.png){kind=icon}
.png){kind=icon}
Return
A preference disaggregation-driven multiple criteria sorting model based on regret theory
.png){kind=icon}
PRE
AI
DOI：10.1016/j.omega.2024.103150.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Regret theory is a classic behavioural decision theory, but existing literature related to the regret theory used different utility functions, reference points, and parameter values, which may lead to biased results. In this regard, this study proposes a preference disaggregation-driven multiple-criteria sorting model based on the regret theory, which can infer the values of risk- and regret-aversion parameters involved in the regret theory and category thresholds according to the preference information in both precise and imprecise forms provided by decision-makers. We analyze the utility functions applied in the regret theory, and find that the power function is more reasonable than the exponential function. We also test the reference points applied in the regret theory, and find that the results obtained using the average alternative as a reference point are similar to those obtained without setting reference points while reducing computational complexity. To infer the values of risk- and regretaversion parameters involved in the regret theory and category thresholds, a preference disaggregation-driven multiple-criteria sorting model is developed according to the preference information in both precise and imprecise forms provided by decision-makers. An illustrative example on supplier resilience classification is provided to demonstrate the applicability of the proposed sorting model.
Keywords:
Decision analysis
Multiple criteria sorting
Regret theory
Preference disaggregation
Robust ordinal regression
Journal
O
IF:
7.2
Papers:
3.7K
Citations:
1.4W