Special Issue – RAIS

Risk Analytics in Industrial Systems

Guest editors

Desheng Dash Wu, University of Toronto, Canada
David L. Olson, University of Nebraska, USA
Tsan-Ming Choi, The Hong Kong Polytechnic University, Hong Kong


As the global economy entered a new era after the financial crisis, business models and assumptions in industrial systems have come under greater scrutiny. For example, in a shrinking market in the post-crisis era, a typical industrial system of supply chain faces many types of risks and performance evaluation of this supply chain needs to consider a great deal of risk factors besides various financial factors. Risk analytics has become especially important in industrial systems during the last decade. Risk analytics technology in industrial systems such as operations management systems can enable users to capture, extract and analyze data and deliver risk intelligence that helps improve decision making strategy, operations and performance. New risk analytics approaches such as enterprise risk management (ERM) have emerged as a systematic and integrated approach to manage risks facing an organization. ERM seeks the most effective way to deal with financial and operations systems risks in the big data era. It has become a vital topic in both academia and practice during the past several decades. Data oriented risk analytics methods have recently received widespread attention from both the business and academic community – it is now emerging as a new discipline in systems engineering. Most data analytics tools have been used for optimizing risk management in a great deal of industrial systems. Risk management tools benefit from various data analytics approaches. For example, traditional time series models have been developed for simulating risk measures such as value at risk. Financial risks such as credit risks are measured by using various business intelligence and data mining models. Early warning systems of company bankruptcy have been built on advanced decision support systems such as neural networks and support vector machines. Systems dynamics and agent-based decision systems have been used in typical industrial systems such as supply chain risk management systems. Undoubtedly, investigation of risk analytics tools in industrial systems is beneficial to both practitioners and academic researchers.
This special issue of IEEE Systems Journal is intended to present recent methodological advances and contemporary applications of risk management and data analytics to enhance decision making in industrial systems. Topics of interest include, but are not limited to:
– Algorithms, approaches, and strategies for risk analytics
– Characterization and metrics of risk analytics in systems
– Risk analytics measurement, profiling, and test-beds
– System dynamics and data analytics in operational risk management
– Interdisciplinary risk analytics technologies and issues
– Systems engineering approach to risk analytics
– Data-oriented engineering risk analysis
– Risk analytics for systems-of-systems
– Social networks for risk-based decision making
– Risk analytics and reliability in industrial systems
– Systems level risk analytics for industrial applications
– Key Risk Indexes (KRI) for Industrial Systems
– Agent-based risk management in industrial systems
– Economic and business impact and issues of risk analytics in industrial systems
– Risk analytics in supply chain systems and logistics
– Enterprise risk management in supply chains
– Risk analysis in portfolio selection and decision support of financial services
– Credit scoring and risk analytics
– Intelligence multi-criteria decision making in finance
– Risk analysis and management in decision making and business analytics under uncertainty
– Risk analysis and management in green engineering and services
– Knowledge management and data mining for natural disasters risk management