Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Netflix

Benchmarks

Task NameDataset NameSOTA ResultTrend
RecommendationNetflix (test)
NDCG@10039.5
30
Multi-modal recommendationNetflix
Recall@205.13
16
Sequential RecommendationNetflix
AUC77.1
14
Collaborative FilteringNetflix strong generalization
AOA Recall@2036.66
14
Matrix CompletionNetflix
RMSE0.803
14
RecommendationNetflix 15/12/2005
Recall@207.24
12
Sequential RecommendationNetflix
HR @ 59.22
10
RecommendationNetflix coherent users
Recall@2056
10
RecommendationNetflix 80/20 (test)
Recall@1021.56
10
Density EstimationNetflix Randomly-perturbed (test)
Log-likelihood-58.27
9
Density EstimationNetflix Adversarially-perturbed Ta (test)
Log-Likelihood-60.61
9
Collaborative FilteringNetflix large (test)
Recall@2036.2
9
RankingNetflix
Recall@2036.2
8
RankingNetflix (test)
Recall@2036.2
8
Density EstimationNetflix Original T (test)
Log-Likelihood-57.59
7
RecommendationNetflix w/o history
Performance Metric2.13
7
RecommendationNetflix strong generalization
R@2036.58
7
Collaborative FilteringNetflix (test)
Test RMSE0.803
7
Collaborative RankingNetflix Prize (test)
Hit Rate@100.5371
6
Matrix FactorizationNetflix (test)
Training Time (s)3.3
4
Query Processing PerformanceNetflix
Throughput (ops/s)173,459
4
Movie RecommendationNetflix w/ history
Expected User Rating4.141
4
RecommendationNetflix high reward trajectories
NDCG@10106.2
4
Spatiotemporal Vector RetrievalNetflix
Avg Insert Latency (ms)0.0343
4
Spatiotemporal Vector RetrievalNetflix
Recall@175.2
4
Showing 25 of 32 rows