Search results

Allocation of complex crowdsourcing tasks, which typically include heterogeneous attributes such as value, difficulty, skill required, effort required and deadline, is still a challenging open problem. In recent years, agent-based crowdsourcing approaches focusing on recommendations or incentives have emerged to dynamically match workers with diverse characteristics to tasks to achieve high collective productivity. However, existing approaches are mostly designed based on expert knowledge grounded in well-established theoretical frameworks. They often fail to leverage on user-generated data to capture the complex interaction of crowdsourcing participants’ behaviours. This paper aims to address this challenge.

The paper proposes a policy network plus reputation network (PNRN) approach which combines supervised learning and reinforcement learning to imitate human task allocation strategies which beat artificial intelligence strategies in this large-scale empirical study. The proposed approach incorporates a policy network for the selection of task allocation strategies and a reputation network for calculating the trends of worker reputation fluctuations. Then, by iteratively applying the policy network and reputation network, a multi-round allocation strategy is proposed.

PNRN has been trained and evaluated using a large-scale real human task allocation strategy data set derived from the Agile Manager game with close to 500,000 decision records from 1,144 players in over 9,000 game sessions. Extensive experiments demonstrate the validity and efficiency of computational complex crowdsourcing task allocation strategy learned from human participants.

The paper can give a better task allocation strategy in the crowdsourcing systems.

The purpose of this study is to investigate how the levels of perceived information influence consumers’ purchase evaluations and intentions when making hotel reservations on an opaque-selling travel website. Because of the uniqueness of the opaque-selling model, consumers must book a hotel room without knowing the hotel’s identity. Thus, consumers’ decision-making process is intricate and substantially influenced by the limited information provided by the websites.

This study used an experimental design approach that used promotional and preventative messages to manipulate the information levels. In total, 402 completed questionnaires were collected and analyzed by using quantitative research method.

The results indicated that perceived risks and perceived benefits lead toward different paths in regard to purchase intentions and information inquiries. To make a final booking decision, consumers have to go through a “debating” process, which involves assessing the overall value of the hotel deal claimed on the website.

To reduce consumers’ perceived risks and increase the likelihood of purchasing, opaque-selling websites should cautiously choose what information is displayed on their websites and also improve communications and interactions with the consumers.

This study contributes to the limited literature on information levels and its role in consumer’s evaluative process in the context of opaque-selling travel websites. In addition, this study has presented insights into opaque-buying behavior so that hotel manager may develop more appropriate pricing strategies for their target customer group.

The safety and reliability of high-speed trains rely on the structural integrity of their components and the dynamic performance of the entire vehicle system. This paper aims to define and substantiate the assessment of the structural integrity and dynamical integrity of high-speed trains in both theory and practice. The key principles and approaches will be proposed, and their applications to high-speed trains in China will be presented.

First, the structural integrity and dynamical integrity of high-speed trains are defined, and their relationship is introduced. Then, the principles for assessing the structural integrity of structural and dynamical components are presented and practical examples of gearboxes and dampers are provided. Finally, the principles and approaches for assessing the dynamical integrity of high-speed trains are presented and a novel operational assessment method is further presented.

Vehicle system dynamics is the core of the proposed framework that provides the loads and vibrations on train components and the dynamic performance of the entire vehicle system. For assessing the structural integrity of structural components, an open-loop analysis considering both normal and abnormal vehicle conditions is needed. For assessing the structural integrity of dynamical components, a closed-loop analysis involving the influence of wear and degradation on vehicle system dynamics is needed. The analysis of vehicle system dynamics should follow the principles of complete objects, conditions and indices. Numerical, experimental and operational approaches should be combined to achieve effective assessments.

The practical applications demonstrate that assessing the structural integrity and dynamical integrity of high-speed trains can support better control of critical defects, better lifespan management of train components and better maintenance decision-making for high-speed trains.

Driven by the rapid expansion of online retail and the surge in livestream commerce, the impact of different livestream mode on brand and platform performance has become a critical issue. This paper analyzes the impact of artificial intelligence (AI) and key opinion leader (KOL) livestream on the profitability of brands and the platform, incorporating the effects of horizontal interactions to identify the optimal livestream mode.

This paper develops a model of a platform supply chain involving two brands and a platform, where each brand independently decides whether to utilize KOL or AI livestream. Applying Stackelberg game approach, the study derives equilibria for various livestream scenarios, identifying the optimal livestream mode for both parties. Additionally, the model is extended to incorporate asymmetric market potential and network externality to evaluate their impact on a brand’s choice of livestream mode.

Several interesting and important results are derived in this paper. Firstly, it is found that AI livestream enables brands to leverage network externality and mitigate the market disadvantage, thereby gaining a competitive advantage. Secondly, while KOL livestream promotes trust, the medium KOL commission rates could cause brands to be trapped in a prisoner’s dilemma, and excessively high commission rates may render them less profitable. Thirdly, the KOL commission rate, network externality intensity, horizontal interactions and market disadvantage are critical determinants influencing a brand’s choice of livestream mode.

This study is the first to investigate the effects of horizontal interactions, asymmetric market potential and asymmetric network externality on livestream mode selection by brands within a platform supply chain. The research provides valuable insights into optimizing livestream strategies to enhance brand profitability.

With the development of social media, live-streaming has become an indispensable marketing activity for firms, especially in China. From the initial cooperation with the influencer, firms begin to create their own live-streaming channel, namely, the brands' self-built live-streaming. The purpose of this study is to explore the process of consumer engagement in the brands' self-built live-streaming.

This research comprises two experimental studies. Study 1 examined the effect of streamer types (CEO vs. celebrity) on consumer engagement. Study 2 investigated the moderating effects of product innovativeness.

Results showed that CEO streamers could enhance consumer engagement by increasing consumers' cognitive trust, and celebrity streamers could enhance consumer engagement by increasing consumers' emotional trust. In addition, consumer engagement was higher for really new products (vs. incremental new products) in CEO streamers' (vs. celebrity streamers') live-streaming.

Compared with previous studies that focused on streamers based on the influencer marketing, this study expands the scope of research on the live-streaming ecosystem by exploring the effect of different streamer types on the brands' self-built live-streaming. By investigating consumer engagement, this study gives implications for the sustainable traffic issue in live-streaming e-commerce.

The anomaly detection task for oil and gas pipelines based on acoustic signals faces issues such as background noise coverage, lack of effective features, and small sample sizes, resulting in low fault identification accuracy and slow efficiency. The purpose of this paper is to study an accurate and efficient method of pipeline anomaly detection.

First, to address the impact of background noise on the accuracy of anomaly signals, the adaptive multi-threshold center frequency variational mode decomposition method(AMTCF-VMD) method is used to eliminate strong noise in pipeline signals. Secondly, to address the strong data dependency and loss of local features in the Swin Transformer network, a Hybrid Pyramid ConvNet network with an Agent Attention mechanism is proposed. This compensates for the limitations of CNN’s receptive field and enhances the Swin Transformer’s global contextual feature representation capabilities. Thirdly, to address the sparsity and imbalance of anomaly samples, the SpecAugment and Scaper methods are integrated to enhance the model’s generalization ability.

In the pipeline anomaly audio and environmental datasets such as ESC-50, the AMTCF-VMD method shows more significant denoising effects compared to wavelet packet decomposition and EMD methods. Additionally, the model achieved 98.7% accuracy on the preprocessed anomaly audio dataset and 99.0% on the ESC-50 dataset.

This paper innovatively proposes and combines the AMTCF-VMD preprocessing method with the Agent-SwinPyramidNet model, addressing noise interference and low accuracy issues in pipeline anomaly detection, and providing strong support for oil and gas pipeline anomaly recognition tasks in high-noise environments.

This case study is designed to enable students to understand the reasons behind the launch of a beauty brand grounded on traditions and culture, understand the strategies adopted by Florasis to establish its presence in the C-beauty space and emerge successful, analyze the positioning of a C-beauty brand in a highly competitive beauty market, identify the issues and challenges faced by a C-beauty brand in its efforts to disrupt the C-beauty space and suggest strategies that Florasis can adopt to emerge as a market leader in the global beauty industry.

Set in 2021, the case study discusses about the emerging C-beauty brand Florasis innovative strategies to promote the brand. Florasis was founded in 2017 with a vision to become a century old national makeup brand of China. Florasis was successful in getting on board a story-telling experience that featured traditional Chinese culture, aesthetics and heritage. It sold cosmetic products with retro packaging, concepts derived from traditional Chinese style, promoting a sense of national pride and nostalgia. The case study highlights the innovative strategies Florasis adopted like influencer marketing through key opinion leaders and key opinion customers, celebrity endorsements, user co-creation programs, social content and network marketing, brand crossovers and collaborations, etc. In April 2021, Florasis became the No. 1 cosmetic company in China with a gross merchandise value of 218m yuan and further the total sales for second quarter of 2021 reached 830m yuan, endorsing its supremacy over other global and local beauty brands in China. However, with success came along a set of challenges. Some analysts pointed that the brand was slow in innovating its product line-up, it focused more on promotions and advertisements and the brand positioning with a single sales channel, the cost performance and quality of the products and excessive marketing campaigns targeting a niche segment. Going forward, what should Florasis do to conquer the global beauty space? Can Florasis aspire to become a digitally empowered global beauty brand? Has it got the momentum? Will its direct-to-consumer model and unprecedented marketing and promotion gimmicks, help it achieve the lead in the global beauty space?

This case study is suitable for students of the graduate and undergraduate programs in management.

Teaching notes are available for educators only.

CSS 8: Marketing.

This research paper aims to investigate the critical factors influencing the live commerce industry and their implications for Key Opinion Leaders (KOLs) and brands.

The study comprehensively reviews previous research, develops relevant hypotheses and utilizes personal information from 66 anchors, along with data from 23,000 product links obtained from the backends of live commerce platforms.

The study emphasizes that KOLs with higher traffic significantly influence Gross Merchandise Volume (GMV). Intriguingly, KOLs with lower traffic levels exhibit a more pronounced effect on Return on Investment (ROI), highlighting their significance in driving profitability. Furthermore, the study explores the correlation between KOL hashtags and GMV/ROI and the intricate relationship between product types and KOL hashtags.

The findings significantly enhance the understanding of live shopping behavior and provide valuable insights for business management strategies. Practitioners can leverage this empirical evidence to make informed decisions, utilizing extensive data samples of KOLs and brands.

This research contributes unique insights into the live-streaming commerce industry using backend data from Live Streaming E-commerce platforms. The findings are more accurate based on market data than previous studies that relied on platform reviews or questionnaires. Additionally, this paper investigates the impact of KOLs on the performance of live e-commerce from three perspectives: GMV, ROI and hot-selling products.

A decade and a half after the debut of pervasive computing, a large number of prototypes, applications, and interaction interfaces have emerged. However, there is a lack of consensus about the best approaches to create such systems or how to evaluate them. To address these issues, this paper aims to develop a performance evaluation framework for pervasive computing systems.

Based on the authors' experience in the Gator Tech Smart House – an assistive environment for the elderly, they established a reference scenario that was used to guide the analysis of the large number of systems they studied. An extensive survey of the literature was conducted, and through a thorough analysis, the authors derived and arrived at a broad taxonomy that could form a basic framework for evaluating existing and future pervasive computing systems.

A taxonomy of pervasive systems is instrumental to their successful evaluation and assessment. The process of creating such taxonomy is cumbersome, and as pervasive systems evolve with new technological advances, such taxonomy is bound to change by way of refinement or extension. This paper found that a taxonomy for something so broad as pervasive systems is very complex. It overcomes the complexity by focusing the classifications on key aspects of pervasive systems, decided purely empirically and based on the authors own experience in a real‐life, large‐scale pervasive system project.

There are currently no methods or frameworks for comparing, classifying, or evaluating pervasive systems. The paper establishes a taxonomy – a first step toward a larger evaluation methodology. It also provides a wealth of information, derived from a survey of a broad collection of pervasive systems.

By investigating trust in the organization as a mediator and traditionality as a moderator, this study aims to examine the effect perceived organizational exploitation poses on frontline hotel employees’ service performance.

A three-wave survey that targets 219 supervisor–subordinate dyads from four Chinese hotels was conducted to test the hypotheses. The authors used SPSS 20.0 and AMOS 21.0 to analyze the data and verify the theoretical model.

This study found that perceived organizational exploitation exerts a destructive impact on frontline hotel employees’ service performance. Trust in the organization is a full mediator of the link connecting perceived organizational exploitation to service performance. Furthermore, traditionality weakens perceived organizational exploitation’s impact on trust in the organization and subsequent service performance.

The authors’ findings remind hotels to cease exploiting their employees to avoid compromising service performance. Hotels should also endeavor to instill trust among employees toward the hotel and allocate more attention to employees with lower levels of traditionality.

First, to the best of the authors’ knowledge, this study is among the first to explore the impact of perceived organizational exploitation on frontline hotel employees’ service performance. Second, this study reveals a novel mechanism underlying the connection between perceived organizational exploitation and service performance. Finally, this study identifies frontline hotel employees’ traditionality as a vital moderator that mitigates the negative relationships among perceived organizational exploitation, trust in the organization and service performance.