Personalized progressive filtering of skyline queries in high dimensional spaces

Skyline queries were introduced to formulate multi-criteria searches. Such a query tries to select in a relation the tuples that optimize all the criteria, called dominant tuples. There rarely exists a single dominant tuple, but usually a set of incomparable ones, the skyline set. Unfortunately, the deterioration of the query (the size of its answer) increases proportionally with the number of criteria. To address this limitation, we propose a flexible approach to categorize and refine the skyline set by applying successive relaxations of the dominance conditions with respect to user's preferences. Our approach, called θ-skyline, is based on decision theory which deals with decision-making in the presence of conflicting choices. We also define global ranking method over the skyline set.