Netflix

This is the Netflix Prize dataset. The network is bipartite. Nodes are users of the movie website Netflix, and movies. Edges connect a user with a movie, and represent ratings.

Metadata

CodeNX
Internal namenetflix
NameNetflix
Data sourcehttp://www.netflixprize.com/community/viewtopic.php?pid=9857
AvailabilityDataset is not available for download
Consistency checkDataset passed all tests
Category
Rating network
Node meaningUser, movie
Edge meaningRating
Network formatBipartite, undirected
Edge typeRatings, no multiple edges
Temporal data Edges are annotated with timestamps
Snapshot Is a snapshot and likely to not contain all data

Statistics

Size n =497,959
Left size n1 =480,189
Right size n2 =17,770
Volume m =100,480,507
Wedge count s =2,856,821,221,128
Cross count x =2.934 64 × 1021
Maximum degree dmax =232,944
Maximum left degree d1max =17,653
Maximum right degree d2max =232,944
Average degree d =403.569
Average left degree d1 =209.252
Average right degree d2 =5,654.50
Fill p =0.011 775 6
Size of LCC N =497,959
Diameter δ =5
50-Percentile effective diameter δ0.5 =1.616 16
90-Percentile effective diameter δ0.9 =3.103 31
Median distance δM =2
Mean distance δm =2.299 71
Gini coefficient G =0.792 409
Balanced inequality ratio P =0.191 115
Left balanced inequality ratio P1 =0.266 697
Right balanced inequality ratio P2 =0.148 073
Relative edge distribution entropy Her =0.836 646
Power law exponent γ =1.215 01
Degree assortativity ρ =−0.216 685
Degree assortativity p-value pρ =0.000 00
Spectral norm α =1,545.05
Negativity ζ =0.439 781

Plots

Degree distribution

Cumulative degree distribution

Lorenz curve

Spectral distribution of the adjacency matrix

Spectral distribution of the normalized adjacency matrix

Spectral distribution of the Laplacian

Spectral graph drawing based on the adjacency matrix

Spectral graph drawing based on the normalized adjacency matrix

Degree assortativity

Hop distribution

Item rating evolution

Edge weight/multiplicity distribution

Temporal distribution

Diameter/density evolution

Signed temporal distribution

Downloads

References

[1] Jérôme Kunegis. KONECT – The Koblenz Network Collection. In Proc. Int. Conf. on World Wide Web Companion, pages 1343–1350, 2013. [ http ]
[2] James Bennett and Stan Lanning. The Netflix prize. In Proc. KDD Cup, pages 3–6, 2007.