A Prescriptive Approach to Eliciting Decision Information

The importance of making good decisions is well-known in the business world and the perception of decision making as rational choice is the most common view. The amount of information involved in many decision making situations has increased dramatically in recent years and support of some kind is often needed. Consequently, fields like Business Intelligence (BI) and Decision Support Systems (DSS) have advanced. Decision analysis applications belong to the latter category and aim to support decision making activities in businesses and organizations, and provide more clearly structured decision material to use as a basis for decisions. In spite of a belief in their potential, their employment is still limited in practice. This can partly be attributed to the fact that existing tools are incomplete to support decision processes sufficiently in real settings. Moreover, in traditional decision process models, the elicitation of input data to the decision model is one of the key components during modelling. However, in spite of the fact that it involves quite a few problematic elements and its importance to the quality of the process as a whole, the specification and execution of the elicitation process is often left to the discretion of the user. This thesis focuses on the elicitation of information in decision analysis applications and the need for more prescriptive methods (realistic and practically useful) than what is offered today. A process model emphasizing the importance of structured elicitation of adequate input data throughout decision processes is also suggested. In order to further define the problematic aspects of elicitation, three empirical studies were conducted, where problems from existing literature were further studied. The problems with eliciting precise decision data suggests that using imprecise values within elicitation is a more realistic and useful approach to strive for, and perhaps even more important within preference elicitation. Based on theory and the findings of the studies presented in papers I-III, an elicitation method for imprecise statements and noisy input was formalized and the method was further refined into the Cardinal Rank Ordering of Criteria (CROC) weight elicitation method, presented in paper VII. The CROC method is both compatible with an adapted prescriptive decision making model, focused on a more structured elicitation component as well as algorithms for dealing with such data. It was employed and validated in two real-life cases (described in papers V and VI), which is not so common within decision analysis research, i.e. there are relatively few examples of reallife cases employing such techniques.