A multi-criteria metric algorithm for recommender systems

Information overload and an abundance of choices create situations where selecting one option becomes extremely difficult or even worse, a guessing game. Collaborative ranking systems are widely used to alleviate this problem by creating intelligent rankings of items based on an aggregation of user opinions. Current ranking systems can still be improved in a number of areas, including accuracy, transparency and flexibility. This paper presents a multi-criteria ranking algorithm that can be used on a non-rigid set of criteria. The system implementing the algorithm fares well with respect to the above qualities.