Large-scale human mobility data contains rich spatial and temporal information for urban sensing, crowd flow modeling, and urban planning. However, it is usually difficult to access wide-coverage, long-term, and consistent-time human mobility data. Most of the publicly available datasets are actually only records of discontinuous trajectories of a very small portion of urban citizens in asynchronous time due to the limited usage of apps for location data collection or the limited number of volunteers. To address this problem and empower open urban research, this paper constructs a high-quality human mobility dataset by generating large-scale citizen trajectories based on massive cellular signaling data. Particularly, we first propose a heatmap diffusion module to generate a probability heatmap that produces plausible trajectories at both the individual and city scales. Then, we propose a masked trajectory AutoEncoder, which can generate individual trajectory embeddings from partially given or empty trajectories. Third, a flexible framework is provided to incorporate the heatmap diffusion module with the masked trajectory embeddings, demonstrating significant flexibility in handling both fully masked trajectories for city-wide analysis and partially masked trajectories for specific locations. We have conducted extensive experiments to validate the utility of the regenerated trajectories at both individual and region levels for various applications. Numerous case studies further illustrate that our model learns not only the distribution of the trajectories but also the semantics of different urban areas.

Dynamic graph learning has attracted much attention in recent years due to the fact that most of the real-world graphs are dynamic and evolutionary.As a result, many dynamic learning methods have been proposed to cope with the changes of node states over time.Among these studies, a critical issue is how to update the representations of nodes when new temporal events are observed.In this paper, we provide a novel memory structure -Memory Map (MemMap) for this problem.MemMap is an adaptive and evolutionary latent memory space, where each cell corresponds to an evolving "topic" of the dynamic graph.Moreover, the representation of a node is generated from its semantically correlated memory cells, rather than linked neighbors of the node.We have conducted experiments on real-world datasets and compared our method with the SOTA ones.It can be concluded that: 1) By constructing an adaptive and evolving memory structure during the dynamic learning process, our method can capture the dynamic graph changes, and the learned MemMap is actually a compact evolving structure organized according to the latent "topics" of the graph nodes.2) Our research suggests that it is a more effective and efficient way to generate node representations from a latent semantic space (like MemMap in our method) than from directly connected neighbors (like most of the previous graph learning methods).The reason is that the number of memory cells in latent space could be much smaller than the number of nodes in a real-world graph, and the representation learning process could well balance the global and local message passing by leveraging the semantic similarity of graph nodes via the correlated memory cells.

Cognitive diagnosis models have been widely used in different areas, especially intelligent education, to measure users' proficiency levels on knowledge concepts, based on which users can get personalized instructions. As the measurement is not always reliable due to the weak links of the models and data, the uncertainty of measurement also offers important information for decisions. However, the research on the uncertainty estimation lags behind that on advanced model structures for cognitive diagnosis. Existing approaches have limited efficiency and leave an academic blank for sophisticated models which have interaction function parameters (e.g., deep learning-based models). To address these problems, we propose a unified uncertainty estimation approach for a wide range of cognitive diagnosis models. Specifically, based on the idea of estimating the posterior distributions of cognitive diagnosis model parameters, we first provide a unified objective function for mini-batch based optimization that can be more efficiently applied to a wide range of models and large datasets. Then, we modify the reparameterization approach in order to adapt to parameters defined on different domains. Furthermore, we decompose the uncertainty of diagnostic parameters into data aspect and model aspect, which better explains the source of uncertainty. Extensive experiments demonstrate that our method is effective and can provide useful insights into the uncertainty of cognitive diagnosis.

Numerous spatial-temporal learning methods have been proposed for crowd flow modeling, which is an important problem in Intelligent Transportation Systems (ITS). However, most of the existing methods were designed to use data in one specific form to solve one particular task of crowd flow modeling and the shared patterns among different tasks have been largely ignored. In this paper, we investigate how to learn generic node representations that can simultaneously support various downstream tasks of crowd flow modeling. Along this line, we develop a continuous-time dynamic graph representation learning method based onBootstrapping forCrowdFlow modeling (BootCF). Our approach follows a training procedure with two phases. In the pre-training phase, the continuous-time dynamic encoder converts edges with timestamps into messages to update the representations of the related traffic nodes. Inspired by the recent progress of contrastive learning, a bootstrapping framework for continuous-time dynamic graphs is designed to calculate pre-training loss and update the model in a self-supervised way, and thus enabling the node representation learning to be task-agnostic. Moreover, a context-aware data augmentation on continuous-time dynamic graphs is proposed to generate the augmented view of input data. Once the general node representations are obtained, the second phase can learn an effective model for any downstream task. Experiments on two real-world datasets show that our approach can achieve significant performance gain on four downstream tasks, which demonstrates that the proposed method has the powerful generalization capability for learning task-agnostic node representations.

Given a sequence of sets, where each set has a timestamp and contains an arbitrary number of elements, temporal sets prediction aims to predict the elements in the subsequent set. Previous studies for temporal sets prediction mainly focus on the modelling of elements and implicitly represent each user's preference based on his/her interacted elements. However, user preferences are often continuously evolving and the evolutionary trend cannot be fully captured with the indirect learning paradigm of user preferences. To this end, we propose a continuous-time user preference modelling framework for temporal sets prediction, which explicitly models the evolving preference of each user by maintaining a memory bank to store the states of all the users and elements. Specifically, we first construct a universal sequence by arranging all the user-set interactions in a non-descending temporal order, and then chronologically learn from each user-set interaction. For each interaction, we continuously update the memories of the related user and elements based on their currently encoded messages and past memories. Moreover, we present a personalized user behavior learning module to discover user-specific characteristics based on each user's historical sequence, which aggregates the previously interacted elements from dual perspectives according to the user and elements. Finally, we develop a set-batch algorithm to improve the model efficiency, which can create time-consistent batches in advance and achieve 3.5× and 3.0× speedups in the training and evaluation process on average. Experiments on four real-world datasets demonstrate the superiority of our approach over state-of-the-arts under both transductive and inductive settings. The good interpretability of our method is also shown.

Popularity prediction, which aims to forecast how many users would like to interact with a target item or online content in the future, can help online shopping or social media platforms to identify popular items or digital contents. Many efforts have been made to study how the multi-faceted factors, such as item features, user preferences, and social influence, affect user-item interactions, but little work has focused on the evolutionary dynamics of these factors for individuals or groups. In that light, this paper develops a community-based dynamic graph learning method for popularity prediction. First, a dynamic graph learning framework is proposed to maintain a dynamic representation for each item or user entity and update the representations according to the newly observed user-item interactions. Second, a community detection module is designed to capture the evolving community structures and identify the most influential nodes. More importantly, our framework leverages a community-level message passing during the learning process to balance local and global information propagation. Finally, we predict the popularity of the target item or online content based on the learned representations. Our experimental results based on three real-world datasets demonstrate that the proposed method achieves better performance than the baselines. Our method could not only model the changes in a user's preferences, but also capture how the communities evolve over time.

Guaranteed Delivery (GD) advertising plays an essential part in e-commerce marketing, where the ad publisher signs contracts with advertisers in advance by promising delivery of advertising impressions to fulfill targeting requirements for advertisers. Previous research on GD advertising mainly focused on online serving yet overlooked the importance of contract allocation at the GD selling stage. Traditional GD selling approaches consider impression inventory prediction and contract allocation as two separate stages. However, such a two-stage optimization often leads to inferior contract allocation performance. In this paper, our goal is to reduce this performance gap with a novel end-to-end approach. Specifically, we propose the Neural Lagrangian Selling (NLS) model to jointly predict the impression inventory and optimize the contract allocation of advertising impressions with a unified learning objective. To this end, we first develop a differentiable Lagrangian layer to backpropagate the allocation problem through the neural network and allow direct optimization of the allocation regret. Then, for effective optimization with various allocation targets and constraints, we design a graph convolutional neural network to extract predictive features from the bipartite allocation graph. Extensive experiments show that our approach can improve GD selling performance compared with existing two-stage approaches. Particularly, our optimization layer can outperform the baseline solvers in both computational efficiency and solution quality. To the best of our knowledge, this is the first study to apply the end-to-end prediction and optimization approach for industrial GD selling problems. Our work has implications for general prediction and allocation problems as well.

Dynamic systems are often monitored with multivariate time series where each dimension represents a local component measured through a (virtual) sensor. Performing accurate diagnostic for dynamic systems while simultaneously taking into account their similarities/distinctions, is a non-trivial task. To this end, we develop an adaptive regularization approach to learning sparse connectivity structures in complex dynamic systems. The learned connectivity networks shed lights on the structural compositions of the system and hence can serve as highly informative inputs for various machine learning tasks such as classification. In particular, we focus on high-dimensional and semi-supervised learning scenarios and present a joint learning approach to recover system-wise connectivity patterns by adaptively constructing a shared, sparsity-inducing regularization template across all systems. The shared template can be physically interpreted and used as a modeling template for analyzing new systems. Moreover, our approach has the flexibility to incorporate supervising information such as must-links and cannot-links for constructing regularization templates. Overall, our approach, named sparse adaptive regularization (SAR), can extract structure-related connectivity features efficiently and effectively, and result in significant improvements for machine learning tasks in dynamic systems. We benchmark our approach against the state-of-the-art methods with real-world data. Our results demonstrate the superiority of our approach.

Representation learning on heterogeneous graphs aims to obtain meaningful node representations to facilitate various downstream tasks. Existing heterogeneous graph learning methods are primarily developed by following the propagation mechanism of node representations. There are few efforts on studying the role of relations for improving the learning of more fine-grained node representations. Indeed, it is important to collaboratively learn the semantic representations of relations and discern node representations with respect to different relation types. In this paper, we propose a novel Relation-aware Heterogeneous Graph Neural Network (R-HGNN), to learn node representations on heterogeneous graphs at a fine-grained level by considering relation-aware characteristics. Specifically, a dedicated graph convolution component is first designed to learn unique node representations from each relation-specific graph separately. Then, a cross-relation message passing module is developed to improve the interactions of node representations across different relations. Also, the relation representations are learned in a layer-wise manner to capture relation semantics, which are used to guide the node representation learning process. Moreover, a semantic fusing module is presented to aggregate relation-aware node representations into a compact representation with the learned relation representations. Experimental results on extensive graph learning tasks demonstrate that our approach could consistently outperform existing methods.

Guaranteed Display (GD) is widely used in e-commerce marketing for advertisers to acquire an agreed-upon number of impressions with target audiences. With the main objective to maximize the contract delivery rate under contract constraints, user interest (such as click-through rate and conversion rate) is also essential to improve the long-time return on investment for advertisers and the e-commerce platform. In this paper, we design an adaptive unified allocation framework (AUAF) by not only considering supply of audience impressions in request-level but also avoiding over-allocation of audience impressions. Specifically, our allocation model simultaneously optimizes the contract delivery and the match between advertisements and user interests with explicit constraint to prevent unnecessary allocation. Facing the challenge of serving billion-scale requests per day, a parameter-server based parallel optimization algorithm is also developed, enabling the proposed allocation model to be efficiently optimized and incrementally updated in minutes. Thus, the offline optimization results and the online decisions can be synchronized for real-time serving. In other words, our approach can achieve adaptive pacing that is consistent with the optimal allocation solution. Our extensive experimental results demonstrate that the proposed AUAF framework can improve both contract delivery rate and average click-through rate (CTR), which we use to measure the user interest in this paper. The improvements on CTR are statistically significant in comparison with existing methods. Moreover, since March 2020, AUAF has been deployed in the guaranteed display advertising system of Alibaba, bringing more than 10% increase on CTR without loss of contract delivery rate, which has resulted in significant value creation for the business.

The understanding of people’s inter-regional mobility behaviors, such as predicting the next activity region (AR) or uncovering the intentions for regional mobility, is of great value to public administration or business interests. While there are numerous studies on human mobility, these studies are mainly from a statistical view or study movement behaviors within a region. The work on individual-level inter-regional mobility behavior is limited. To this end, in this article, we propose a dynamic region-relation-aware graph neural network (DRRGNN) for exploring individual mobility behaviors over ARs. Specifically, we aim at developing models that can answer three questions: (1) Which regions are the ARs? (2) Which region will be the next AR, and (3) Why do people make this regional mobility? To achieve these tasks, we first propose a method to find out people’s ARs. Then, the designed model integrates a dynamic graph convolution network (DGCN) and a recurrent neural network (RNN) to depict the evolution of relations between ARs and mine the regional mobility patterns. In the learning process, the model further considers peoples’ profiles and visited point-of-interest (POIs). Finally, extensive experiments on two real-world datasets show that the proposed model can significantly improve accuracy for both the next AR prediction and mobility intention prediction.

Predicting treatment medicines is a key task in many intelligent healthcare systems. Prediction of treatment medicines can assist doctors in making informed prescription decisions for patients according to their Electronic Health Records (EHRs). However, predicting treatment medicines is a challenging task due to the following reasons: (1) heterogeneous nature of EHR data that typically includes laboratory results, treatment records, disease conditions, and demographic information; (2) complex correlations among EHR sequences, including inter-correlations between sequences and temporal intra-correlations within each sequence; (3) temporal dynamics of these correlations changing with disease progression. In this paper, we predict treatment medicines for patients with dual adaptive sequential networks (DASNet). Specifically, DASNet is designed with three components. First, a decomposed adaptive long short-term memory network (DA-LSTM) is designed to capture the intra- and inter-correlations in multiple heterogeneous temporal sequences. Then, we develop an attentive meta learning network (AT-MetaNet) to learn dynamic weight parameters for DA-LSTM, thus enabling it to model various correlation structures. Finally, we employ an attentive fusion network (AT-FuNet) to incorporate historical information and collectively fuse representation embeddings of heterogeneous data to predict treatment medicines. Our results on the public MIMIC-III dataset covering 11 medical conditions demonstrate that the proposed end-to-end model can achieve the state-of-the-art prediction performance while providing clinically useful insights.

Online display advertising has become a vital business for large-scale E-commerce markets. As the main goal of advertisers is to reach interested customer prospects, accurate conversion prediction is essential for successful online display advertising. A particular challenge for conversion prediction is that conversions may occur long after the click events. Such delayed feedback makes it a non-trivial task to keep conversion prediction models updated and consistent with the latest customer distribution. Although several studies have been conducted to tackle the delayed feedback issue, the relationship between the early conversion and full term conversion has not been fully exploited to improve conversion prediction. In this paper, we consider conversion prediction as a multi-task learning problem by leveraging multiple conversion labels after different observation intervals. Specifically, we propose a multi-task model with an end-to-end architecture for conversion prediction. Our approach is guided by theoretical and probabilistic analysis of the early and full term conversions. Our mixture-of-experts module can integrate distinct characteristics of input features and optimize the task-specific experts. In addition, the multiple tasks are jointly learned with a regularization term to ensure the embedding consistency between tasks and prevent potential overfitting issues. In comparison with competitive benchmarks, our approach can significantly improve conversion prediction with delayed feedback and improve business performance of online display advertising.

Uplift modeling is an important task for online advertising and marketing. Advertisers rely on accurate modeling of the uplift effect to formulate, plan and implement their advertising and marketing strategies. Therefore, the capability of effective and efficient uplift modeling is essential for advertising platforms to attract and satisfy their customers (i.e., advertisers). In practical advertising applications, uplift modeling focuses on the estimation of the uplift effect caused by ad exposure. It is not a trivial task to estimate such causal impact of ad exposure at the individual level. In this paper, we propose an end-to-end approach for explicit uplift modeling, using data collected from Randomized Controlled Trials (RCTs) in large-scale real-world advertising platforms. More specifically, we first introduce the Explicit Uplift Effect Network (EUEN) to explicitly model the uplift effect and demonstrate its advantages in uplift modeling. Then for the exposure uplift effect modeling, we further propose the Explicit Exposure Uplift Effect Network (EEUEN), which can correct the exposure bias for uplift modeling. We evaluate our proposed approach with both public data sets as well as data sets collected from our advertising platform. The significant improvements with respect to various performance metrics demonstrate the advantages of our approach.

In knowledge graphs, there are usually different types of nodes, multiple heterogeneous relations, and numerous attributes of nodes and edges, which impose the challenges on the task of Node Importance Estimation (NIE). Indeed, existing NIE approaches, such as PageRank (PR) and Node-Degree (ND), are not designed for handling knowledge graphs with the rich information related with these multifarious nodes and edges. To this end, in this paper, we propose a representation learning framework to leverage the rich information inherent in these multifarious nodes and edges for improving node importance estimation in knowledge graphs. Specifically, we provide a Relational Graph Transformer Network (RGTN), where a relational graph transformer is first proposed to propagate node information with the consideration of semantic predicate representations. Here, the assumption is that different predicates may have distinct effects on the transmission of node importance. Then, two separate encoders are designed to capture both the structural and semantic information of nodes respectively, and a co-attention module is developed to fuse the two separate representations of nodes. Next, an attention-based aggregation module is adopted to map the representations of nodes to their importance values. In addition, a learning-to-rank loss is designed to ensure that the learned representations can be aware of the relative ranking information among nodes. Finally, extensive experiments have been conducted on real-world knowledge graphs, and the results illustrate that our model outperforms the existing methods consistently for all the evaluation metrics. The code and the data are available at https://github.com/GRAPH-0/RGTN-NIE.

As a data-driven healthcare service, automatic treatment regimen design has great potential to improve healthcare efficiency and quality. However, it is a nontrivial endeavor to develop such a healthcare service due to two major challenges: 1) the treatment records are complex data objects consisting of various semantic and temporal information, and 2) the treatment outcome usually depends on a large number of internal and external factors. Because of these difficulties, automatic treatment regimen design is still an open research problem nowadays. To fill this research gap, this paper first formulates a treatment sequence as temporal sets, then provides a novel Extended Jaccard Similarity (EJS) measure to quantify the similarities between treatment sequences. We show that the proposed EJS is a general and effective measure to capture the similarity between two complex temporal sets. Further, we develop an efficient clustering algorithm which can achieve reasonable clustering results with only a portion of the pairwise similarities between treatment sequences and then extract a semantic prototype of the treatment regimen from each cluster of treatment sequences. Finally, we adopt a matrix factorization framework to predict the treatment outcomes by integrating multiple internal and external factors. We conduct comprehensive experiments on Electronic Medical Records (EMRs) of more than 28,000 patients from 14 hospitals. The results demonstrate the effectiveness of our approach and its superiority over the state-of-the-art ones.

Coupon is a powerful tool for promotional marketing and customer targeting. Improving customer conversion effects by optimally allocating coupons to the right customers, however, is a nontrivial task. In particular, offering coupons to all customers may not be cost effective while offering coupons to randomly selected customers may not lead to optimal effects. In this paper, we address challenges in precision coupon targeting with a customer triage framework which would ration coupons precisely to customers who will be the most promising commercial conversions. Specifically, first we use random user-experiments to quantify the coupon effects of our interest. Then, we model the observation from user-experiments to predict the expected coupon effects on all customers. With the predicted coupon effects, we develop a joint decision strategy for customer triage to target customers with the most influential coupons under budget constraints. The joint decision strategy can dynamically balance exploitation and exploration in the decision process spanning multiple decision periods. Implemented on a real-world online takeout service system, our results show significant improvements in comparison with alternative approaches.

Knowledge Tracing (KT) is a fundamental but challenging task in online education that traces learners' evolving knowledge states. Much attention has been drawn to this area and several works such as Bayesian Knowledge Tracing and Deep Knowledge Tracing are proposed. Recent works have explored the value of relations among concepts and proposed to introduce knowledge structure into KT task. However, the propagated influence among concepts, which has been shown to be a key factor in human learning by the educational theories, is still under-explored. In this paper, we propose a new framework called Structure-based Knowledge Tracing (SKT), which exploits the multiple relations in knowledge structure to model the influence propagation among concepts. In the SKT framework, we not only consider the temporal effect on the exercising sequence but also take the spatial effect on the knowledge structure into account. We take advantages of two novel formulations in modeling the influence propagation on the knowledge structure with multiple relations. For undirected relations such as similarity relations, the synchronization propagation method is adopted, where the influence propagates bidirectionally between neighbor concepts. For directed relations such as prerequisite relations, the partial propagation method is applied, where the influence can only unidirectionally propagate from a predecessor to a successor. Meanwhile, we employ the gated functions to update the states of concepts temporally and spatially. Extensive experiments demonstrate the effectiveness and interpretability of SKT.

Given a sequence of sets, where each set contains an arbitrary number of elements, the problem of temporal sets prediction aims to predict the elements in the subsequent set. In practice, temporal sets prediction is much more complex than predictive modelling of temporal events and time series, and is still an open problem. Many possible existing methods, if adapted for the problem of temporal sets prediction, usually follow a two-step strategy by first projecting temporal sets into latent representations and then learning a predictive model with the latent representations. The two-step approach often leads to information loss and unsatisfactory prediction performance. In this paper, we propose an integrated solution based on the deep neural networks for temporal sets prediction. A unique perspective of our approach is to learn element relationship by constructing set-level co-occurrence graph and then perform graph convolutions on the dynamic relationship graphs. Moreover, we design an attention-based module to adaptively learn the temporal dependency of elements and sets. Finally, we provide a gated updating mechanism to find the hidden shared patterns in different sequences and fuse both static and dynamic information to improve the prediction performance. Experiments on real-world data sets demonstrate that our approach can achieve competitive performances even with a portion of the training data and can outperform existing methods with a significant margin.

Understanding the target audience for popular television series is valuable for online video platform to manage advertising sales, purchase video copyrights, and compete with other video service platforms. Existing studies in this domain generally focus on using data mining and machine learning techniques to recommend television series to individual users or predict the popularity of television series. Knowing only the popularity of television series may, however, limit our ability to answer more in-depth questions and develop more intelligent applications. In this paper, we develop a data-driven framework to model and predict audience competition patterns for popular online television series. Specifically, we first construct a sequence of dynamic competition networks of television series by mining the detailed viewership records. Then, we design the Dynamic Deep Network Factorization (DDNF), a hybrid modeling framework for predicting the future competition networks. Our framework adopts the deep neural network (DNN) and the knowledge-base (KB) embedding to incorporate static features, and integrates the Long Short-Term Memory (LSTM) network to learn dynamic features of the television series. Finally, extensive experiments on real-world data sets validate the effectiveness of our approach compared with state-of-the-art baselines in predicting the audience competition for existing and new television series.

Many sequential behaviors such as purchasing items from time to time, selecting courses in different terms, collecting event logs periodically could be formalized as sequential sets of actions or elements, namely temporal sets. Predicting the subsequent set according to historical sequence of sets could help us make better producing, scheduling, or operating decisions. However, most of the existing methods were designed for predicting time series or temporal events, which could not be directly used for temporal sets prediction due to the difficulties of multi-level representations of items and sets, complex temporal dependencies of sets, and evolving dynamics of sequential behaviors. To address these issues, this paper provides a novel sets prediction method, called DSNTSP (Dual Sequential Network for Temporal Sets Prediction). Our model first learns both item-level representations and set-level representations of set sequences separately based on a transformer framework. Then, a co-transformer module is proposed to capture the multiple temporal dependencies of items and sets. Last, a gated neural module is designed to predict the subsequent set by fusing all the multi-level correlations and multiple temporal dependencies of items and sets. The experimental results on real-world data sets show that our methods lead to significant and consistent improvements as compared to other methods.

A Point-of-Interest (POI) refers to a specific location that people may find useful or interesting. In modern cities, a large number of POIs emerge, grow, stabilize for a period, then finally disappear. The stages (e.g., emerge and grow) in this process are called lifetime statuses of a POI. While a large body of research has been devoted to identifying and recommending POIs, there are few studies on inferring the lifetime status of POIs. Indeed, the predictive analytics of POI lifetime status can be valuable for various tasks, such as urban planning, business site selection, and real estate appraisal. In this article, we propose a multitask learning approach, named inferring POI lifetime status, to inferring the POI lifetime status with multifaceted data sources. Specifically, we first define three types of POI lifetime status, i.e., booming, decaying, and stable. Then, we formulate a serial classification problem to predict the sequential/successive lifetime statuses of POIs over time. Leveraging geographical data and human mobility data, we examine and integrate three aspects of features related to the prosperity of POIs, i.e., region popularity, region demands, and peer competitiveness. Next, as the booming/decaying POIs are relatively rare in our data, we perform stable class decomposition to alleviate the imbalance between stable POIs and booming/decaying POIs. Finally, we develop a POI lifetime status classifier by exploiting the multitask learning framework as well as the multiclass kernel-based vector machines. We perform extensive experiments using large-scale and real-world datasets of New York City. The experimental results validate the effectiveness of our approach to automatically inferring POI lifetime status.

Guaranteed display (GD) has been a successful model for display advertising. Existing solutions usually model GD services as a crowd-level supply allocation problem. This formulation, however, not only ignores user heterogeneity within crowds, but also makes it difficult to incorporate individual-level constraints. In this paper, we present an large-scale system for personalized delivery in GD advertising services. A unique contribution is to model the allocation problem at the individual level that accounts for user-ad interactions. Therefore, our system can conveniently incorporate complex constraints, such as the priority of GD contracts, the display frequency of ads, and the effectiveness of ad slots arrangement. Moreover, we develop a real-time pacing strategy to fulfill GD contracts with smooth ad delivery and optimized ad performance, such as cost-per-click (CPC) and cost-per-action (CPA). Our system can be parallelized to efficiently compute the delivery solution with billions decision variables. Using both offline evaluation and online A/B tests, we demonstrate that our solution is effective in terms of both accuracy and efficiency.

Adaptive learning, also known as adaptive teaching, relies on learning path recommendation, which sequentially recommends personalized learning items (e.g., lectures, exercises) to satisfy the unique needs of each learner. Although it is well known that modeling the cognitive structure including knowledge level of learners and knowledge structure (e.g., the prerequisite relations) of learning items is important for learning path recommendation, existing methods for adaptive learning often separately focus on either knowledge levels of learners or knowledge structure of learning items. To fully exploit the multifaceted cognitive structure for learning path recommendation, we propose a Cognitive Structure Enhanced framework for Adaptive Learning, named CSEAL. By viewing path recommendation as a Markov Decision Process and applying an actor-critic algorithm, CSEAL can sequentially identify the right learning items to different learners. Specifically, we first utilize a recurrent neural network to trace the evolving knowledge levels of learners at each learning step. Then, we design a navigation algorithm on the knowledge structure to ensure the logicality of learning paths, which reduces the search space in the decision process. Finally, the actor-critic algorithm is used to determine what to learn next and whose parameters are dynamically updated along the learning path. Extensive experiments on real-world data demonstrate the effectiveness and robustness of CSEAL.

Massive data collected by automated fare collection (AFC) systems provide opportunities for studying both personal traveling behaviors and collective mobility patterns in urban areas. Existing studies on AFC data have primarily focused on identifying passengers' movement patterns. However, we creatively leveraged such data for identifying pickpocket suspects. Stopping pickpockets in the public transit system has been crucial for improving passenger satisfaction and public safety. Nonetheless, in practice, it is challenging to discern thieves from regular passengers. In this paper, we developed a suspect detection and surveillance system, which can identify pickpocket suspects based on their daily transit records. Specifically, we first extracted a number of useful features from each passenger's daily activities in the transit system. Then, we took a two-step approach that exploits the strengths of unsupervised outlier detection and supervised classification models to identify thieves, who typically exhibit abnormal traveling behaviors. Experimental results demonstrated the effectiveness of our method. We also developed a prototype system for potential uses by security personnel.

Matching buyers with most suitable sellers providing relevant items (e.g., products) is essential for e-commerce platforms to guarantee customer experience. This matching process is usually achieved through modeling inter-group (buyer-seller) proximity by e-commerce ranking systems. However, current ranking systems often match buyers with sellers of various qualities, and the mismatch is detrimental to not only buyers' level of satisfaction but also the platforms' return on investment (ROI). In this paper, we address this problem by incorporating intra-group structural information (e.g., buyer-buyer proximity implied by buyer attributes) into the ranking systems. Specifically, we propose De ep Gr aph E mbe dding (DEGREE), a deep learning based method, to exploit both inter-group and intra-group proximities jointly for structural learning. With a sparse filtering technique, DEGREE can significantly improve the matching performance with computation resources less than that of alternative deep learning based methods. Experimental results demonstrate that DEGREE outperforms state-of-the-art graph embedding methods on real-world e-commence datasets. In particular, our solution boosts the average unit price in purchases during an online A/B test by up to 11.93%, leading to better operational efficiency and shopping experience.

Following the recent advances of artificial intelligence, financial text mining has gained new potential to benefit theoretical research with practice impacts. An essential research question for financial text mining is how to accurately identify the actual financial opinions (e.g., bullish or bearish) behind words in plain text. Traditional methods mainly consider this task as a text classification problem with solutions based on machine learning algorithms. However, most of them rely heavily on the hand-crafted features extracted from the text. Indeed, a critical issue along this line is that the latent global and local contexts of the financial opinions usually cannot be fully captured. To this end, we propose a context-aware deep embedding network for financial text mining, named CADEN, by jointly encoding the global and local contextual information. Especially, we capture and include an attitude-aware user embedding to enhance the performance of our model. We validate our method with extensive experiments based on a real-world dataset and several state-of-the-art baselines for investor sentiment recognition. Our results show a consistently superior performance of our approach for identifying the financial opinions from texts of different formats.

Recent years have witnessed an opportunity for improving healthcare efficiency and quality by mining Electronic Medical Records (EMRs). This paper is aimed at developing a treatment engine, which learns from historical EMR data and provides a patient with next-period prescriptions based on disease conditions, laboratory results, and treatment records of the patient. Importantly, the engine takes consideration of both treatment records and physical examination sequences which are not only heterogeneous and temporal in nature but also often with different record frequencies and lengths. Moreover, the engine also combines static information (e.g., demographics) with the temporal sequences to provide personalized treatment prescriptions to patients. In this regard, a novel Long Short-Term Memory (LSTM) learning framework is proposed to model inter-correlations of different types of medical sequences by connections between hidden neurons. With this framework, we develop three multifaceted LSTM models: Fully Connected Heterogeneous LSTM, Partially Connected Heterogeneous LSTM, and Decomposed Heterogeneous LSTM. The experiments are conducted on two datasets: one is the public MIMIC-III ICU data, and the other comes from several Chinese hospitals. Experimental results reveal the effectiveness of the framework and the three models. The work is deemed important and meaningful for both academia and practitioners in the realm of medical treatment and prediction, as well as in other fields of applications where intelligent decision support becomes pervasive.

In online education systems, finding similar exercises is a fundamental task of many applications, such as exercise retrieval and student modeling. Several approaches have been proposed for this task by simply using the specific textual content (e.g. the same knowledge concepts or the similar words) in exercises. However, the problem of how to systematically exploit the rich semantic information embedded in multiple heterogenous data (e.g. texts and images) to precisely retrieve similar exercises remains pretty much open. To this end, in this paper, we develop a novel Multimodal Attention-based Neural Network (MANN) framework for finding similar exercises in large-scale online education systems by learning a unified semantic representation from the heterogenous data. In MANN, given exercises with texts, images and knowledge concepts, we first apply a convolutional neural network to extract image representations and use an embedding layer for representing concepts. Then, we design an attention-based long short-term memory network to learn a unified semantic representation of each exercise in a multimodal way. Here, two attention strategies are proposed to capture the associations of texts and images, texts and knowledge concepts, respectively. Moreover, with a Similarity Attention, the similar parts in each exercise pair are also measured. Finally, we develop a pairwise training strategy for returning similar exercises. Extensive experimental results on real-world data clearly validate the effectiveness and the interpretation power of MANN.

Business to Business (B2B) marketing aims at meeting the needs of other businesses instead of individual consumers, and thus entails management of more complex business needs than consumer marketing. The buying processes of the business customers involve series of different marketing campaigns providing multifaceted information about the products or services. While most existing studies focus on individual consumers, little has been done to guide business customers due to the dynamic and complex nature of these business buying processes. To this end, in this paper, we focus on providing a unified view of social and temporal modeling for B2B marketing campaign recommendation. Along this line, we first exploit the temporal behavior patterns in the B2B buying processes and develop a marketing campaign recommender system. Specifically, we start with constructing a temporal graph as the knowledge representation of the buying process of each business customer. Temporal graph can effectively extract and integrate the campaign order preferences of individual business customers. It is also worth noting that our system is backward compatible since the participating frequency used in conventional static recommender systems is naturally embedded in our temporal graph. The campaign recommender is then built in a low-rank graph reconstruction framework based on probabilistic graphical models. Our framework can identify the common graph patterns and predict missing edges in the temporal graphs. In addition, since business customers very often have different decision makers from the same company, we also incorporate social factors, such as community relationships of the business customers, for further improving overall performances of the missing edge prediction and recommendation. Finally, we have performed extensive empirical studies on real-world B2B marketing data sets and the results show that the proposed method can effectively improve the quality of the campaign recommendations for challenging B2B marketing tasks.

Volatile Point-of-Interests (vPOIs) refer to those small businesses which appear and disappear quickly in cities. How to maintain and incubate small business in the urban area is a big concern for both business owners and government administrators. Therefore, the prediction task for the rise and fall of vPOIs is valuable for both shopkeepers and administrators by supporting a variety of applications in urban economics. In this paper, we propose a framework, named FRFP, to predict the prosperity of vPOIs over time. Specifically, due to the data sparsity and skewness of the individual vPOIs, we first aggregate vPOIs prosperities at focal areas w.r.t. each vPOI category. Then we develop the dynamic-continuous CRF (DC-CRF) model to integrate the association between input and output as well as the correlations between outputs from temporal, spatial and contextual perspectives. Finally, we conduct empirical experiments on real-world data from Google Maps and NYC OpenData. The evaluation results demonstrate that our proposed approach outperforms baseline algorithms with considerable margins. In addition, we explore the predictability of different explanatory variables and provide actionable insights for both shopkeepers and urban planners.

Point-of-Interest (POI) demand modeling in urban regions is critical for many applications such as business site selection and real estate investment. While some efforts have been made for the demand analysis of some specific POI categories, such as restaurants, it lacks systematic means to support POI demand modeling. To this end, in this paper, we develop a systematic POI demand modeling framework, named Region POI Demand Identification (RPDI), to model POI demands by exploiting the daily needs of people identified from their large-scale mobility data. Specifically, we first partition the urban space into spatially differentiated neighborhood regions formed by many small local communities. Then, the daily activity patterns of people traveling in the city will be extracted from human mobility data. Since the trip activities, even aggregated, are sparse and insufficient to directly identify the POI demands, especially for underdeveloped regions, we develop a latent factor model that integrates human mobility data, POI profiles, and demographic data to robustly model the POI demand of urban regions in a holistic way. In this model, POI preferences and supplies are used together with demographic features to estimate the POI demands simultaneously for all the urban regions interconnected in the city. Moreover, we also design efficient algorithms to optimize the latent model for large-scale data. Finally, experimental results on real-world data in New York City (NYC) show that our method is effective for identifying POI demands for different regions.

Matrix sketching is aimed at finding compact representations of a matrix while simultaneously preserving most of its properties, which is a fundamental building block in modern scientific computing. Randomized algorithms represent state-of-the-art and have attracted huge interest from the fields of machine learning, data mining, and theoretic computer science. However, it still requires the use of the entire input matrix in producing desired factorizations, which can be a major computational and memory bottleneck in truly large problems. In this paper, we uncover an interesting theoretic connection between matrix low-rank decomposition and lossy signal compression, based on which a cascaded compression sampling framework is devised to approximate an m-by-n matrix in only O(m+n) time and space. Indeed, the proposed method accesses only a small number of matrix rows and columns, which significantly improves the memory footprint. Meanwhile, by sequentially teaming two rounds of approximation procedures and upgrading the sampling strategy from a uniform probability to more sophisticated, encoding-orientated sampling, significant algorithmic boosting is achieved to uncover more granular structures in the data. Empirical results on a wide spectrum of real-world, large-scale matrices show that by taking only linear time and space, the accuracy of our method rivals those state-of-the-art randomized algorithms consuming a quadratic, O(mn), amount of resources.

Advances in real-time location systems have enabled us to collect massive amounts of fine-grained semantically rich location traces, which provide unparalleled opportunities for understanding human activities and generating useful knowledge. This, in turn, delivers intelligence for real-time decision making in various fields, such as workflow management. Indeed, it is a new paradigm to model workflows through knowledge discovery in location traces. To that end, in this paper, we provide a focused study of workflow modeling by integrated analysis of indoor location traces in the hospital environment. In particular, we develop a workflow modeling framework that automatically constructs the workflow states and estimates the parameters describing the workflow transition patterns. More specifically, we propose effective and efficient regularizations for modeling the indoor location traces as stochastic processes. First, to improve the interpretability of the workflow states, we use the geography relationship between the indoor rooms to define a prior of the workflow state distribution. This prior encourages each workflow state to be a contiguous region in the building. Second, to further improve the modeling performance, we show how to use the correlation between related types of medical devices to reinforce the parameter estimation for multiple workflow models. In comparison with our preliminary work [11], we not only develop an integrated workflow modeling framework applicable to general indoor environments, but also improve the modeling accuracy significantly. We reduce the average log-loss by up to 11 percent.

In marketing analytics, customer segmentation (clustering) divides a customer base into groups of similar individuals, while buyer targeting (classification) identifies promising customers. Both customer segmentation and buyer targeting help the business to improve marketing performances by allocating resources to the most profitable customers. Due to the heterogeneity across the customer groups, some studies have been made on combining the tasks of customer segmentation and buyer targeting for tailored marketing strategies. However, these efforts usually combine these two tasks in a simple step-by-step approach. It is still unclear how to implement these two tasks in a more integrated and optimized way, which is the research objective of this paper. Specifically, we formulate customer segmentation and buyer targeting as a unified optimization problem. Then, the customer segments are adaptively realized during the targeting optimization process. In this way, the integrated approach not only improves the buyer targeting performances but also provides a new perspective of segmentation based on the buying decision preferences of the customers. The unified customer segmentation and buyer targeting method not only quantifies the purchase tendency of a specific customer but also characterizes the buying decision behaviors at the segment level. We also develop an efficient K-Classifiers Segmentation algorithm to solve the unified optimization problem. Moreover, we show that the customer segmentation based on the buying decision preferences can also be consistent with the features on customer profiles. Finally, we have performed the extensive experiments on several real-world Business to Business (B2B) marketing data sets. The results show that our approach offers not only more accurate targeting of promising customers but also meaningful customer segmentation solutions with interpretable buying decision preferences for each customer segment.

Recent years have witnessed the boom of venture capital industry. Venture capitalists can attain great financial rewards if their invested companies exit successfully, via being acquired or going IPO (Initial Public Offering). The literature has revealed that, from both financial and managerial perspectives, decision-making process and successful rates of venture capital (VC) investments can be greatly improved if the investors well know the team members of target startups. However, much less efforts have been made on understanding the impact of prominent social ties between the members of VC firms and start-up companies on investment decisions. To this end, we propose to study such social relationship and see how this information can contribute to foreseeing investment deals. We aim at providing analytical guidance for the venture capitalists in choosing right investment targets. Specifically, we develop a Social-Adjusted Probabilistic Matrix Factorization (PMF) model to exploit members social connections information from VC firms and startups for investment recommendations. Unlike previous studies, we make use of the directed relationship between any pair of connected members from the two institutions respectively and quantify the variety of social network groups. As a result, it brings in much more flexibility, and the modeling results inherently provide meaningful managerial implications for the operators of VC firms and startups. Finally, we evaluate our model on both synthetic and real-world data. The results demonstrate that our approach outperforms the baseline algorithms with a significant margin.

Massive data collected by automated fare collection (AFC) systems provide opportunities for studying both personal traveling behaviors and collective mobility patterns in the urban area. Existing studies on the AFC data have primarily focused on identifying passengers' movement patterns. In this paper, however, we creatively leveraged such data for identifying thieves in the public transit systems. Indeed, stopping pickpockets in the public transit systems has been critical for improving passenger satisfaction and public safety. However, it is challenging to tell thieves from regular passengers in practice. To this end, we developed a suspect detection and surveillance system, which can identify pick-pocket suspects based on their daily transit records. Specifically, we first extracted a number of features from each passenger's daily activities in the transit systems. Then, we took a two-step approach that exploits the strengths of unsupervised outlier detection and supervised classification models to identify thieves, who exhibit abnormal traveling behaviors. Experimental results demonstrated the effective- ness of our method. We also developed a prototype system with a user-friendly interface for the security personnel.

Point-of-interest (POI) recommendation, which helps mobile users explore new places, has become an important location-based service. Existing approaches for POI recommendation have been mainly focused on exploiting the information about user preferences, social influence, and geographical influence. However, these approaches cannot handle the scenario where users are expecting to have POI recommendation for a specific time period. To this end, in this paper, we propose a unified recommender system, named the 'Where and When to gO' (WWO) recommender system, to integrate the user interests and their evolving sequential preferences with temporal interval assessment. As a result, the WWO system can make recommendations dynamically for a specific time period and the traditional POI recommender system can be treated as the special case of the WWO system by setting this time period long enough. Specifically, to quantify users' sequential preferences, we consider the distributions of the temporal intervals between dependent POIs in the historical check-in sequences. Then, to estimate the distributions with only sparse observations, we develop the low-rank graph construction model, which identifies a set of bi-weighted graph bases so as to learn the static user preferences and the dynamic sequential preferences in a coherent way. Finally, we evaluate the proposed approach using real-world data sets from several location-based social networks (LBSNs). The experimental results show that our method outperforms the state-of-the-art approaches for POI recommendation in terms of various metrics, such as F-measure and NDCG, with a significant margin.

The analysis of large-scale Electrical Medical Records (EMRs) has the potential to develop and optimize clinical treatment regimens. A treatment regimen usually includes a series of doctor orders containing rich temporal and heterogeneous information. However, in many existing studies, a doctor order is simplified as an event code and a treatment record is simplified as a code sequence. Thus, the information inherent in doctor orders is not fully used for in-depth analysis. In this paper, we aim at exploiting the rich information in doctor orders and developing data-driven approaches for improving clinical treatments. To this end, we first propose a novel method to measure the similarities between treatment records with consideration of sequential and multifaceted information in doctor orders. Then, we propose an efficient density-based clustering algorithm to summarize large-scale treatment records, and extract a semantic representation of each treatment cluster. Finally, we develop a unified framework to evaluate the discovered treatment regimens, and find the most effective treatment regimen for new patients. In the empirical study, we validate our methods with EMRs of 27,678 patients from 14 hospitals. The results show that: 1) Our method can successfully extract typical treatment regimens from large-scale treatment records. The extracted treatment regimens are intuitive and provide managerial implications for treatment regimen design and optimization. 2) By recommending the most effective treatment regimens, the total cure rate in our data improves from 19.89% to 21.28%, and the effective rate increases up to 98.29%.

Sequential pattern analysis aims at finding statistically relevant temporal structures where the values are delivered in a sequence. With the growing complexity of real-world dynamic scenarios, more and more symbols are often needed to encode the sequential values. This is so-called “curse of cardinality”, which can impose significant challenges to the design of sequential analysis methods in terms of computational efficiency and practical use. Indeed, given the overwhelming scale and the heterogeneous nature of the sequential data, new visions and strategies are needed to face the challenges. To this end, in this paper, we propose a “temporal skeletonization” approach to proactively reduce the cardinality of the representation for sequences by uncovering significant, hidden temporal structures. The key idea is to summarize the temporal correlations in an undirected graph, and use the “skeleton” of the graph as a higher granularity on which hidden temporal patterns are more likely to be identified. As a consequence, the embedding topology of the graph allows us to translate the rich temporal content into a metric space. This opens up new possibilities to explore, quantify, and visualize sequential data. Our approach has shown to greatly alleviate the curse of cardinality in challenging tasks of sequential pattern mining and clustering. Evaluation on a business-to-business (B2B) marketing application demonstrates that our approach can effectively discover critical buying paths from noisy customer event data.

In the retail market, the consumers' indecisiveness refers to the inability to make quick and assertive decisions when they choose among competing product options. Indeed, indecisiveness has been investigated in a number of fields, such as economics and psychology. However, these studies are usually based on the subjective customer survey data with some manually defined questions. Instead, in this paper, we provide a focused study on automatically mining indecisiveness in massive customer behaviors in online stores. Specifically, we first give a general definition to measure the observed indecisiveness in each behavior session. From these observed indecisiveness, we can learn the latent factors/reasons by a probabilistic factor-based model. These two factors are the indecisive indexes of the customers and the product bundles, respectively. Next, we demonstrate that this indecisiveness mining process could be useful in several potential applications, such as the competitive product detection and personalized product bundles recommendation. Finally, we perform extensive experiments on a large-scale behavioral logs of online customers in a distributed environment. The results reveal that our measurement of indecisiveness agrees with the common sense assessment, and the discoveries are useful in predicting customer behaviors and providing better recommendation services for both customers and online retailers.

Business to Business (B2B) marketing aims at meeting the needs of other businesses instead of individual consumers. In B2B markets, the buying processes usually involve series of different marketing campaigns providing necessary information to multiple decision makers with different interests and motivations. The dynamic and complex nature of these processes imposes significant challenges to analyze the process logs for improving the B2B marketing practice. Indeed, most of the existing studies only focus on the individual consumers in the markets, such as movie/product recommender systems. In this paper, we exploit the temporal behavior patterns in the buying processes of the business customers and develop a B2B marketing campaign recommender system. Specifically, we first propose the temporal graph as the temporal knowledge representation of the buying process of each business customer. The key idea is to extract and integrate the campaign order preferences of the customer using the temporal graph. We then develop the low-rank graph reconstruction framework to identify the common graph patterns and predict the missing edges in the temporal graphs. We show that the prediction of the missing edges is effective to recommend the marketing campaigns to the business customers during their buying processes. Moreover, we also exploit the community relationships of the business customers to improve the performances of the graph edge predictions and the marketing campaign recommendations. Finally, we have performed extensive empirical studies on real-world B2B marketing data sets and the results show that the proposed method can effectively improve the quality of the campaign recommendations for challenging B2B marketing tasks.

The rapid growth in the development of healthcare information systems has led to an increased interest in utilizing the patient Electronic Health Records (EHR) for assisting disease diagnosis and phenotyping. The patient EHRs are generally longitudinal and naturally represented as medical event sequences, where the events include clinical notes, problems, medications, vital signs, laboratory reports, etc. The longitudinal and heterogeneous properties make EHR analysis an inherently difficult challenge. To address this challenge, in this paper, we develop a novel representation, namely the temporal graph, for such event sequences. The temporal graph is informative for a variety of challenging analytic tasks, such as predictive modeling, since it can capture temporal relationships of the medical events in each event sequence. By summarizing the longitudinal data, the temporal graphs are also robust and resistant to noisy and irregular observations. Based on the temporal graph representation, we further develop an approach for temporal phenotyping to identify the most significant and interpretable graph basis as phenotypes. This helps us better understand the disease evolving patterns. Moreover, by expressing the temporal graphs with the phenotypes, the expressing coefficients can be used for applications such as personalized medicine, disease diagnosis, and patient segmentation. Our temporal phenotyping framework is also flexible to incorporate semi-supervised/supervised information. Finally, we validate our framework on two real-world tasks. One is predicting the onset risk of heart failure. Another is predicting the risk of heart failure related hospitalization for patients with COPD pre-condition. Our results show that the diagnosis performance in both tasks can be improved significantly by the proposed approaches. Also, we illustrate some interesting phenotypes derived from the data.

The emergence of social networks has provided opportunities for both targeted marketing and viral marketing. By concentrating the efforts on a few key customers, targeted marketing could make the promotion of the items (products) much easier and more cost-effective. On the other hand, viral marketing aims at finding a set of individuals (seeds) to maximize the word-of-mouth propagation of an item. However, these two marketing strategies can only exploit some specific characteristics of the social networks, and the problem of how to combine them together to build a better, stronger business is still open. To that end, in this paper, we propose a general approach for integrated marketing. Specifically, to market a given item, we first generate the item-specific candidate users by a recommendation algorithm, and then select the typical users who have the best balanced utility scores and consumption/social entropy. Next, treating typical users as targeted customers, we study the problem of maximizing information awareness in viral marketing with these constrained targets. Along this line, we define it as a constrained coverage maximization problem, and propose three solutions: GMIC, LMIC and QMIC. Finally, extensive experimental results on real-world datasets demonstrate that our integrated marketing approach could outperform the methods that consider only targeted marketing or viral marketing.

Optimal planning for public transportation is one of the keys to sustainable development and better quality of life in urban areas. Compared to private transportation, public transportation uses road space more efficiently and produces fewer accidents and emissions. In this paper, we focus on the identification and optimization of flawed bus routes to improve utilization efficiency of public transportation services, according to people's real demand for public transportation. To this end, we first provide an integrated mobility pattern analysis between the location traces of taxicabs and the mobility records in bus transactions. Based on mobility patterns, we propose a localized transportation mode choice model, with which we can accurately predict the bus travel demand for different bus routing. This model is then used for bus routing optimization which aims to convert as many people from private transportation to public transportation as possible given budget constraints on the bus route modification. We also leverage the model to identify region pairs with flawed bus routes, which are effectively optimized using our approach. To validate the effectiveness of the proposed methods, extensive studies are performed on real world data collected in Beijing which contains 19 million taxi trips and 10 million bus trips.

Advances in real-time location system (RTLS) solutions have enabled us to collect massive amounts of fine-grained semantically rich location traces, which provide unparalleled opportunities for understanding human activities and discovering useful knowledge. This, in turn, delivers intelligence for real-time decision making in various fields, such as workflow management. Indeed, it is a new paradigm for workflow modeling by the knowledge discovery in location traces. To that end, in this paper, we provide a focused study of workflow modeling by the integrated analysis of indoor location traces in the hospital environment. In comparison with conventional workflow modeling based on passive workflow logs, one salient feature of our approach is that it can proactively unravel the workflow patterns hidden in the location traces, by automatically constructing the workflow states and estimating parameters describing the transition patterns of moving objects. Specifically, to determine a meaningful granularity for the model, the workflow states are first constructed as regions associated with specific healthcare activities. Then, we transform the original indoor location traces to the sequences of workflow states and model the workflow transition patterns by finite state machines. Furthermore, we leverage the correlations in the location traces between related types of medical devices to reinforce the modeling performance and enable more applications. The results show that the proposed framework can not only model the workflow patterns effectively, but also have managerial applications in workflow monitoring, auditing, and inspection of workflow compliance, which are critical in the healthcare industry.

Sequential pattern analysis targets on finding statistically relevant temporal structures where the values are delivered in a sequence. With the growing complexity of real-world dynamic scenarios, more and more symbols are often needed to encode a meaningful sequence. This is so-called 'curse of cardinality', which can impose significant challenges to the design of sequential analysis methods in terms of computational efficiency and practical use. Indeed, given the overwhelming scale and the heterogeneous nature of the sequential data, new visions and strategies are needed to face the challenges. To this end, in this paper, we propose a 'temporal skeletonization' approach to proactively reduce the representation of sequences to uncover significant, hidden temporal structures. The key idea is to summarize the temporal correlations in an undirected graph. Then, the 'skeleton' of the graph serves as a higher granularity on which hidden temporal patterns are more likely to be identified. In the meantime, the embedding topology of the graph allows us to translate the rich temporal content into a metric space. This opens up new possibilities to explore, quantify, and visualize sequential data. Our approach has shown to greatly alleviate the curse of cardinality in challenging tasks of sequential pattern mining and clustering. Evaluation on a Business-to-Business (B2B) marketing application demonstrates that our approach can effectively discover critical buying paths from noisy customer event data.

Rapid growth in the development of real-time location system solutions has led to an increased interest in indoor location-aware services, such as hospital asset management. Although there are extensive studies in the literature on the analysis of outdoor location traces, the studies of indoor location traces are less touched and fragmented. To that end, in this paper, we provide a focused study of indoor location traces collected by the sensors attached to medical devices in a hospital environment. Along this line, we first introduce some unique properties of these indoor location traces. We show that they can capture the movement patterns of the medical devices, which are tightly coupled with the work flow in the controlled hospital environment. Based on this observation, we propose a stochastic model for context-aware anomaly detection in indoor location traces, which exploits the hospital work flow and models the movements of medical devices as transitions in finite state machines. In detail, we first develop a density-based method to identify the hotspots filled with high-level abnormal activities in the indoor environment. The discovered hotspots serve as the context for nearby trajectories. Then, we introduce an N-gram based method for measuring the degree of anomaly based on the detected hotspots, which is able to predict the missing events possibly due to the devices being stolen. Besides, to address the noisy nature of the indoor sensor networks, we also propose an iterative algorithm to estimate the transition probabilities. This algorithm allows to effectively recover the missing location records which are critical for the abnormality estimation. Finally, the experimental results on the real-world date sets validate the effectiveness of the proposed context-aware anomaly detection method for identifying abnormal events.

It is well known that the distance metric plays an important role in the clustering process. Indeed, many clustering problems can be treated as an optimization problem of a criterion function defined over one distance metric. While many distance metrics have been developed, it is not clear that how these distance metrics can impact on the clustering/optimization process. To that end, in this paper, we study the impact of a set of popular cosine-based distance metrics on K-means clustering. Specifically, by revealing the common order-preserving property, we first show that K-means has exactly the same cluster assignment for these metrics during the E-step. Next, by both theoretical and empirical studies, we prove that the cluster centroid is a good approximator of their respective optimal centers in the M-step. As such, we identify a problem with K-means: it cannot differentiate these metrics. To explore the nature of these metrics, we propose an evolutionary K-means framework that integrates K-means and genetic algorithms. This framework not only enables inspection of arbitrary distance metrics, but also can be used to investigate different formulations of the optimization problem. Finally, this framework is used in extensive experiments on real-world data sets. The results validate our theoretical findings on the characteristics and interrelationships of these metrics. Most importantly, this paper furthers our understanding of the impact of the distance metrics on the optimization process of K-means.

Advances in GPS tracking technology have enabled us to install GPS tracking devices in city taxis to collect a large amount of GPS traces under operational time constraints. These GPS traces provide unparallel opportunities for us to uncover taxi driving fraud activities. In this paper, we develop a taxi driving fraud detection system, which is able to systematically investigate taxi driving fraud. In this system, we first provide functions to find two aspects of evidences: travel route evidence and driving distance evidence. Furthermore, a third function is designed to combine the two aspects of evidences based on Dempster-Shafer theory. To implement the system, we first identify interesting sites from a large amount of taxi GPS logs. Then, we propose a parameter-free method to mine the travel route evidences. Also, we introduce route mark to represent a typical driving path from an interesting site to another one. Based on route mark, we exploit a generative statistical model to characterize the distribution of driving distance and identify the driving distance evidences. Finally, we evaluate the taxi driving fraud detection system with large scale real-world taxi GPS logs. In the experiments, we uncover some regularity of driving fraud activities and investigate the motivation of drivers to commit a driving fraud by analyzing the produced taxi fraud data.

The increasing availability of large-scale location traces creates unprecedent opportunities to change the paradigm for knowledge discovery in transportation systems. A particularly promising area is to extract useful business intelligence, which can be used as guidance for reducing inefficiencies in energy consumption of transportation sectors, improving customer experiences, and increasing business performances. However, extracting business intelligence from location traces is not a trivial task. Conventional data analytic tools are usually not customized for handling large, complex, dynamic, and distributed nature of location traces. To that end, we develop a taxi business intelligence system to explore the massive taxi location traces from different business perspectives with various data mining functions. Since we implement the system using the real-world taxi GPS data, this demonstration will help taxi companies to improve their business performances by understanding the behaviors of both drivers and customers. In addition, several identified technical challenges also motivate data mining people to develop more sophisticate techniques in the future.