Abstract | ||
---|---|---|
In this paper we evaluate the performance of different collaborative algorithms in cold-start situations, where the initial lack of ratings may affect the quality of the algorithms. The evaluation has been performed on the pay-per-view datasets collected by two IP-television providers over a period of several months. The analysis shows that item-based algorithms perform better with respect to SVD-based ones in the early stage of the cold-start problem. Moreover, the accuracy of SVD-based algorithms, when using few latent factors, decreases with the time-evolution of the dataset. On the contrary, the same algorithms used with a large-enough number of latent features increase their accuracy with time and may outperform the item-based algorithms. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1145/1639714.1639756 | RecSys |
Keywords | DocType | Citations |
svd-based algorithm,latent feature,item-based algorithm,cold-start problem,initial lack,different collaborative algorithm,ip-television provider,early stage,cold-start situation,iptv system,cold-start recommendation,latent factor,collaborative,cold start | Conference | 36 |
PageRank | References | Authors |
1.56 | 16 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Paolo Cremonesi | 1 | 1306 | 87.23 |
Roberto Turrin | 2 | 859 | 34.94 |