paper, we solve the problem with relay transportation, where a relay courier collects orders at the delivery station and sends them to delivery couriers, and delivery couriers focus on the order delivery at corresponding delivery areas. We design a real-time relay courier scheduling system called REDE to minimize the average relay order delivery time (ARODT) considering the relay and delivery couriers’ mobility and the order destination distribution. First, a heterogeneous task aware route prediction algorithm is proposed to characterize the delivery courier’s mobility. Then a distance-aware greedy algorithm and an ARODT-constrained exchange algorithm are designed to generate the relay route, which is updated with real-time order pickup requests. Extensive evaluation results with real-world logistics data from 100 delivery stations in 38 cities show that REDE reduces ARODT by up to 8.4% compared to baseline methods. The online A/B tests show that compared to the state-of-the-practice method, REDE improves the delivery courier’s working efficiency and the daily number of pickup orders by 20.13% and 4.51%, respectively.

Last-mile logistics is the final step of the delivery process from a transit station to customers. In last-mile logistics systems, a city is divided into many delivery areas for couriers to finish the parcel transition tasks. In recent years, last-mile logistics faces huge challenges in system efficiency and customer experience due to highly dynamic logistics service demand across different delivery areas. How to design a proper mechanism to improve the system efficiency and customer experience has become an important task. In this paper, we formulate the delivery area assignment problem and propose a Group-based Cooperative Reinforcement Learning (GCRL) framework to optimize the last-mile logistics system. Firstly, we design a multi-level attention mechanism to construct an optimal courier team that provides cooperative pick-up and delivery services. Secondly, A graph generator and graph-based strategy are proposed to represent the decision dependency and coordinate the dependent behaviors among couriers, respectively. Finally, we design a simultaneous training mechanism to maximize the discounted return and guide the delivery area for each courier. Being formulated in a multi-agent way, GCRL focuses on the cooperation among couriers while considering the system context and couriers’ preferences. Experiments on real-world data show that GCRL achieves an average of 12% improvements compared with state-of-the-art models.

Crowd logistics, as an emerging delivery paradigm, provides a cost-efficient way of leveraging crowdsourcing couriers to help express enterprises to match the surging delivery demands that are hard to be addressed by regular couriers only during online mega sale days. However, it is a challenging problem how to recruit an appropriate number of crowdsourcing couriers and assign an appropriate number of parcels to them and regular couriers, as many practical issues need to be considered, such as the dynamic competitive crowdsourcing market, the turnover of crowdsourcing couriers, and unique workload patterns of regular couriers. We design a crowdsourcing-assisted express system called COME to coordinate crowdsourcing and regular couriers for minimizing the overall cost of labor payment and parcel backlog. In COME, we design an Opponent-Aware Reinforcement Learning model to learn the recruitment difficulty in a competitive crowdsourcing market to make an appropriate recruitment plan, and design a four-staged approach to make an appropriate parcel assignment plan, which can address not only the dynamic recruitment difficulty but also the dynamic number of couriers. We have implemented and deployed COME on a real-world crowdsourcing-assisted express system in China involving 1358 delivery stations over 145 cities, and extensively evaluated it with a four-year real-world dataset, demonstrating its great advantage over other alternative solutions and showing high feasibility and generality.

The popularity of online e-commerce has promoted the rapid development of last-mile logistics in recent years. In last-mile services, to ensure delivery efficiency and enhance user experience, the delivery zone is proposed to perform delivery task assignment, which is a fundamental part of last-mile delivery. Each courier is responsible for one delivery zone. Couriers will collect orders belonging to their delivery zones from the delivery station and deliver orders to customers. Existing delivery zone partition practices in last-mile logistics consist of manual experience-based and static optimization-based methods, which perform order amount balancing among different zone but suffer from dissatisfaction and inefficiency because of two limitations: (i) using order amount is not always a good balancing metric considering deliveries' various difficulties (e.g., residence or industrial park, with or without elevators); (ii) less considering couriers' familiarity and preference behaviors. To generate delivery zone partition with equitable workload assignment, in this paper, we propose E-partition, a data-driven delivery zone partition framework to achieve equitable workload assignment in last-mile logistics. We first design a learning-based workload prediction model to estimate service time given a partition plan that consists of unseen courier-zone matching scenarios. Then, a delivery zone partition algorithm is proposed to iterative optimize couriers' core-AOI (i.e., area of interest) generation and AOI assignment process. Extensive offline experimental results show that our model outperforms baselines in working time prediction and workload balancing performances. Real-world deployment results at JD Logistics also verify the effectiveness of equitable-assignment aware delivery zone partition, with a 2.2% increase in service on-time rate compared to state-of-practice partition solutions.

In recent years, we have been witnessing a rapid prevalence of instant delivery services (e,g., UberEats, Instacart, and Eleme) due to their convenience and timeliness. A unique characteristic of instant delivery services is the concurrent dispatch mode, where (i) one courier usually simultaneously delivers multiple orders, especially during rush hours, and (ii) couriers can receive new orders when delivering existing orders. Most existing concurrent dispatch systems are efficiency-oriented, which means they usually dispatch a group of orders that have a similar delivery route to a courier. Although this strategy may achieve high overall efficiency, it also potentially causes a huge disparity of earnings between different couriers. To address the problem, in this paper, we design a Fairness-aware Concurrent dispatch system called FairCod, which aims to optimize the overall operation efficiency and individual fairness at the same time. Specifically, in FairCod, we design a Dynamic Advantage Actor-Critic algorithm with Fairness constrain (DA2CF). The basic idea is that it includes an Actor network to make dispatch decisions based on dynamic action space and a Critic network to evaluate the dispatch decisions from the fairness perspective. More importantly, we extensively evaluate our FairCod system based on one-month real-world data consisting of 36.38 million orders from 42,000 couriers collected by one of the largest instant delivery companies in China. Experimental results show that our FairCod improves courier fairness by 30.3% without sacrificing the overall system benefit compared to state-of-the-art baselines.

In recent years, emergency last-mile logistics (ELML) have played an essential role in urban emergencies. The efficient allocation of couriers in ELML is of practical significance to ensure the supply of essential materials, especially in public health emergencies (PHEs). However, couriers allocation becomes challenging due to the instability of demand, dynamic supply comprehension, and the evolutional delivery environment for ELML caused by PHEs. While existing work has delved into couriers allocation, the impact of PHEs on demand-supply-delivery has yet to be considered. In this work, we design PTOCA, a Predict-Then-Optimize Couriers Allocation framework. Specifically, in the prediction stage, we design a resource-aware prediction module that performs spatio-temporal modeling of unstable demand characteristics using a variational graph GRU encoder and builds a task-resource regressor to predict demand accurately. In the optimization stage, firstly, the priority ranking module solves the matching of delivery resources under demand-supply imbalance. Then the multi-factor task allocation module is used to model the dynamic evolutional environment and reasonably assign the delivery tasks of couriers. We evaluate PTOCA using real-world data covering 170 delivery zones, more than 10,000 couriers, and 100 million delivery tasks. The data is collected from JD Logistics, one of the largest logistics service companies. Extensive experimental results show that our method outperforms the baseline in task delivery rate and on-time delivery rate.

For a nationwide logistics transportation system, it is critical to make the vehicle loading plans (i.e., given many packages, deciding vehicle types and numbers) at each sorting and distribution center. This task is currently completed by dispatchers at each center in many logistics companies and consumes a lot of workloads for dispatchers. Existing works formulate such an issue as a cargo loading problem and solve it by combinatorial optimization methods. However, it cannot work in some real-world nationwide applications due to the lack of accurate cargo volume information and effective model design under complicated impact factors as well as temporal correlation. In this paper, we explore a new opportunity to utilize large-scale route and human behavior data (i.e., dispatchers' decision process on planning vehicles) to generate vehicle loading plans (i.e., plans). Specifically, we collect a five-month nationwide operational dataset from JD Logistics in China and comprehensively analyze human behaviors. Based on the data-driven analytics insights, we design a Vehicle Loading Plan learning model, named VeLP, which consists of a pattern mining module and a deep temporal cross neural network, to learn the human behaviors on regular and irregular routes, respectively. Extensive experiments demonstrate the superiority of VeLP, which achieves performance improvement by 35.8% and 50% for trunk and branch routes compared with baselines, respectively. Besides, we deployed VeLP in JDL and applied it in about 400 routes, reducing the time by approximately 20% in creating plans. It saves significant human workload and improves operational efficiency for the logistics company.

For a new city that is committed to promoting Electric Vehicles (EVs), it is significant to plan the public charging infrastructure where charging demands are high. However, it is difficult to predict charging demands before the actual deployment of EV chargers for lack of operational data, resulting in a deadlock. A direct idea is to leverage the urban transfer learning paradigm to learn the knowledge from a source city, then exploit it to predict charging demands, and meanwhile determine locations and amounts of slow/fast chargers for charging stations in the target city. However, the demand prediction and charger planning depend on each other, and it is required to re-train the prediction model to eliminate the negative transfer between cities for each varied charger plan, leading to the unacceptable time complexity. To this end, we design an effective solution of S imultaneous Demand P rediction A nd P lanning ( SPAP ): discriminative features are extracted from multi-source data, and fed into an Attention-based Spatial-Temporal City Domain Adaptation Network ( AST-CDAN ) for cross-city demand prediction; a novel Transfer Iterative Optimization ( TIO ) algorithm is designed for charger planning by iteratively utilizing AST-CDAN and a charger plan fine-tuning algorithm. Extensive experiments on real-world datasets collected from three cities in China validate the effectiveness and efficiency of SPAP . Specially, SPAP improves at most 72.5% revenue compared with the real-world charger deployment.

With the rapid development of sharing economy, we have access to massive sharing systems such as Uber, Airbnb, and bike sharing nowadays. The sharing economy, at its core, is to achieve efficient use of resources. However, the actual usage of shared resources is still unclear to us. Little measurement or analysis, if any, has been conducted to investigate the resource usage patterns with the large-scale data collected from these sharing systems. In this paper, we first analyze the shared bike usage patterns in three typical bike sharing systems based on 140-month multi-event data. From our data-driven analysis, we found that the most used 20% of shared bikes account for 45% of total usage, while the least used 20% of bikes account for less than 1% of usage. To efficiently utilize shared bikes, we propose a usage balancing design called eShare+ to improve the bike sharing systems by considering both the quality of service and bike maintenance, which includes three key components: (i) a statistical model based on archived data to infer historical usage; (ii) an entropy and contextual LSTM-based prediction model with both real-time and archived data to infer future usage; (iii) a model-driven optimal calibration engine for bike selection to dynamically balance usage. We develop an ID swapping-based evaluation methodology to measure the efficiency of eShare+ with data from three large-scale bike sharing systems including 84,000 bikes and 3,300 service stations. Our results show that eShare+ not only fully utilizes shared bikes with efficient maintenance but also improves the quality of service. In addition, eShare+ also has the potential to be applicable to different fleet sizes.

With the rapid growth of the number of private vehicles, searching for accessible parking spaces becomes intractable for drivers, especially during high-demand hours. In recent years, we are witnessing a number of sharing economy services. Contract parking sharing, as an innovative sharing economy mode, has the potential to alleviate the difficult parking issue and make full use of the urban parking resources. However, the uncertainties of both drivers’ parking demand and owners’ sharing supply make it challenging to achieve efficient sharing. Thanks to IoT technology, many current parking lots now record vehicles’ fine-grained parking data for billing purposes. Leveraging these fine-grained parking data, we exploit available contract parking spaces to share them with drivers that have temporary parking demand. Specifically, we propose$\mathrm{W^{2}}$Parking, awin-win contractparkingsharing system, which includes two key components: (i) an idle time prediction model to estimate available periods of parking spaces and (ii) a parking sharing model to schedule temporary users to have access to these available parking spaces under both demand and supply uncertainties using dynamic programming combined with a 2-approximation algorithm with performance-bound guarantees. we evaluate our system on seven-month real-world parking data from 368 parking lots with 14,704 parking spaces. Extensive experimental results show that our$\mathrm{W^{2}}$Parking achieves more than 90% of accuracy in parking time prediction, and the utilization rate of contract parking spaces is improved by 35%.

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.

Geocoding, associating textual addresses with corresponding GPS coordinates, is vital for many location-based services (e.g., logistics, ridesharing, and social networks). One of the most common Geocoding solutions is using commercial map services (e.g., Google Maps) by uploading textual addresses to obtain corresponding coordinates. However, this is typically not practical for some location-based service providers due to real-world challenges like commercial competition and high costs (recurring fees). In this paper, we design a new cost-effective Geocoding framework to automatically infer the geographic coordinates from textual addresses for service providers. To achieve this, we take the E-Commerce logistics service as a concrete scenario and design CoMiner, an unsupervised coordinate inference framework based on textual address data, delivery event data, and courier trajectory data. There are three main components in CoMiner. (1) A POI-level clustering model by modeling customers' shopping patterns at different spatial granularities; (2) A Delivery Mobility Graph (DMG) by modeling couriers' delivery events and geographic coordinates; (3) A behavior-driven address ranking model by mining couriers' uncertain reporting behaviors to further infer coordinates on DMG. We extensively verify the performance of CoMiner with a three-phase evaluation from data-driven experiments to real-world deployment. (i) We conduct extensive experiments on three large-scale datasets where CoMiner achieves an average accuracy of 95.1%, which outperforms the state-of-the-art methods by 20.3%. (ii) We deploy CoMiner in JD Logistics, inferring coordinates for over 30 million addresses with an average accuracy of 93.3%. (iii) We utilize CoMiner for two Geocoding-based applications, i.e., parcel re-routing optimization and abnormal delivery event detection.

An address, a textual description of a physical location, plays an important role in location-based services such as on-demand delivery and e-commerce. However, abnormal addresses (i.e., an address without detailed information representing a spatial location) have led to significant costs. In real-world settings like e-commerce, abnormal address detection is not trivial because it needs to be completed in real-time to support massive online queries. In this study, we design FastAddr, a fast abnormal address detection framework, which detects abnormal addresses among millions of addresses in a short time. By investigating and modeling the hierarchical structure of address data, we first design a novel contrastive address augmentation approach to generate training data via learning the entity transition probability matrix. We further design a lightweight multi-head attention model for learning compact address representation by modeling the address characteristics. We conduct a comprehensive three-phase evaluation. (i) We evaluate FastAddr on a real-world dataset and it yields the average F1 of 85.7% in 0.058 milliseconds, which outperforms the state-of-the-art models by 47.4% with similar detection time. (ii) An offline A/B test shows that FastAddr outperforms the previous deployed model significantly. (iii) We also conduct an online A/B test to compare FastAddr with the deployed model, which shows an improvement of F1 by more than 20%. Moreover, a real-world case study demonstrates both the efficiency and effectiveness of FastAddr.

The emergence of Online-to-Offline (O2O) stores based on delivery platforms (e.g., Uber Eats, DoorDash, and Eleme) provides great convenience to people's lives. In the O2O model, one of the essential problems for merchants is to select a suitable store site, i.e., store site recommendation problem. We argue that the existing works for the traditional brick-and-mortar stores cannot address this problem due to two unique factors in the O2O model including (i) dynamic supply caused by courier capacity and dispatching strategies and (ii) various customer demands caused by delivery distance and customer preferences. To incorporate these new factors, we design$O^{2}$SiteRec, a store site recommendation method under the O2O model via multi-graph attention networks, which consists of (i) a courier capacity model based on a multi-semantic relation graph attention network to capture courier capacity; (ii) a heterogeneous multi-graph based recommendation model, where the courier capacity, customer preferences, and context features are fused. We evaluate our method based on one-month real-world data consisting of 39,465 stores and 23.6 million orders from one of the largest O2O platforms in China. Experimental results demonstrate that our method outperforms state-of-the-art baselines in various metrics.

On-demand delivery is a new form of logistics where customers place orders through online platforms and the platform arranges couriers to deliver them within a short time. The acquisition of indoor status (i.e., arrival or departure at the merchants) of couriers plays an important role in order dispatching and route planning. The Bluetooth Low Energy (BLE) device is a promising solution for city-wide indoor status estimation due to the low hardware and deployment costs and low power consumption. However, the environment and smartphone model heterogeneities affect the status characteristics contained in the Bluetooth signal, resulting in the decline of status estimation performance. The previous methods to alleviate the heterogeneity are not suitable for city-wide scenarios with thousands of merchants and hundreds of smartphone models. In this paper, we propose Para-Pred, an indoor status estimation framework based on the graph neural network, which directly Predicts the effective indoor status estimation model Parameters for unseen scenarios. Our key idea is to utilize similarity between the influence patterns of heterogeneities on the Bluetooth signal to directly infer unseen scenarios' influence patterns. We evaluate the Para-Pred on 109,378 couriers with 672 smartphone models in 12,109 merchants from an on-demand delivery company. The evaluation results show that across environment and smartphone model heterogeneities, the accuracy and recall of our method achieve 93.62% and 95.20%, outperforming state-of-the-art solutions.

We are witnessing a rapid taxi electrification process due to the ever-increasing concern about urban air quality and energy security. A key difference between conventional gas taxis and electric taxis is their energy replenishment mechanisms, i.e., refueling or charging, which is reflected in two aspects: (i) much longer charging processes vs. short refueling processes and (ii) time-varying electricity prices vs. time-invariant gasoline prices during a day. The complicated charging issues (e.g., long charging time and dynamic charging pricing) potentially reduce electric taxis' daily operation time and profits, and also cause overcrowded charging stations during some off-peak charging pricing periods. Motivated by a set of findings obtained from a data-driven investigation, in this paper, we design a fairness-aware vehicle displacement system called FairMove to improve the overall profit efficiency and profit fairness of electric taxi fleets by considering both the passenger travel demand and taxi charging demand. We first formulate the electric taxi displacement problem as multi-agent deep reinforcement learning, and then we propose a centralized multi-agent actor-critic approach to tackle this problem. More importantly, we implement and evaluate FairMove with real-world streaming data from the Chinese city Shenzhen, including GPS data and transaction data from more than 20,100 electric taxis, coupled with the data of 123 charging stations, which constitute, to our knowledge, the largest all-electric taxi network in the world. The extensive experimental results show that our fairness-aware FairMove effectively improves the profit efficiency and profit fairness of the Shenzhen electric taxi fleet by 25.2% and 54.7%, respectively.

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.

Electric carsharing, i.e., electric vehicle sharing, as an emerging mobility-on-demand service, has been proliferating worldwide recently. Though providing convenient, low-cost, and environmentally-friendly mobility, there are also some potential roadblocks in electric carsharing services due to existing inefficient fleet management strategies, which relocate the vehicles using predefined periodic schedules without self-adapting to the highly dynamic user demand, and many practical factors like time-variant charging pricing also have not been fully considered. To remedy these problems, in this paper, we design Record, an effective fleet management system with joint Repositioning and Charging for electric carsharing based on dynamic deadlines to improve its operating profits and also satisfy users' real-time pickup and return demand. Record considers not only the highly dynamic user demand for vehicle repositioning (i.e., where to relocate) but also the time-varying charging pricing for charging scheduling (i.e., where to charge). To perform the two tasks efficiently, in Record, we design a dynamic deadline-based distributed deep reinforcement learning algorithm, which generates dynamic deadlines via usage prediction combined with an error compensation mechanism to adaptively search and learn the optimal locations for satisfying highly dynamic and unbalanced user demand in real time. We implement and evaluate the Record system with 10-month real-world electric carsharing data, and the extensive experimental results show that our Record effectively reduces 25.8% of charging costs and reduces 30.2% of vehicle movements by workers, and it also satisfies user demand and achieves a small runtime overhead at the same time.

We are witnessing a rapid growth of electrified vehicles due to the ever-increasing concerns on urban air quality and energy security. Compared to other types of electric vehicles, electric buses have not yet been prevailingly adopted worldwide due to their high owning and operating costs, long charging time, and the uneven spatial distribution of charging facilities. Moreover, the highly dynamic environment factors such as unpredictable traffic congestion, different passenger demands, and even the changing weather can significantly affect electric bus charging efficiency and potentially hinder the further promotion of large-scale electric bus fleets. To address these issues, in this article, we first analyze a real-world dataset including massive data from 16,359 electric buses, 1,400 bus lines, and 5,562 bus stops. Then, we investigate the electric bus network to understand its operating and charging patterns, and further verify the necessity and feasibility of a real-time charging scheduling. With such understanding, we design busCharging , a pricing-aware real-time charging scheduling system based on Markov Decision Process to reduce the overall charging and operating costs for city-scale electric bus fleets, taking the time-variant electricity pricing into account. To show the effectiveness of busCharging , we implement it with the real-world data from Shenzhen, which includes GPS data of electric buses, the metadata of all bus lines and bus stops, combined with data of 376 charging stations for electric buses. The evaluation results show that busCharging dramatically reduces the charging cost by 23.7% and 12.8% of electricity usage simultaneously. Finally, we design a scheduling-based charging station expansion strategy to verify our busCharging is also effective during the charging station expansion process.

Understanding representativeness in cellular web logs at city scale is essential for web applications. Most of the existing work on cellular web analyses or applications is built upon data from a single network in a city, which may not be representative of the overall usage patterns since multiple cellular networks coexist in most cities in the world. In this paper, we conduct the first comprehensive investigation of multiple cellular networks in a city with a 100% user penetration rate. We study web usage pattern (e.g., internet access services) correlation and difference between diverse cellular networks in terms of spatial and temporal dimensions to quantify the representativeness of web usage from a single network in usage patterns of all users in the same city. Moreover, relying on three external datasets, we study the correlation between the representativeness and contextual factors (e.g., Point-of-Interest, population, and mobility) to explain the potential causalities for the representativeness difference. We found that contextual diversity is a key reason for representativeness difference, and representativeness has a significant impact on the performance of real-world applications. Based on the analysis results, we further design a correction model to address the bias of single cellphone networks and improve representativeness by 45.8%.

Due to the ever-growing concerns over air pollution and energy security, more and more cities have started to replace their conventional taxi fleets with electric ones. Even though environmentally friendly, the rapid promotion of electric taxis raises problems to both taxi drivers and governments, e.g., prolonged waiting/charging time, unbalanced utilization of charging infrastructures, and inadequate taxi supply due to the long charging time. In this article, we conduct the first longitudinal measurement study to understand the long-term evolution of mobility and charging patterns by utilizing 5-year data from one of the largest electric taxi networks in the world, i.e., the Shenzhen electric taxi network in China. In particular, (1) we first perform an electric taxi contextualization about their operation and charging activities; (2) then we design a generic charging event extraction algorithm based on GPS data and charging station data, and (3) based on the contextualization and extracted charging activities, we perform a comprehensive measurement study called ePat to explore the evolution of the electric taxi network from the mobility and charging perspectives. Our ePat is based on 4.8 TB taxi GPS data, 240 GB taxi transaction data, and metadata from 117 charging stations, during an evolution process from 427 electric taxis in 2013 to 13,178 in 2018. Moreover, ePat also explores the impacts of various contexts and benefits during the evolution process. Our ePat as a comprehensive measurement of the electric taxi network mobility and charging evolution has the potential to advance the understanding of the evolution patterns of electric taxi networks and pave the way for analyzing future shared autonomous vehicles.

With the rapid development of sharing economy, massive sharing systems such as Uber, Airbnb, and bikeshare have percolated into people's daily life. The sharing economy, at its core, is to achieve efficient use of resources. The actual usage of shared resources, however, is unclear to us. Little measurement or analysis, if any, has been conducted to investigate the resource usage status with the large-scale data collected from these sharing systems. In this paper, we analyze the bike usage status in three typical bikeshare systems based on 140-month multi-event data. Our analysis shows that the most used 20% of bikes account for 45% of usage, while the least used 20% of bikes account for less than 1% of usage. To efficiently utilize shared bikes, we propose a usage balancing design called eShare which has three components: (i) a statistical model based on archived data to infer historical usage; (ii) an entropy-based prediction model based on both real-time and archived data to infer future usage; (iii) a model-driven optimal calibration engine for bike selection to dynamically balance usage. We develop an ID swapping based evaluation methodology and measure the efficiency of eShare with data from three systems including the world's largest bikeshare system with 84,000 bikes and 3,300 stations. Our results show that eShare not only fully utilizes shared bikes but also improves service quality.

Real-time human mobility modeling is essential to various urban applications. To model such human mobility, numerous data-driven techniques have been proposed. However, existing techniques are mostly driven by data from a single view, for example, a transportation view or a cellphone view, which leads to over-fitting of these single-view models. To address this issue, we propose a human mobility modeling technique based on a generic multi-view learning framework called coMobile. In coMobile, we first improve the performance of single-view models based on tensor decomposition with correlated contexts, and then we integrate these improved single-view models together for multi-view learning to iteratively obtain mutually reinforced knowledge for real-time human mobility at urban scale. We implement coMobile based on an extremely large dataset in the Chinese city Shenzhen, including data about taxi, bus, and subway passengers along with cellphone users, capturing more than 27 thousand vehicles and 10 million urban residents. The evaluation results show that our approach outperforms a single-view model by 51% on average. More importantly, we design a novel application where urban taxis are dispatched based on unaccounted mobility demand inferred by coMobile.

Real-time traffic modeling at national scale is essential to many applications, but its calibration is extremely challenging due to its large spatial and fine temporal coverage. The existing work mostly is focused on urban-scale calibration with complete field data from single data sources (e.g., loop sensors or taxis), which cannot be generalized to national scale, because complete single-source field data at national scale are almost impossible to obtain. To address this challenge, in this paper, we design MultiCalib, a model calibration framework to optimize traffic models based on multiple incomplete data sources at national scale in real time. Instead of naively combining multi-source data, we theoretically formulate a multi-source model calibration problem based on real-world contexts and multi-view learning. More importantly, we implement and evaluate MultiCalib with two heterogeneous nationwide vehicle networks with 340,000 vehicles to infer traffic conditions on 36 expressways and 119 highways, along with 4 cities across China. The results show that MultiCalib outperforms state-of-the- art calibration by 25% on average with same input data.

Nowadays most metro advertising systems schedule advertising slots on digital advertising screens to achieve the maximum exposure to passengers by exploring passenger demand models. However, our empirical results show that these passenger demand models experience uncertainty at fine temporal granularity (e.g., per min). As a result, for fine-grained advertisements (shorter than one minute), a scheduling based on these demand models cannot achieve the maximum advertisement exposure. To address this issue, we propose an online advertising approach, called EveryoneCounts, based on an uncertain passenger demand model. It combines coarse-grained statistical demand modeling and fine-grained Bayesian demand modeling by leveraging realtime card-swiping records along with both passenger mobility patterns and travel periods within metro systems. Based on this uncertain demand model, it schedules advertising time online based on robust receding horizon control to maximize the advertisement exposure. We evaluate the proposed approach based on an one-month sample from our 530 GB real-world metro fare dataset with 16 million cards. The results show that our approach provides a 61.5% lower traffic prediction error and 20% improvement on advertising efficiency on average.

Real-time human mobility modeling is essential to various urban applications. To model such human mobility, numerous data-driven techniques have been proposed. However, existing techniques are mostly driven by data from a single view, e.g., a transportation view or a cellphone view, which leads to over-fitting of these single-view models. To address this issue, we propose a human mobility modeling technique based on a generic multi-view learning framework called coMobile. In coMobile, we first improve the performance of single-view models based on tensor decomposition with correlated contexts, and then we integrate these improved single-view models together for multi-view learning to iteratively obtain mutually-reinforced knowledge for real-time human mobility at urban scale. We implement coMobile based on an extremely large dataset in the Chinese city Shenzhen, including data about taxi, bus and subway passengers along with cellphone users, capturing more than 27 thousand vehicles and 10 million urban residents. The evaluation results show that our approach outperforms a single-view model by 51% on average.

Carpooling taxicab services hold the promise of providing additional transportation supply, especially in extreme weather or rush hour when regular taxicab services are insufficient. Although many recommendation systems about regular taxicab services have been proposed recently, little research, if any, has been done to assist passengers to find a successful taxicab ride with carpooling. In this paper, we present the first systematic work to design a unified recommendation system for both regular and carpooling services, called CallCab, based on a data driven approach. In response to a passenger's request, CallCab aims to recommend either (i) a vacant taxicab for a regular service with no detour, or (ii) an occupied taxicab heading to the similar direction for a carpooling service with less detour, yet without assuming any knowledge of destinations of passengers already on occupied taxicabs. To analyze these unknown destinations of occupied taxicabs, CallCab generates and refines taxicab trip distributions based on GPS datasets and context information collected in the existing taxicab infrastructure. To improve CallCab's efficiency to process such a big dataset, we augment the efficient MapReduce model with a Measure phase tailored for our application. We evaluate CallCab with a real world dataset of 14,000 taxicabs, and results show that compared to ground truth, CallCab can reduce 64% of the total mileage to deliver all passengers and 63% of passenger's waiting time.