Interactive Elicitation of a Majority Rule Sorting Model with Maximum Margin Optimization

Nefla, Ons; Öztürk, Meltem; Viappiani, Paolo; Brigui-Chtioui, Imène

doi:10.1007/978-3-030-31489-7_10

Cited by 3 publications

(2 citation statements)

References 20 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, Sobrie et al [35] tackled it with a metaheuristic, and Belahcene et al [1] with a Boolean satisfiability (SAT) formulation. Other authors proposed approaches to infer MR-Sort incorporating veto phenomenon [28], and imprecise/missing evaluations [29], and [32] presented an interactive elicitation for the learning of MR-Sort parameters with given profiles values. Recently [23] proposes an enriched preference modelling framework that accounts for a different type of input.…”

Section: Inv-mr-sort: Learning An Mr-sort Model From Assignment Examplesmentioning

confidence: 99%

A MIP-based approach to learn MR-Sort models with single-peaked preferences

et al. 2022

View full text Add to dashboard Cite

The Majority Rule Sorting (MR-Sort) method assigns alternatives evaluated on multiple criteria to one of the predefined ordered categories. The Inverse MR-Sort problem (Inv-MR-Sort) consists in computing MR-Sort parameters that match a dataset. Existing learning algorithms for Inv-MR-Sort consider monotone preference on criteria. We extend this problem to the case where the preference on criteria are not necessarily monotone, but possibly single-peaked (or single-valley). We propose a mixed-integer programming based algorithm that learns from the training data the preference on criteria together with the other MR-Sort parameters. Numerical experiments investigate the performance of the algorithm, and we illustrate its use on a real-world case study.

show abstract

Section: Inv-mr-sort: Learning An Mr-sort Model From Assignment Examplesmentioning

confidence: 99%

A MIP-based approach to learn MR-Sort models with single-peaked preferences

et al. 2022

View full text Add to dashboard Cite

show abstract

“…They proposed a MIP implementation for solving the Inv-MR-Sort problem, while Sobrie et al [34] tackled it with a metaheuristic and Belahcene et al [1] with a Boolean satisfiability (SAT) formulation. Other authors proposed approaches to infer MR-Sort incorporating veto phenomenon [27], and imprecise/missing evaluations [28], and [31] presented an interactive elicitation for the learning of MR-Sort parameters with given profiles values. Recently [22] proposed an enriched preference modelling framework which accounts for different types of input.…”

Section: Given a Single-peaked Criterion I For Which An Approved Set ...mentioning

confidence: 99%

Learning MR-Sort Models from Non-Monotone Data

Minoungou,

Mousseau,

Ouerdane

et al. 2021

Preprint

View full text Add to dashboard Cite

The Majority Rule Sorting (MR-Sort) method assigns alternatives evaluated on multiple criteria to one of the predefined ordered categories. The Inverse MR-Sort problem (Inv-MR-Sort) computes MR-Sort parameters that match a dataset. Existing learning algorithms for Inv-MR-Sort consider monotone preferences on criteria. We extend this problem to the case where the preferences on criteria are not necessarily monotone, but possibly single-peaked (or single-valley). We propose a mixed-integer programming based algorithm that learns the preferences on criteria together with the other MR-Sort parameters from the training data. We investigate the performance of the algorithm using numerical experiments and we illustrate its use on a real-world case study.

show abstract