Research on Escaping the Big-Data Traps in O2O Service Recommendation Strategy

Xue, Xiao; Huangfu, Shuai; Zhang, Lejun; Wang, Shufang

doi:10.1109/tbdata.2019.2915798

Cited by 6 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since DP-GD satis es the di erential privacy model by introducing random noise to the gradient, DPMF satis es the di erential privacy model by adding noise to the objective function; the noise introduced by both methods will carry data loss in gradient descent. e perturbation noise designed in this paper does not disturb the gradient data when performing gradient aggregation, so the accuracy of the comparison should be like that of the matrix decomposition model algorithm that does not do privacy protection and the scheme that uses encryption algorithm privacy protection [27]. It can also be seen from the experimental plots that the three methods have similar prediction error comparison results in two data sets with di erent amounts of data.…”

Section: Multivariate Statistical Analysis Of Enterprise Humanmentioning

confidence: 90%

Random Matrix-Based Multivariate Statistical Analysis of Enterprises in a Distributed Environment Human Resource Management

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

This paper addresses the design of an enterprise human resource management system due to multivariate statistical analysis computation in a random matrix recommendation algorithm in a distributed scenario. This paper defines multivariate statistical analysis human resource practice (DI-RP). It determines the composition of DI-HRP based on the nature of multivariate statistical analysis and enterprise human resource practice. In addition, the role of DI-HRP in influencing employees’ innovative behaviors is explored based on the theoretical basis of resource conservation theory. This paper mainly develops according to the software development process typical to software engineering, organizes the current business logic of the company, understands the relevant content of the company’s human resource management, conducts requirement research on the human resource department, analyzes the feasibility of system implementation from different perspectives, and finally designs a human resource management system based on B/S architecture on the result of requirement analysis. The technology and tools used in the system were decided on the existing technical architecture of the company. The system design was divided into five modules: personal information management module, work management module, attendance management module, reimbursement management module, and entry/exit management module according to the requirements and finishing process, and each functional module of the system was coded and implemented, respectively. The development tool is PyCharm, and some front-end pages are edited and modified by Visual Studio Code. The Permission model of Django is used to add corresponding permissions for various types of users to ensure the security of the system when running.

show abstract

Section: Multivariate Statistical Analysis Of Enterprise Humanmentioning

confidence: 90%

Random Matrix-Based Multivariate Statistical Analysis of Enterprises in a Distributed Environment Human Resource Management

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Chaos means that the dynamic properties of a system no longer belong to the closed orbit but to the open or unpredictable trajectory. A classic example of amplification through chaos is the "butterfly effect" [77] .…”

Section: ) Correlationmentioning

confidence: 99%

Research Roadmap of Service Ecosystems: A Crowd Intelligence Perspective

Xue

Zhou

et al. 2022

Int. J. Crowd Sci.

Self Cite

View full text Add to dashboard Cite

With the mutual interaction and dependence of several intelligent services, a crowd intelligence service network has been formed, and a service ecosystem has gradually emerged. Such a development produces an ever-increasing effect on our lives and the functioning of the whole society. These facts call for research on these phenomena with a new theory or perspective, including what a smart society looks like, how it functions and evolves, and where its boundaries and challenges are. However, the research on service ecosystems is distributed in many disciplines and fields, including computer science, artificial intelligence, complex theory, social network, biological ecosystem, and network economics, and there is still no unified research framework. The researchers always have a restricted view of the research process. Under this context, this paper summarizes the research status and future developments of service ecosystems, including their conceptual origin, evolutionary logic, research topic and scale, challenges, and opportunities. We hope to provide a roadmap for the research in this field and promote sound development.

show abstract

“…In service ecosystem, local optimization of a single smart service does not necessarily lead to global optimization of the overall system [35][36][37] . For example, smart transportation services may alleviate traffic congestion in a certain local area, but due to the big data traps caused by limited resources and user games, it may have limited effect on alleviating global traffic conditions 38,39 .…”

Section: Networked Connectionmentioning

confidence: 99%

“…When there are various problems and contradictions in the real world itself, the cyber world will also present the same problems. In many cases, the positive feedback characteristics of machine intelligence will strengthen and amplify problems, such as information cocoon 34,35 and algorithmic discrimination [18][19][20] . In addition, whether the mapping relationship is complete and accurate will directly affect the performance of smart services, which may induce potential pitfalls, such as the lack of ability to deal with emergencies 88 and the "disastrous forgetting" in cross-domain applications 89,90 .…”

Section: Traceabilitymentioning

confidence: 99%