Premium
Decision Support Method with AHP According to Similar Preference
Author(s) -
YUMOTO MASAKI
Publication year - 2017
Publication title -
electronics and communications in japan
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.131
H-Index - 13
eISSN - 1942-9541
pISSN - 1942-9533
DOI - 10.1002/ecj.11957
Subject(s) - analytic hierarchy process , preference , computer science , set (abstract data type) , value (mathematics) , evaluation methods , operations research , data mining , machine learning , mathematics , statistics , engineering , reliability engineering , programming language
SUMMARY In the decision support method with analytic hierarchy process (AHP), each evaluation criteria are evaluated for target objective, and each alternative is evaluated for each evaluation criteria. This method recommends alternatives to the user according to the total degree of weight, which is calculated from these two kinds of evaluation values. If the target user does not know all alternatives, AHP needs to use the average value of other evaluators’ evaluation in usual decision support method. However, this method does not reflect target user's preference, and the result does not satisfy the user in many cases. This paper proposes a decision support method with AHP according to similar preference. The proposal method searches the set of alternatives evaluation by others, which is nearest to evaluation by target user in the evaluation distance between alternatives. Evaluation distance is calculated using the value of an evaluation level. The shorter distance the set of alternatives is, the more appropriate alternatives user finds in this method. In practical experiment, the proposal method recommended more satisfied alternatives than the usual method, in which the evaluation value of alternatives is the average value among other evaluators.