Learning a Majority Rule Model from Large Sets of Assignment Examples

Learning the parameters of a Majority Rule Sorting model MR-Sort through linear programming requires to use binary variables. In the context of preference learning where large sets of alternatives and numerous attributes are involved, such an approach is not an option in view of the large computing times implied. Therefore, we propose a new metaheuristic designed to learn the parameters of an MR-Sort model. This algorithm works in two phases that are iterated. The first one consists in solving a linear program determining the weights and the majority threshold, assuming a given set of profiles. The second phase runs a metaheuristic which determines profiles for a fixed set of weights and a majority threshold. The presentation focuses on the metaheuristic and reports the results of numerical tests, providing insights on the algorithm behavior.

[1]  John C. Butler,et al.  Simulation techniques for the sensitivity analysis of multi-criteria decision models , 1997 .

[2]  Vincent Mousseau,et al.  Inferring an ELECTRE TRI Model from Assignment Examples , 1998, J. Glob. Optim..

[3]  Patrice Perny,et al.  Algorithmic Decision Theory: First International Conference, ADT 2009, Venice, Italy, October 20-23, 2009. Proceedings , 2009, ADT.

[4]  Denis Bouyssou,et al.  Further results on concordance relations , 2007 .

[5]  V. Mousseau.  Using Assignment Examples to Infer Category Limits for the ELECTRE TRI Method , 2002 .

[6]  Magdalene Marinaki,et al.  An evolutionary approach to construction of outranking models for multicriteria classification: The case of the ELECTRE TRI method , 2009, Eur. J. Oper. Res..

[7]  Eyke Hüllermeier,et al.  Preference Learning: An Introduction , 2010, Preference Learning.

[8]  M. Pirlot.  General local search methods , 1996 .

[9]  Thierry Marchant,et al.  An axiomatic approach to noncompensatory sorting methods in MCDM, II: More than two categories , 2007, Eur. J. Oper. Res..

[10]  Thierry Marchant,et al.  An axiomatic approach to noncompensatory sorting methods in MCDM I: The case of two categories (juin 2005) , 2005 .

[11]  Bernard Roy,et al.  Aide multicritère à la décision : méthodes et cas , 1993 .

[12]  Constantin Zopounidis,et al.  Multicriteria Decision Aid Classification Methods , 2002 .

[13]  Luis C. Dias,et al.  An aggregation/disaggregation approach to obtain robust conclusions with ELECTRE TRI , 2002, Eur. J. Oper. Res..

[14]  José Rui Figueira,et al.  Using assignment examples to infer weights for ELECTRE TRI method: Some experimental results , 2001, Eur. J. Oper. Res..

[15]  Luis C. Dias,et al.  Inferring Electre's veto-related parameters from outranking examples , 2006, Eur. J. Oper. Res..

[16]  Denis Bouyssou,et al.  A characterization of concordance relations , 2005, Eur. J. Oper. Res..

[17]  Patrick Meyer,et al.  Eliciting Electre Tri category limits for a group of decision makers , 2012, Eur. J. Oper. Res..

[18]  Marc Pirlot,et al.  Learning the Parameters of a Multiple Criteria Sorting Method , 2011, ADT.