Article ID: | iaor2001403 |
Country: | Netherlands |
Volume: | 25 |
Issue: | 4 |
Start Page Number: | 289 |
End Page Number: | 308 |
Publication Date: | May 1999 |
Journal: | Decision Support Systems |
Authors: | Reverberi Pierfrancesco, Talamo Maurizio |
A probabilistic reasoning model is defined where the decision maker (d.m.) is engaged in a sequential information-gathering process facing the trade-off between the reliability of the achieved solution and the associated observation cost. The d.m. is directly involved in the proposed flexible control strategy, which is based on information-theoretic principles. The devised strategy works on a Bayesian belief network that allows the efficient representation and manipulation of the knowledge base relevant to the problem domain. It is shown that this strategy guarantees a constant factor approximate solution with respect to the optimum of the decision problem. Some application examples are also discussed.