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
Statistics
Size  n =  497,959

Left size  n_{1} =  480,189

Right size  n_{2} =  17,770

Volume  m =  100,480,507

Wedge count  s =  2,856,821,221,128

Cross count  x =  2.934 64 × 10^{21}

Maximum degree  d_{max} =  232,944

Maximum left degree  d_{1max} =  17,653

Maximum right degree  d_{2max} =  232,944

Average degree  d =  403.569

Average left degree  d_{1} =  209.252

Average right degree  d_{2} =  5,654.50

Fill  p =  0.011 775 6

Size of LCC  N =  497,959

Diameter  δ =  5

50Percentile effective diameter  δ_{0.5} =  1.616 16

90Percentile effective diameter  δ_{0.9} =  3.103 31

Median distance  δ_{M} =  2

Mean distance  δ_{m} =  2.299 71

Gini coefficient  G =  0.792 409

Balanced inequality ratio  P =  0.191 115

Left balanced inequality ratio  P_{1} =  0.266 697

Right balanced inequality ratio  P_{2} =  0.148 073

Relative edge distribution entropy  H_{er} =  0.836 646

Power law exponent  γ =  1.215 01

Degree assortativity  ρ =  −0.216 685

Degree assortativity pvalue  p_{ρ} =  0.000 00

Spectral norm  α =  1,545.05

Negativity  ζ =  0.439 781

Plots
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.
