Description:
<jats:p> This chapter is about an important tool in the data science workbench, Bayesian networks (BNs). Data science is about generating information from a given data set using applications of statistical methods. The quality of the information derived from data analysis is dependent on various dimensions, including the communication of results, the ability to translate results into actionable tasks and the capability to integrate various data sources [R. S. Kenett and G. Shmueli, On information quality, J. R. Stat. Soc. A 177(1), 3 (2014).] This paper demonstrates, with three examples, how the application of BNs provides a high level of information quality. It expands the treatment of BNs as a statistical tool and provides a wider scope of statistical analysis that matches current trends in data science. For more examples on deriving high information quality with BNs see [R. S. Kenett and G. Shmueli, Information Quality: The Potential of Data and Analytics to Generate Knowledge (John Wiley and Sons, 2016), www.wiley.com/go/information_quality.] The three examples used in the chapter are complementary in scope. The first example is based on expert opinion assessments of risks in the operation of health care monitoring systems in a hospital environment. The second example is from the monitoring of an open source community and is a data rich application that combines expert opinion, social network analysis and continuous operational variables. The third example is totally data driven and is based on an extensive customer satisfaction survey of airline customers. The first section is an introduction to BNs, Sec. 2 provides a theoretical background on BN. Examples are provided in Sec. 3. Section 4 discusses sensitivity analysis of BNs, Sec. 5 lists a range of software applications implementing BNs. Section 6 concludes the chapter. </jats:p>