Bayesian Belief Networks in IT Investment Decision Making

This section aims at describing the concept of Bayesian Belief Networks (BBN), building principles and application of BBN and influence diagrams, as well as the reasons why BBN are considered an adequate tool for IS availability modeling.

Application of BBN in Information Systems and Operational Risk Management

In this chapter, the model used to measure and maximize IS availability is described. The method of selecting independent variables will be presented, with a detailed definition of each variable in the model. This section presents a model based on Bayesian network, utility theory and influence diagrams. Finally, a method for probability elicitation through an interview with domains experts will be described, as recommended data collection model, for cases where it is not possible to set parameter' values based on learning from data.

Information System Availability

In order to provide better understanding of the availability concept, it is necessary to define and review the terms that shape a framework for information systems availability. This section introduces the concept of availability and the three terms that are most associated with the concept of availability, namely: dependability, reliability and maintainability. A short introduction to availability modeling is also presented in this section by explaining three most widely used methods: Reliability Block Diagrams, Fault Trees Diagrams, and Markov Chains.