Multi-attribute decision tree evaluation in imprecise and uncertain domains
2004 (English)In: Proc. Seventeenth Int. Fla. Artif. Intell. Res. Soc. Conf. FLAIRS, 2004, 850-855 p.Conference paper (Refereed)
We present a decision tree evaluation method integrated with a common framework for analyzing multi-attribute decisions under risk, where information is numerically imprecise. The approach extends the use of additive and multiplicative utility functions for supporting evaluation of imprecise statements, relaxing requirements for precise estimates of decision parameters. Information is modeled in convex sets of utility and probability measures restricted by closed intervals. Evaluation is done relative to a set of rules, generalizing the concept of admissibility, computationally handled through optimization of aggregated utility functions. Pros and cons of two approaches, and tradeoffs in selecting a utility function, are discussed.
Place, publisher, year, edition, pages
2004. 850-855 p.
, Proceedings of the Seventeenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2004, 2
Information analysis, Optimization, Parameter estimation, Probability, Problem solving, Uncertain systems, Utility programs, Decision parameters, Decision tree evaluation, Uncertain domains, Decision theory
IdentifiersURN: urn:nbn:se:kth:diva-157560ScopusID: 2-s2.0-10044228557ISBN: 1577352017OAI: oai:DiVA.org:kth-157560DiVA: diva2:771320
Proceedings of the Seventeenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2004, 17-19 May 2004, Miami Beach, FL, USA
QC 201412122014-12-122014-12-112014-12-12Bibliographically approved