Agent Based Models Trending at WinterSim 2013


Industry leaders are realizing the benefits of Agent Based Modeling with AnyLogic software. In the dynamic and complex market environments of telecommunications, insurance, epidemiology, and healthcare, consumers make choices based on the characteristics of the consumers themselves and other factors that are best captured by the agent based modeling paradigm. Individual-centric data from Customer Relationship Management systems can be used to parameterize the model agents.

The number of papers published for WinterSim 2013 using Agent Based Models nearly doubled from that of 2012. See how industry leaders are putting CRM, ERP and other big data to work using Agent Based Models.


“The aggregate (top-bottom) modeling nature of DES, however, offers low flexibility for direct modeling of contacts (and transmission events) at the individual level, and restricts application of such models to complex social networks. ABS (Agent Based Modeling) is an alternative approach that models the system at the individual level and offers high flexibility to incorporate various modeling assumptions. ABS models have wide application in the social sciences (Epstein 1999, Macal and North 2010), and the models have been applied to study various infectious diseases such as influenza (Chao et al. 2010), smallpox (Longini et al. 2006), and HIV/AIDS (Alam, Meyer, and Norling 2008). “ W, D. Kelton Department of Operations, Business Analytics and Information Systems at the University of Cincinnati*


“According to North and Macal (2007), ABS (Agent Based Models) will be the predominant simulation approach in the future for various, systems and technology related, reasons such as increasingly systems complexity, close similarity with object-oriented programming and increased computational power.” A. Anagnostou, A. Nouman, S.J.E. Taylor from Department of Information Systems, Computing and Mathematics at Brunel University*


“To validate our proposed approach, we compared our results from the agent based simulation with the existing dual toll pricing optimization approach by using same metric. The results validation showed that the pro-posed simulation based optimization approach enables us to develop a more reliable dual toll pricing policy with various drivers’ preferences and decisions.” S. Kim, S. Mungle and Y. Son from Systems and Industrial Engineering at the University of Arizona*


*Information gathered from published papers in the WinterSim archives (http://informs-sim.org/)