Modelling cause and effect relationships has been a major challenge for statisticians in a wide range of application areas. Bayesian Networks (BN) combine graphical analysis with Bayesian analysis to represent causality maps linking measured and target variables. Such maps can be used for diagnostics and predictive analytics. The paper presents an introduction to Bayesian Networks and various applications such as the impact of management style on statistical efficiency (Kenett1), studies of web site usability (Kenett2), operational risks (Kenett3), biotechnology (Peterson4), customer satisfaction surveys (Kenett5), healthcare systems (Kenett6) and the testing of web services (Bai7). Following the presentation of these case studies, a general section discusses various properties of Bayesian Networks. Some references to software programs used to construct BNs are also provided. A concluding section lists some possible directions for future research.