Algorithmic Recognition of 2-Euclidean Preferences
Résumé
A set of voters’ preferences on a set of candidates is 2-Euclidean if candidates and voters can be mapped to the plane so that the preferences of each voter decrease with the Euclidean distance between her position and the positions of candidates. Based on geometric properties, we propose a recognition algorithm, that returns either “yes” (together with a planar positioning of candidates and voters) if the preferences are 2-Euclidean, or “no” if it is able to find a concise certificate that they are not, or “unknown” if a time limit is reached. Our algorithm outperforms a quadratically constrained programming solver achieving the same task, both in running times and the percentage of instances it is able to recognize. In the numerical tests conducted on the PrefLib library of preferences, 91.5% (resp. 4.5%) of the available sets of complete strict orders are proven not to be (resp. to be) 2-Euclidean, and the status of only 4.5% of them could not be decided. Furthermore, for instances involving 5 (resp. 6, 7) candidates, we were able to find planar representations that are compatible with 87.4% (resp. 58.1%, 60.1%) of voters’ preferences.