From Incomplete Preferences to Ranking via Optimization

We consider methods for aggregating preferences that are based on the resolution of discrete optimization problems. The preferences are represented by arbitrary binary relations (possibly weighted) or incomplete paired comparison matrices. This incomplete case remains practically unexplored so far. We examine the properties of several known methods and propose one new method. In particular, we test whether these methods obey a new axiom referred to as {\it Self-Consistent Monotonicity}. Some results are established that characterize solutions of the related optimization problems.