Evirilmiş dizin yapılı ve topaklama temelli imeceli süzgeçleme

Collectively, a population contains vast amounts of knowledge and moderncommunication technologies that increase the ease of communication. However,it is not feasible for a single person to aggregate the knowledge of thousandsor millions of data and extract useful information from it. Collaborative infor-mation systems are attempts to harness the knowledge of a population and topresent it in a simple, fast and fair manner. Collaborative filltering has been suc-cessfully used in domains where the information content is not easily parse-ableand traditional information filltering techniques are difficult to apply. Collabora-tive filltering works over a database of ratings for the items which are rated byusers. The computational complexity of these methods grows linearly with thenumber of customers which can reach to several millions in typical commercialapplications. To address the scalability concern, we have developed an efficientcollaborative filltering technique by applying user clustering and using a specifilcinverted index structure (so called cluster-skipping inverted index structure) thatis tailored for clustered environments. We show that the predictive accuracyof the system is comparable with the collaborative filltering algorithms withoutclustering, whereas the efficiency is far more improved.