Managing incomplete preference relations in decision making: A review and future trends
Managing incomplete preference relations in decision making: A review and future trends
复制标题
DOI：
10.1016/j.ins.2014.12.061
复制
发表时间：
2015-05
期刊：
影响因子：
--
通讯作者：
R. Ureña;F. Chiclana;J. A. Morente-Molinera;E. Herrera-Viedma
中科院分区：
文献类型：
--
作者：
R. Ureña;F. Chiclana;J. A. Morente-Molinera;E. Herrera-Viedma
在决策过程中，所有专家都能够有效地表达他们对所有可用选项的偏好的情况是例外而不是规则。事实上，上述设想要求所有专家对要解决的整个问题有精确或足够的了解，包括有能力区分某些选择比其他选择好到什么程度。在许多决策情况下，这些假设可能被视为不切实际，尤其是那些涉及大量可供选择的替代方案和/或相互冲突且动态的信息来源的情况。在这些情况下广泛采用的一些方法是丢弃或更负面地评价那些提供缺失值的偏好的专家。然而，不完整的信息并不等同于低质量的信息，因此，这些方法可能会导致偏见，甚至是坏的解决方案，因为有用的信息可能没有得到适当的考虑，在决策过程中。因此，替代的方法来管理不完全的偏好关系，估计在决策中的缺失信息是可取的和可能的。本文介绍和分析了在这一领域的方法和过程，对决策中的缺失偏好的估计，并强调了未来的研究领域。
In decision making, situations where all experts are able to efficiently express their preferences over all the available options are the exception rather than the rule. Indeed, the above scenario requires all experts to possess a precise or sufficient level of knowledge of the whole problem to tackle, including the ability to discriminate the degree up to which some options are better than others. These assumptions can be seen unrealistic in many decision making situations, especially those involving a large number of alternatives to choose from and/or conflicting and dynamic sources of information. Some methodologies widely adopted in these situations are to discard or to rate more negatively those experts that provide preferences with missing values. However, incomplete information is not equivalent to low quality information, and consequently these methodologies could lead to biased or even bad solutions since useful information might not being taken properly into account in the decision process. Therefore, alternative approaches to manage incomplete preference relations that estimates the missing information in decision making are desirable and possible. This paper presents and analyses methods and processes developed on this area towards the estimation of missing preferences in decision making, and highlights some areas for future research.