Learning non-monotonic additive value functions for multicriteria decision making

Abstract

Multiattribute additive value functions constitute an important class of models for multicriteria decision making. Such models are often used to rank a set of alternatives or to classify them into pre-defined groups. Preference disaggregation techniques have been used to construct additive value models using linear programming techniques based on the assumption of monotonic preferences. This paper presents a methodology to construct non-monotonic value function models, using an evolutionary optimization approach. The methodology is implemented for the construction of multicriteria models that can be used to classify the alternatives in pre-defined groups, with an application to credit rating.

Topics

Keywords

Multicriteria decision making
Value functions
Evolutionary optimization
Classification

Introduction

In multicriteria decision making (MCDM), a wide range of criteria aggregation forms are used for preference modeling and decision making purposes. These include functional forms originating from the multiatribute value theory (Keeny and Raiffa 1993), relational forms based on the outranking relations theory (Roy 1991), and symbolic forms which have been recently proposed within the context of the dominance- based rough sets approach (Greco et al. 2001).

Research Topics: Energy Markets’ Volatility Project Financing Competition and Financial Strategy

Published Papers