【数学类】SCI期刊《European Journal of Operational Research》专刊截稿信息

全文截稿: 2018-01-31

影响因子: 3.297

期刊难度: ★★★★

网址: www.journals.elsevier.com/european-journal-of-operational-research

Stochastic optimization involves mathematical methods for optimal decision making when important model parameters are random. Its importance is demonstrated by a wide diversity of applications, spanning, e.g., energy, health, transportation and logistics, business analytics, finance, education, agriculture, public sector analytics, supply chain management, and the internet. Further applications arise in laboratory settings to help with drug discovery or materials science, design of computer simulations, field experimentation and implementation, covering strategic, tactical and real-time problems.

The application settings are so broad that multiple disciplines have evolved to respond to the different problem characteristics and research questions. Fields have developed with names such as stochastic programming, dynamic programming (including Markov decision processes, approximate/adaptive dynamic programming, and reinforcement learning), stochastic control, stochastic search, robust optimization, online computation, and stochastic equilibrium. Just as important are fields that evolved around learning unknown functions, including global optimization, ranking and selection, and the multi-armed bandit problem. Of increasing importance is the close relationship between stochastic optimization and machine learning, and the importance of careful modeling of stochastic processes, which is creating bridges to the field of uncertainty quantification.

The aim of this special issue is to collect high quality papers spanning all the different flavors of stochastic optimization, so that different communities can learn from each other. The major acceptance criterion for a submission will be the quality and originality of the contribution. However, the special issue will strive to feature a balanced representation of the different communities and problem domains. Applications are highly welcome, but each paper is expected to contain some novel methodological/mathematical content.

全文截稿: 2018-01-31

影响因子: 3.297

期刊难度: ★★★★

网址: www.journals.elsevier.com/european-journal-of-operational-research

Business Analytics is an emerging phenomenon which reflects the increasing significance of data in terms of its growing volumes, variety and velocity (Department for Business Innovation and Skills 2013). There is much excitement around analytics and data science, as commercial organizations explore how they can use their large volumes of data to create value in their business, and governments and communities seek to create value of a broader nature through exploitation of their data resources (Yui, 2012). Analytic methods are being used in many and varied ways, for example to predict consumer choices, to predict the likelihood of a medical condition, to analyze social networks and social media, to better manage traffic networks.

A number of researchers have argued the growing attention and prominence afforded to analytics presents an important challenge and opportunity for the OR community (Liberatore and Luo, 2010, Ranyard et al. 2015, Mortenson et al. 2015). Many in the community have recognized this growth and sought to align themselves with analytics. For instance, the US OR society INFORMS now offers analytics related conferences, certification and a magazine. However, the volume of analytics-orientated studies in journals associated with operational research is still comparatively low (Mortenson et al. 2015).

The current view of analytics is encapsulated by Davenport and Harris’ (2007) succinct and widely adopted definition: “By analytics we mean the extensive use of data, statistical and quantitative analysis, explanatory and predictive models, and fact-based management to drive decisions and actions.” (p. 7, emphasis in the original). The key aspect of this definition is that analytics ultimately provides insight that is actioned – not just descriptive models. Thus, one of the main concerns in business analytics is related to research into the transformation needed for organizations to become data-driven and evidence-based.

Business analytics can be viewed as the intersection of a variety of disciplines, of which OR, machine learning, and information systems are of particular relevance(Figure 1). As a process it can be characterized by descriptive, predictive, and prescriptive model building using heterogeneous and ‘big’ data sources. These models enable organisations to make quicker, better, and more intelligent decisions to create business value in the broadest sense - potentially the difference between survival and extinction in an increasingly competitive world. Thus, business analytics is about the context in which OR and data science are deployed.

The objective of this special issue is to publish papers that contribute to both the theory and practice of business analytics. While papers describing new techniques have been published in other journals, we would expect to see how the technique could be applied in practice with implications for creating value in organizations. Creating value through analytics may lead to, or require, organizational change for it to effective. The relationship with data science is direct but distinct: business analytics is an organizational activity that draws on and uses the techniques of data science and operational research as appropriate.

Research into analytics should seek to both incorporate the unique aspects of the OR discipline, as well as the innovations, concerns and characteristics of the analytics movement. Specifically, this special issue aims to invite OR scholars and practitioners to look at:

- Ethics and governance issues in business analytics: How should data be obtained? What are the ethical implications of using applications of business analytics to influence behaviour?

- Big data and business analytics: What are the limitations and applications of optimisation and other OR techniques to large datasets? What are the challenges for applications of OR methods within distributed systems? What is the possibility that OR models could in fact be the producers of big data, e.g. large-scale simulation models? What new methods/models in response to big data e.g. sentiment mining, can be adopted by OR?

- Organizational issues in business analytics adoption: What are the issues facing organizations trying to adopt business analytics? What is the role of real-time applications of OR in organizations?

- Data quality and business analytics: what methods can be used for hypothesis testing and model validation in large datasets? How can unstructured data be used effectively in OR models? What is the role of multi-methodology in business analytics? What opportunities do open data present for the OR discipline?

- Business analytics and decision support: How can data visualisation techniques be used across the breadth of OR? What role do problem structuring and “soft” OR techniques play in analytics and big data projects?

- Other topics that have relevance for value creation and organisational implications are also welcome.

下载Call4Papers App，获取更多详细内容！