Please use this identifier to cite or link to this item:

http://hdl.handle.net/10609/65846
Title: Impact evaluation of clustering-based k-anonymity for recommendations
Author: Ros Martín, Miguel
Director: Casas Roma, Jordi
Salas Piñón, Julián
Others: Universitat Oberta de Catalunya
Keywords: k-anonimity
clustering
recommendations
Issue Date: 15-Jan-2017
Publisher: Universitat Oberta de Catalunya
Abstract: SaNGreeA is a greedy and deterministic clustering algorithm for achieving kanonymous clusters on a labeled, undirected graph. It is nowadays a classic and the leading work in clustering based k-anonymity algorithms. It has a quadratic time complexity which makes it really slow for a reasonably big network (1 M nodes). Our project adapts SaNGreeA to make it scalable for a real world big network and specialises it to make sure the generated clusters are useful for a recommender system.
Language: English
URI: http://hdl.handle.net/10609/65846
Appears in Collections:Bachelor thesis, research projects, etc.

Share:
Export:
Files in This Item:
File Description SizeFormat 
rossoftTFM0617memoria.pdfMemòria del TFM897.36 kBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons