The proliferation of fraud in online shopping has accompanied the development of e-commerce, leading to substantial economic losses, and affecting consumer trust in online shopping. However, few studies have focused on fraud detection in e-commerce due to its diversity and dynamism. In this work, we conduct a feature set specifically for e-commerce payment fraud, around transactions, user behavior, and account relevance. We propose a novel comprehensive model called Neural Network Based Ensemble Learning with Generation (NNEnsLeG) for fraud detection. In this model, ensemble learning, data generation, and parameter-passing are designed to cope with extreme data imbalance, overfitting, and simulating the dynamics of fraud patterns. We evaluate the model performance in e-commerce payment fraud detection with >310,000 pieces of e-commerce account data. Then we verify the effectiveness of the model design and feature engineering through ablation experiments, and validate the generalization ability of the model in other payment fraud scenarios. The experimental results show that NNEnsLeG outperforms all the benchmarks and proves the effectiveness of generative data and parameter-passing design, presenting the practical application of the NNEnsLeG model in e-commerce payment fraud detection.

As a novel business phenomenon, virtual streamers are increasingly employed to promote consumer purchases in live streaming commerce. However, few scholars have focused on how virtual streamers influence consumer purchase intentions. By drawing upon source credibility theory and the stimulus‒organism‒response framework, this study investigates the mechanism through which perceived characteristics of virtual streamers shape purchase intentions, based on survey data from 318 live streaming consumers. The empirical results demonstrate that consumers’ perceived attractiveness, intelligence, interactivity, and congruence of virtual streamers significantly show associations with consumer purchase intentions through their mediation effects on trust and affection. Notably, perceived attractiveness exhibits a stronger association with affection than with trust, whereas perceived intelligence shows the reverse pattern. Furthermore, fuzzy-set qualitative comparative analysis is used to investigate two different configuration options that can lead to high purchase intentions. The results of this study can help guide effective marketing strategies in live streaming commerce.

It is known that streamers play a special role in live streaming commerce, but there is a huge discrepancy in sales performance resulting from different characteristics of streamers. This study applies social influence theory to systematically analyze how streamer characteristics interact to affect sales performance. Using a unique dataset of 120,794 live streaming records from 597 streamers on Douyin platform, we establish a fixed effects model with unbalanced panel data. The results show that previous sales have strong momentum effects. Total views, number of live commercial products and live streaming duration all have a positive impact on sales volumes. Heterogeneity analysis reveals significant differences across identity types, industry types, and authentication statuses, with celebrities, streamers from entertainment and leisure sectors, and unverified streamers showing notably stronger gains. These findings provide empirical evidence to guide streamers and platforms in optimizing marketing strategies in the competitive live streaming commerce.

PurposeThis study aims to investigate the role of information normalization in online healthcare consultation, a typical complex human-to-human communication requiring both effectiveness and efficiency. The globalization and digitization trend calls for high-quality information, and normalization is considered an effective method for improving information quality. Meanwhile, some researchers argued that excessive normalization (standardized answers) may be perceived as impersonal, repetitive, and cold. Thus, it is not appreciated for human-to-human communication, for instance, when patients are anxious about their health condition (e.g. with high-risk disease) in online healthcare consultation. Therefore, the role of information normalization in human communication is worthy to be explored.Design/methodology/approachData were collected from one of the largest online healthcare consultation platforms (Dxy.com). This study expanded the existing information quality model by introducing information normalization as a new dimension. Information normalization was assessed using medical templates, extracted through natural language processing methods such as Bidirectional Encoder Representations from Transformers (BERT) and Latent Dirichlet Allocation (LDA). Patient decision-making behaviors, namely, consultant selection and satisfaction, were chosen to evaluate communication performance.FindingsThe results confirmed the positive impact of information normalization on communication performance. Additionally, a negative moderating effect of disease risk on the relationship between information normalization and patient decision-making was identified. Furthermore, the study demonstrated that information normalization can be enhanced through experiential learning.Originality/valueThese findings highlighted the significance of information normalization in online healthcare communication and extended the existing information quality model. It also facilitated patient decision-making on online healthcare platforms by providing a comprehensive information quality measurement. In addition, the moderating effects indicated the contradiction between informational support and emotional support, enriching the social support theory.

A growing number of enterprises begin to utilize user-generated content (UGC) to help build brand awareness and loyalty on social media platforms. Thus, it is important to investigate what makes UGC more helpful under the new social media environment. This study attempts to identify the influence mechanism of UGC helpfulness by examining the systematic impacts of argument quality and source reliability, especially considering the effects of creator interactivity. Using a dataset of product-related UGC in a popular social media app, our empirical study finds that the detailedness, readability, and objectivity of the content, as well as the social recognition and popularity of the creator, all have a significant impact on UGC helpfulness. Furthermore, the results indicate that creator interactivity plays a vital role in building UGC helpfulness by moderating other factors. This study contributes to both UGC and social media literature by proposing a comprehensive model to better understand UGC helpfulness. It also provides several practical insights for content creators to improve their online performances.

Purpose The perception of an inferior learning experience is the main challenge for online learning, which leads to higher dropout rates in online courses. The purpose of this paper focuses on investigating how the multi-dimensional construct of social presence would affect the behavior of online learners. Design/methodology/approach A conceptual model that describes online learner behaviors is proposed by including the four social presence variables, learning satisfaction and continuance intention, which is examined via the data collected by a survey of 237 online learners from a typical online learning platform in China. The relationships between variables were tested via structural equation modeling. Findings The results revealed that the intimate and immersive social factors have positive impacts on learning satisfaction, which in turn results in continuous intention in online learning. Thus, online learning platform providers should seriously consider building an intimate and immersive online environment for learners. Furthermore, this research provides a more comprehensive understanding of online learning from a social presence perspective for researchers and practitioners. Originality/value The study contributes to a better understanding of the social presence which is conceptualized as a four-dimensional construct, and shows how social factors influence learning satisfaction and continuous intention, providing a deeper understanding of the core relationship between social aspects and learning performance in online learning.

The popularity of online paid knowledge platforms offers opportunities for massive grassroots knowledge suppliers to participate in knowledge sharing services and get financial rewards, but little is known about the determinants influencing users’ payment decisions in the particular knowledge transaction such as paid Q A. This study examines the factors that influence the performance of grassroots knowledge supplier in paid Q A platforms. We develop a research model integrating reputation, experience, and authority signal to explain the knowledge payment behavior based on signaling theory. Using a panel data analysis of 12,419 records from Zhihu, the largest online Q A platform in China, our empirical study reveals that user payment behavior is significantly influenced by reputation signal and experience signal of a knowledge supplier. Interestingly, different from previous conclusions on professional knowledge payment platforms, authority signal of grassroots knowledge supplier has no significant impact on the payment behavior of online Q A platform users.

Bullet screen as a type of real-time reviews published by viewers is an important unique feature in live streaming commerce. However, it is unclear whether and how bullet screen affects consumers' purchase intention. Drawing upon elaboration likelihood model, this study developed a conceptual model integrating two variables for central cues and three variables for peripheral cues to explain consumers' purchase intention. Using a big dataset of 668,591 records from the Taobao Live, the largest live streaming commerce platform in China, our empirical study finds that bullet screen has a vital role in influencing consumers' purchase intention. Interestingly, bullet screen sentiment has a curvilinear relationship with purchase intention, and source credibility has a negative effect on purchase intention. In addition, product type moderates the impact of bullet screen on purchase intention, and the results indicate that peripheral cues have a stronger influence on purchase intention of experience products than search products. Our study contributes to customer review literature by exploring the influence of real-time reviews on consumer behaviors in live streaming commerce. It also offers a useful practical framework for platform providers and sellers.

It is becoming an important innovation strategy for firms to gather the user-idea extensively through open innovation communities (OICs). However, screening out valuable ideas from massive user ideas in an OIC is a huge challenge for the firm. It is very important to identify the relevant factors that influence user-idea selection. Drawing upon persuasion theory, we develop a conceptual model integrating idea quality characteristics, idea contributor characteristics, and idea emotion characteristics to explain the likelihood of idea selection, using 23,165 user ideas in the MIUI Community hosted by Xiaomi, a Chinese mobile phone manufacturer ranked among the Fortune Global 500. The empirical results show that these characteristics variables have significant impacts on user-idea selection. Specifically, the length of the idea and title has an inverted U-shaped relationship with idea selection. The emotions contained in user ideas have a significant positive impact on idea selection, and user attention negatively moderates the relationship between emotion and idea selection. This study contributes to the user co-creation literature by offering a persuasion perspective to explain user-idea selection in OICs. It also offers novel insights for building reasonable rules in OICs to guide user behavior for managers.

为了实现京津冀协调发展战略,北京市近年实施了"疏解整治促提升"行动.然而,由于历史原因,违法用地和违法建设(简称"两违")长期存在,"两违"的发现、定位、核验以及监测预警难度较大.在国家自然科学基金项目、北京市自然科学基金重点项目以及北京市多项重大专项工程的支持下,北京市测绘设计研究院联合北京建筑大学、北京英泰思迪空间信息技术公司等有关单位,采取"政产学研用"结合、多学科综合交叉的方式,通过综合运用先进遥感、移动道路测量、人工智能、众源数据挖掘、时空分析等新技术,融合多源数据多种技术手段研究"两违"全流程发现-核查-监测预警的监管关键技术、机制与工艺流程(图1),服务于北京城市总体规划,为北京市"疏解整治促提升"行动计划提供了智能化技术手段,为政府决策提供了精准的信息支持.

开放式创新社区是一种用户参与企业创新的网络平台,为了从海量的社区用户中有效识别出领先用户,基于领先用户理论与社会网络关系理论识别出领先用户的五大特征,并从内容信息和客观行为数据两个方面创新性构建了领先用户识别指标体系,研究提出3种基于聚类算法的领先用户识别模型.通过采集手机制造企业小米公司开放式创新社区MIUI的1911位用户数据进行实验分析,验证了领先用户识别模型的有效性,研究结果对国内制造企业运营开放式创新社区具有重要参考价值.

As a valuable source of information, Word Of Mouth1 has always been valued by consumers and business marketers. The Internet provides a new medium for Word Of Mouth communication. Consumers share their views and comments on products, services, brands and enterprises through online platforms, thus forming Internet Word Of Mouth, which will be of great importance to B2C enterprises. However, disturbing and even false information as well as uncertainties and risks existing in the online communication environment lead to the crisis of online trust. Accordingly, this study constructs a trust mechanism model of Internet Word Of Mouth effect, which shows that the professionalism of communicators, online relationship strength, communication channels, and product involvement are key factors significantly affecting the Word Of Mouth effect. This model can provide theoretical guidance in the word-of-mouth marketing and the operation of B2C e-commerce enterprises.

Resource allocation in process management focuses on how to maximize process performance via proper resource allocation since the quality of resource allocation determines process outcome. In order to improve resource allocation, this paper proposes a resource allocation method, which is based on the improved hybrid particle swarm optimization (PSO) in the multi-process instance environment. Meanwhile, a new resource allocation model is put forward, which can optimize the resource allocation problem reasonably. Furthermore, some improvements are made to streamline the effectiveness of the method, so as to enhance resource scheduling results. In the end, experiments are conducted to demonstrate the effectiveness of the proposed method.

Franchising as a global growth strategy, especially in emerging markets, is gaining its popularity. For example, the U.S. Commercial Service estimated that China, having over 2,600 brands with 200,000 franchised retail stores in over 80 sectors, is now the largest franchise market in the world. The popularity of franchising continues to increase, as we witness an emergence of a new e-business model, Netchising, which is the combination power of the Internet for global demand-and-supply processes and the international franchising arrangement for local responsiveness. The essence of franchising lies in managing the good relationship between the franchisor and the franchisee. In this paper, we showed how e-business and analytics strategy plays an important role in growing and nurturing such a good relationship. Specifically, we discussed: managing the franchisor/franchisee relationship, harnessing the e-business strategy with aligning the e-business strategy with application service providers, an attention-based framework for franchisee training and how big data and business analytics can be used to implement the attention-based framework.

Understanding the formation of supply chain flexibility is important. We draw on the organizational learning perspective to examine how inter-organizational systems (IOS) enabled collaborative knowledge creation can enhance the supply chain flexibility. Empirical results from 141 supply chain enterprises support most of our hypotheses. The results show that, (1) IOS use for exploration has positive effects on supply chain flexibility and collaborative knowledge creation plays a partially mediated role between them; (2) Market uncertainty moderates the relationship between IOS use for exploration for collaborative knowledge creation. And (3) under the greater uncertainty in the market environment, the relationship between company's collaborative knowledge creation and supply chain flexibility becomes stronger. This result suggests when supply chain enterprises face market uncertainty, they need to improve the level of IOS use for exploration to facilitate understanding of the market, which will improve the supply chain flexibility.

网络团购发展迅速,团购网站之间竞争日益激烈.因此,如何让用户持续使用是网络团购急需解决的重要问题.但是,现有相关研究比较匮乏,而期望确认模型和技术接受模型则揭示了影响用户持续使用意向的因素和机制.本文将上述两个模型有机结合并引入网络团购研究中,提出了网络团购持续使用模型.实证分析发现:感知价值、期望确认度、满意度、感知价格和感知有用性是影响用户持续使用的重要因素,其中持续使用意向受到感知价值与满意度的显著影响,感知价值受到感知价格与感知有用性的影响,而期望确认度则对感知价值与满意度有显著影响.最后,本文建议团购网站应该改变经营策略,关注用户的持续使用.通过提高用户的价值感知、满意度、价格优势以及有用性来增加团购用户的持续使用行为,从而保持自身的竞争优势.本文不仅揭示了网络团购用户持续使用的影响因素及其作用机制,也对网络团购网站运营提供了重要参考.

Institutional entrepreneurship has increasingly played a critical role in successfully achieving organizational transformation, especially one that involves building a digitally enabled ecosystem. However, despite fruitful research on institutional entrepreneurship, it is still not clearly understood how one might successfully achieve organizational transformation. Thus, our study aims to disambiguate this black box by examining the case study of Red Collar Group (RCG), a market leader in making custom made suits. The findings of this case highlight the significant role played by institutional entrepreneurship in achieving organizational transformation. It highlights that institutional entrepreneurship is evident in different modes of action in the transformational process of building the digital ecosystem.

Purpose – The purpose of this paper is to explore how to use social media in e-government to strengthen interactivity between government and the general public. Design/methodology/approach – Categorizing the determinants to interactivity covering depth and breadth into two aspects that are the structural features and the content features, this study employs general linear model and ANOVA method to analyse 14,910 posts belonged to the top list of the 96 most popular government accounts of Sina, one of the largest social media platforms in China. Findings – The main findings of the research are that both variables of the ratio of multimedia elements, and the ratio of external links have positive effects on the breadth of interactivity, while the ratio of multimedia features, and the ratio of originality have significant effects on the depth of interactivity. Originality/value – The contributions are as follows. First, the authors analyse the properties and the topics of government posts to draw a rich picture of how local governments use the micro-blog as a communications channel to interact with the public. Second, the authors conceptualize the government online interactivity in terms of the breadth and depth. Third, the authors identify factors that will enhance the interactivity from two aspects: structural features and content features. Lastly, the authors offer suggestions to local governments on how to strengthen the e-government interactivity in social media.

Trust has been seen as the foundation of e-commerce. While the interpersonal trust has gain a lot attention in literature, institution-based trust has been studied only infrequently. However, with the significance of the marketplace-based e-commerce, more attention should be paid to institution-based trust, particularly trust at the marketplace level. This study focuses on a specific type institution-based trust associated with marketplaces, termed as trust in marketplace. Based upon the institutional theory and the social presence theory, two categories of marketplace-driven factors, the institutional and social factors, are then proposed as antecedents of trust in marketplace in the new context of social commerce marketplaces. Two formative high-order constructs, perceived effectiveness of institutional structures and perceived social presence, are developed to account for the effects of these two sources on trust in marketplace, which in turn leads to transaction intention in social commerce marketplaces. The research model is examined via the free simulation experimental method where seven real social commerce marketplaces are duplicated. The findings suggest the positive impacts of both constructs in shaping institution-based trust that leads to social commerce marketplace transaction intention. This study then offers insightful understandings to the institutional trust building mechanism in the recent phenomenon of social commerce, as well as introduces the important but neglected social perspective to e-commerce research. (C) 2016 Elsevier B.V. All rights reserved.