A gray market emerges when some distributors divert products to unauthorized distributors/retailers to make sneaky profits from the manufacturers’ differential channel incentives, such as quantity discounts. Traditionally, manufacturers rely heavily on internal audits to periodically investigate the flows of products and funds so as to deter the gray market; however, this is too costly given the large number of distributors and their huge volumes of orders. Owing to the advances in data analytics techniques, the ordering quantities of a distributor over time, which form multivariate time series, can help reveal suspicious product diversion behaviors and narrow the audit scope drastically. To that end, in this paper, we build on the recent advancement of representation learning for time series and adopt a sequence autoencoder to automatically characterize the overall demand patterns. To cope with the underlying entangled factors and interfering information in the multivariate time series of ordering quantities, we develop a disentangled learning scheme to construct more effective sequence representations. An interdistributor correlation regularization is also proposed to ensure more reliable representations. Finally, given the highly scarce anomaly labels for the detection task, an unsupervised deep generative model based on the learned representations of the distributors is developed to estimate the densities of distributions, which enables the anomaly scores generated through end-to-end learning. Extensive experiments on a real-world distribution channel data set and a larger simulated data set empirically validate our model’s superior and robust performances compared with several state-of-the-art baselines. Additionally, our illustrative economic analysis demonstrates that the manufacturers can launch more targeted and cost-effective audits toward the suspected distributors recommended by our model so as to deter the gray market. History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning. Funding: This work was supported by the National Natural Science Foundation of China [Grants 72031001, 72301017, 72371011, and 72242101]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0155 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2022.0155 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

Frauds in supply chain finance not only result in substantial loss for financial institutions (e.g., banks, trust company, private funds), but also are detrimental to the reputation of the ecosystem. However, such frauds are hard to detect due to the complexity of the operating environment in supply chain finance such as involvement of multiple parties under different agreements. Traditional instruments of financial institutions are time-consuming yet insufficient in countering fraudulent supply chain financing. In this study, we propose a novel blockchain-driven framework for deterring fraud in supply chain finance. Specifically, we use inventory financing in jewelry supply chain as an illustrative scenario. The blockchain technology enables secure and trusted data sharing among multiple parties due to its characteristics of immutability and traceability. Consequently, information on manufacturing, brand license, and warehouse status are available to financial institutions in real time. Moreover, we develop a novel rule-based fraud check module to automatically detect suspicious fraud cases by auditing documents shared by multiple parties through a blockchain network. To validate the effectiveness of the proposed framework, we employ agent-based modeling and simulation. Experimental results show that our proposed framework can effectively deter fraudulent supply chain financing as well as improve operational efficiency.

Abstract Entrepreneurs are showing an increasing focus on understanding and managing their social media strategies to optimize the success of their crowdfunding campaigns. While much of the current crowdfunding literature focuses on the roles of social media engagement in the funding performance of crowdfunded projects, in this study, drawing on social media engagement theory, we examine how product and entrepreneur characteristics moderate the influence of social media engagement on funding performance in the reward‐based crowdfunding. Using a dataset of technology crowdfunded projects, we investigated whether Facebook and Twitter engagements affect funding outcomes and if so, how the two interact with each other and their influences vary by project type (hardware and software) and entrepreneur characteristics (gender, experience, and social capital). We found that both Facebook and Twitter engagements positively affect funding, but the two weaken each other's impact, particularly for hardware products. Additionally, Facebook engagements had a larger effect on funding outcomes in the early days of a campaign driven by its prelaunch efforts, whereas Twitter engagements had a larger impact in later days. Furthermore, our findings indicated that Facebook engagement is more influential for hardware products. An entrepreneur's internal social capital built inside the crowdfunding platform also weakened the effects of Facebook engagements generated outside the platform, whereas Twitter engagements on subsequent funding had less influence on experienced entrepreneurs. Our findings suggest that Facebook mainly serves as a channel to show the significant commitment of entrepreneurs to their projects and increase persuasiveness, while Twitter helps to raise awareness by broadcasting crowdfunding campaigns among potential investors.

Driving risk evaluation is a critical issue in driving safety analysis. In traditional driving risk evaluation models, vehicles are analyzed as isolated units. Nevertheless, vehicles are surrounded by other vehicles during driving in a real setting, and therefore, the driving patterns of target vehicles are inevitably affected by surrounding vehicles. In this paper, we proposed a new driving risk evaluation model incorporating the driving patterns of the target vehicle, the driving patterns of surrounding vehicles, and the interactions between the target vehicle and surrounding vehicles to improve driving safety in situations like car-following and merging situations. According to experiments on real data, our proposed method outperformed the state-of-the-art methods by at least 14.2% in terms of precision. Our work verified that factors like the driving patterns of surrounding vehicles and the interactions between a target vehicle and surrounding vehicles can enhance the performance of driving risk evaluation. The experimental results also showed that the driving patterns of surrounding vehicles in different positions vary in evaluating the driving risk of the target vehicle. More specifically, the surrounding vehicles in cross positions casted the strongest influence, followed by the surrounding vehicles in the diagonal cross positions. In summary, our study provided a novel way to enhance driving risk evaluation performance for driving safety improvement.

Blockchain, an emerging paradigm of secure and shareable computing, is a systematic integration of 1) chain structure for data verification and storage, 2) distributed consensus algorithms for generating and updating data, 3) cryptographic techniques for guaranteeing data transmission and access security, and 4) automated smart contracts for data programming and operations. However, the progress and promotion of Blockchain have been seriously impeded by various security issues in blockchain-based applications. Furthermore, previous research on blockchain security has been mostly technical, overlooking considerable business, organizational, and operational issues. To address this research gap from the perspective of information systems, we review blockchain security research in three levels, namely, the process level, the data level, and the infrastructure level, which we refer to as the PDI model of blockchain security. In this survey, we examine the state of blockchain security in the literature. Based on the insights obtained from this initial analysis, we then suggest future directions of research in blockchain security, shedding light on urgent business and industrial concerns in related computing disciplines.

Blockchain is a new generation of secure information technology that is fueling business and industrial innovation. Many studies on key enabling technologies for resource organization and system operation of blockchain-secured smart manufacturing in Industry 4.0 had been conducted. However, the progression and promotion of these blockchain applications have been fundamentally impeded by various issues in scalability, flexibility, and cybersecurity. This survey discusses how blockchain systems can overcome potential cybersecurity barriers to achieving intelligence in Industry 4.0. In this regard, eight cybersecurity issues (CIs) are identified in manufacturing systems. Ten metrics for implementing blockchain applications in the manufacturing system are devised while surveying research in blockchain-secured smart manufacturing. This study reveals how these CIs have been studied in the literature. Based on insights obtained from this analysis, future research directions for blockchain-secured smart manufacturing are presented, which potentially guides research on urgent cybersecurity concerns for achieving intelligence in Industry 4.0.

Live chat, which is embedded in some shopping websites, allows a retailer to communicate with its shoppers directly and respond to their inquiries promptly. We extended the Speech Act Theory (SAT) to this context by developing the Dialog Conversion Model (DCM) that elucidates the characteristics of online dialog between shoppers and retailers. We validated the DCM using quantitative and qualitative data. The quantitative analyses of 1,185 communication sessions and related purchase records reflect that shoppers' cognitive, rather than affective, expressions tend to indicate their purchase intentions, and retailers should emphasize cognitive expressions to the extent possible while being strategic in their choice of expressions. Furthermore, the affective expressions (in positive and negative forms) articulated by retailers have a considerable influence on purchase conversion. However, the same is not true for shoppers. Post‐hoc interviews were conducted with shoppers to gain additional insights.

The growth of individualized product demands drives high flexibility of manufacturing processes, which requires large-scale deployment of Industrial Internet of Things (IIoT). Since centralized control of IIoT suffers from poor flexibility in coping with disturbances and changes, a decentralized organization structure is a better choice, in which a permissioned blockchain-driven IIoT can enable partially decentralized self-organization and thus offload and accelerate the optimization of upper-level manufacturing planning. A novel iterative bi-level hybrid intelligence model named ManuChain is proposed to get rid of unbalance/inconsistency between holistic planning and local execution in individualized manufacturing systems. Lower-level blockchain-driven smart contracts proactively decentralize fine-grained and individualized task execution among machine tools via Raspberry Pi-based smart gateways and make the results available on an upper-level digital twin model for iterative coarse-grained holistic optimization. A prototype ManuChain based on a permissioned blockchain network is presented to realize both lower-level crowd self-organizing intelligence and upper-level holistic optimization intelligence.

One challenge to the success of online knowledge-sharing communities relates to the participants' longtime participation. Literature has explored the determinants of initial participation rather than longtime participation despite significant differences between them. To fill this research gap, this article conceptualizes involvement and continuous commitment regarding longtime participation and examines their antecedents in the Chinese context. Extending the expectancy-value theory, knowledge-sharing expectancy, knowledge-sharing value, and knowledge-sharing affect are identified as antecedents of involvement and continuous commitment. This article further suggests that interpersonal trust and the norm of reciprocity are important contextual factors in the Chinese context that enhance the positive impacts of these antecedents on involvement and continuous commitment. Empirical results confirm most hypotheses. Interestingly, the impact of knowledge-sharing affect is not influenced by interpersonal trust or the norm of reciprocity. Both theoretical and practical implications are discussed.

It is well documented in management literature that characteristics of collaboration processes strongly influence team performance in a business environment. However, little work has been done on how specific collaboration process patterns affect teamwork performance, leading to an open issue in collaboration management. To address this research gap, we develop a Collaboration Process Pattern (CPP) approach that analyzes teamwork performance by mining collaboration system logs from open source software development. Our research is novel in three ways. First, our research is fact-driven, as the result is based on teamwork tracking logs. Second, we develop a pattern mining approach based on sequence mining and graph mining. Third, using time-dependent Cox regression, our approach derives business insights from real-world collaboration data that are directly applicable to managerial actions. Our empirical study identifies collaboration patterns that can lead to more efficient teamwork. It also shows that the effects of collaboration patterns vary depending on the types of tasks. These findings are of significant business value since they suggest that managers should carefully prioritize their limited attention on certain types of tasks for intervention. Data and the online supplement are available at https://doi.org/10.1287/ijoc.2016.0739 .

Mobile business is becoming a reality due to ubiquitous Internet connectivity, popular mobile devices, and widely available cloud services. However, characteristics of the mobile environment, such as mobility, unpredictability, and variation of mobile network's signal strength, present challenges in selecting optimal services for composition. Traditional QoS-aware methods that select individual services with the best QoS may not always result in the best composite service because constant mobility makes the performance of service invocation unpredictable and location-based. This paper discusses the challenges of this problem and defines it in a formal way. To solve this new research problem, we propose a mobility model, a mobility-aware QoS computation rule, and a mobility-enabled selection algorithm with teaching-learning-based optimization. The experimental simulation results demonstrate that our approach can obtain better solutions than current standard composition methods in mobile environments. The approach can obtain near-optimal solutions and has a nearly linear algorithmic complexity with respect to the problem size.

QoS as an important criterion has attracted more and more attention in the service selection process. Various QoS-aware service selection methods have been proposed in recent years. However, few of them take into account of the QoS correlations between services, causing several performance issues. QoS correlations can be defined as that some QoS attributes of a service are not only dependent on the service itself but are also correlated to other services. Since such correlations will affect QoS values, it is important to study how to select appropriate candidate services while taking into account of QoS correlations when generating composite services with optimal QoS values. To this end, we propose a novel method of service selection, called the correlation-aware service pruning (CASP) method. It manages QoS correlations by accounting for all services that may be integrated into optimal composite services and prunes services that are not the optimal candidate services. Our experiments show that this method can manage complicated correlations between services and significantly improve the QoS values of the generated composite services.

Ontology is the backbone of the Semantic Web, helping users search for relevant resources from the Web of linked data. The existing context-free mapping approach between tags and concepts fails to address the problems of social synonymy and social polysemy when ontologies are induced from folksonomies. The novel contributions of this paper are threefold. First, grounded in the cognitively motivated category utility measure, a novel basic-level concept mining algorithm is developed to construct semantically rich concept vectors to alleviate the problem of social synonymy. Second, contextual aspects of ontology learning are exploited via probabilistic topic modeling to address the problem of social polysemy. Third, a novel context-sensitive domain ontology learning algorithm that combines link- and content-based semantic analysis is developed to identify both taxonomic and associative relations among concepts. To the best of our knowledge, this is the first successful research that exploits a cognitively motivated method to learn context-sensitive domain ontologies from folksonomies. By using the Open Directory Project ontology as a benchmark, we examined the effectiveness of the proposed algorithms based on social annotations crawled from three different folksonomy sites. Our experimental results show that the proposed ontology learning system significantly outperforms the best baseline system by 13.83% in terms of taxonomic F-measure. The practical implication of our research is that high-quality ontologies are constructed with minimal human intervention to facilitate concept-driven retrieval of linked data and the knowledge-based interoperability among enterprises.

Classical supervised machine learning techniques have been explored for semantically annotating unstructured textual data such as consumers' comments archived at social media websites to extract business intelligence. However, these techniques often require a large number of manually labeled training examples to produce accurate annotations. Several active learning approaches that are designed based on probabilistic sequence models have been explored to minimize the number of labeled training examples for semantic annotation tasks. Recent research has shown that large-margin classifiers are viable alternatives to automated semantic annotation, given their strong generalization capabilities and the ability to process high-dimensional data. However, the existing active learning methods that are designed for probabilistic sequence models cannot be easily adapted and applied to large-margin classifiers. The main contribution of this paper is the development of novel active learning methods for large-margin classifiers to fill the aforementioned research gap. In particular, we propose an innovative perspective of taking active learning as a search of optimal parameters for large-margin classifiers. A rigorous evaluation involving two benchmark tests and an empirical test based on real-world data extracted from Amazon.com reveals that the proposed active learning methods can train effective classifiers with significantly fewer training examples while achieving similar annotation performance, compared to a typical state-of-the-art classifier that only uses several labeled training examples. More specifically, one of our proposed active learning methods can reduce the number of training examples by 19.74% at the 68% level of F1 when compared to the best baseline method, as evaluated based on the Amazon data set. Our research opens the door to the application of intelligent semantic annotation techniques to support real-world applications such as automatically analyzing consumer comments for customer relationship management.

The effective use of corporate memory is becoming increasingly important because every aspect of e‐business requires access to information repositories. Unfortunately, less‐than‐satisfying effectiveness in state‐of‐the‐art information‐retrieval techniques is well known, even for some of the best search engines such as Google. In this study, the authors resolve this retrieval ineffectiveness problem by developing a new framework for predicting query performance, which is the first step toward better retrieval effectiveness. Specifically, they examine the relationship between query performance and query context. A query context consists of the query itself, the document collection, and the interaction between the two. The authors first analyze the characteristics of query context and develop various features for predicting query performance. Then, they propose a context‐sensitive model for predicting query performance based on the characteristics of the query and the document collection. Finally, they validate this model with respect to five real‐world collections of documents and demonstrate its utility in routing queries to the correct repository with high accuracy.

Data security in e-markets is vital to maintaining trust among trading partners. In an e-market, companies must share information to improve operational efficiency in their supply chains, while at the same time, access to sensitive information by rival companies should be prevented. In today’s highly dynamic business environment, the relationships among companies in e-markets are constantly changing while these relationships determine how company information should be shared with other companies. In this paper, the authors show that existing access control models are not designed for managing data security in e-markets with dynamic company relationships and propose a Relationship Driven Access Control (RDAC) model to provide a better solution. In particular, the authors design a rule-based approach for managing dynamic company relationships and a secure query processing mechanism to filter shared information based on company relationships. A prototype system is developed to demonstrate and validate the authors’ RDAC model.

Community-based open source, or “community source”, has emerged as an innovative approach to developing open-source enterprise application software (EAS). Unlike the conventional model of in-house development, community source creates a virtual software development community that pools human, financial, and technological resources from multiple partner organizations to develop custom software solutions. The solution is available as open-source software to all end users. In this way, the community source model takes a step forward from outsourcing to third-party software vendors. By studying a real-world case of the Kuali community source project, the authors found that community source faced a number of challenges in project management, particularly in the areas of in-house staffing and project sustainability. The interview analysis further concludes that outsourcing the community source development to either domestic or foreign third-party vendors could be a viable solution. Finally, the authors propose a research framework and seven related propositions that warrant future investigation into the relationship between community source and software outsourcing.

Workflow systems provide the key technology to enable business-process automation. One important function of workflow management is role resolution, i.e., the mechanism of assigning tasks to individual workers at runtime according to the role qualification defined in the workflow model. Role-resolution decisions directly affect the productivity of workers in an organization, and consequently affect corporate profitability. Therefore it is important to develop effective policies governing these decisions. However, there has not been a formal treatment of role-resolution policies in the literature. In this paper, we analyze role-resolution policies used in current workflow practice and propose new optimization-based policies that utilize online batching. Through a computational study, we examine three workflow-performance measures including maximum flowtime, average workload, and workload variation under these policies in different business scenarios. These scenarios vary by overall system load, task-processing-time distribution, and the number of workers. Based on computational results, we obtain the following insights that can help guide the selection of role-resolution policies. (a) As the overall system load increases, the benefit of using batching-based online optimization policies becomes more significant. (b) Processing-time variation has a major impact on workflow performance, and higher variation favors optimization-based policies. (c) Online optimization has the potential to reduce average workload significantly, and to reduce workload variation significantly as well.

Online analytical processing (OLAP) is becoming increasingly important as today's organizations frequently make business decisions based on statistical analysis of their enterprise data. This data is multidimensional and is derived from transactional data using various levels of aggregation. As the business model changes frequently, the multidimensional arrays must be extended in terms of the value ranges of each dimension and even new dimensions. We propose new methods to deal with disk resident extendible arrays. A new index data structure for keeping track of the extensions is introduced, and a performance analysis is conducted for array extension and retrievals.

Future multimedia information systems are likely to manage thousands of videos with various lengths and display requirements. Mismatch of playback and delivery rates of compressed video data requires sophisticated buffer management algorithms to guarantee smooth playback of video data. In this paper, we address some of the many design and operational issues including buffer size requirements, refreshing policies, and support of multiple access points to the same video object. Three different buffer management strategies are proposed and analyzed to minimize the average waiting time while ensuring display without jerkiness. We also evaluate the effectiveness these buffer management strategies with a simulation study.>

We describe a manufacturing environment where, driven by market forces, organizations cooperate as well as compete with one another. We argue that a federated database system (FDBS) is appropriate for such an environment. Contrary to conventional wisdom, complete transparency, assumed desirable and mandatory in distributed database systems, is neither desirable nor feasible in this environment. We propose a new approach that is based on schema coordination rather than integration under which each component database is free to change its data structure, attribute naming, and data semantics. A federated metadata model based on the notion of universal relation is introduced for the FDBS. We also develop the query processing paradigm, and present procedures for query transformation and heterogeneity resolution.>

In intelligent database systems, knowledge directed inference often derives large amounts of data, and the efficiency of query processing in these systems depends upon how the derived data is maintained. This paper focuses on situations where the rule is conditional on a join of multiple data objects (relations) and the rule-derived data are materialized to reduce the overall query processing costs. We develop an indexing technique based on a unique construct called join pattern relation. Several pattern redundancy reduction methods are also introduced to minimize the overhead cost of join indexing.

Spatial data are found in geographic information systems such as digital road map databases where city and road attributes are associated with nodes and links in a directed graph. Queries on spatial data are expensive because of the recursive property of graph traversal. We propose a graph indexing technique to expedite spatial queries where the graph topology remains relatively stationary. Using a probabilistic analysis, this paper shows that the graph indexing technique significantly improves the efficiency of constrained spatial queries.

In intelligent database systems, knowledge-directed inference often derives large amounts of & @ and the efficiency of query processing in these systems depends upon how the derived data are maintained, This paper focuses on situations where data-deriving rules are conditional on joins of multiple data objects (or relations) and the derived data are materialized to reduce the overall query processing costs. Join indexing is needed for the efficient maintenance of such rule-derived daa but existing join indexing methods are not suitable for this purpose. We develop a family of join indexing techniques-join pattern indexing-- based on a unique construct called join pattern relation. The performance of the proposed join pattern indexing techniques is evaluated to demonstrate their cost effectiveness. 1.

Rule processing strategies in expert database systems which involve rules conditional on join results of base relations are studied. In particular, those rules that require very fast response time in their evaluation are considered. It is proposed to materialize the results of firing a rule in a relation, the rule relation. Performance evaluation of several strategies shows that under the clustered B-trees, strategies using pattern relations perform better than those without pattern relations. The strategy with skinny pattern relations performs poorly in comparison to that with bulky pattern relations. The selective bulky pattern strategy performs better than the bulky pattern strategy. The selective pattern strategy outperforms other strategies in terms of expected total cost. However, it always uses more storage space than the direct materialization.>