Behavior Computing: Discovering Complex Behavior Intelligence

Longbing Cao
Professor, Faculty of Engineering and IT
Director, Advanced Analytics Institute
University of Technology Sydney, Australia

Abstract:

Complex behaviors are ubiquitous in commercial, social, economic, industry and governmental business. The in-depth understanding of complex behaviors has been increasingly recognized as a crucial means for disclosing interior driving forces, causes and impact on businesses in handling many challenging issues. This forms the need and emergence of behavior computing (we also call behavior informatics), i.e. understand behaviors from the informatics perspective.

In current entity-relationship based data management, behavior-oriented elements are hidden in split tables and transactions. As a result, it is ineffective or even impossible to deeply scrutinize native behavior intention, life-cycle, dynamics and impact on complex problems and business issues. In this talk, we present an overview of behavior informatics, and showcase our research outcomes in behavior representation, behavior impact analysis, behavior pattern analysis, negative behavior analysis, behavior interaction and evolution, as well as group-based and coupled behaviors. We will also briefly discuss the issue of non-iidness in complex behavior analysis. Several real-world case studies are demonstrated, including analyzing exceptional market microstructure behaviors, mining for high impact social security behavior patterns, detecting abnormal coupled trading behaviors, presenting student progression behaviors, and analyzing online banking behavior interactions. We show that behavior computing creates new opportunities, directions and means for quantitative, formal and systematic modeling, learning and analysis of complex behaviors in both physical and virtual organizations.

Slides in PDF