Premium
Multiobjective Decision‐Tree Analysis 1
Author(s) -
Haimes Yacov Y.,
Li Duan,
Tulsiani Vijay
Publication year - 1990
Publication title -
risk analysis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.972
H-Index - 130
eISSN - 1539-6924
pISSN - 0272-4332
DOI - 10.1111/j.1539-6924.1990.tb01026.x
Subject(s) - decision tree , computer science , decision analysis , decision problem , influence diagram , node (physics) , decision rule , expected utility hypothesis , set (abstract data type) , expected value , extreme value theory , flood myth , mathematical optimization , operations research , data mining , mathematics , mathematical economics , artificial intelligence , algorithm , statistics , engineering , structural engineering , programming language , philosophy , theology
Single‐objective‐based decision‐tree analysis has been extensively and successfully used in numerous decision‐making problems since its formal introduction by Howard Raiffa more than two decades ago. This paper extends the traditional methodology to incorporate multiple noncommensurate objective functions and use of the conditional expected value of the risk of extreme and catastrophic events. The proposed methodology considers the cases where (a) a finite number of actions are available at each decision node and (b) discrete or continuous states of nature can be presented at each chance node. The proposed extension of decision‐tree analysis is introduced through an example problem that leads the reader step‐by‐step into the methodological procedure. The example problem builds on flood warning systems. Two noncommensurate objectives—the loss of lives and the loss of property (including monetary costs of the flood warning system)–are incorporated into the decision tree. In addition, two risk measures—the common expected value and the conditional expected value of extreme and catastrophic events—are quantified and are also incorporated into the decision‐making process. Theoretical difficulties associated with the stage‐wise calculation of conditional expected values are identified and certain simplifying assumptions are made for computational tractibility. In particular, it is revealed that decisions concerning experimentation have a very interesting impact on the noninferior solution set of options—a phenomenon that has no equivalence in the single‐objective case.