ML100K Performance Summary

This is a summary view of model performance on the ML100K data set.

Top-N Recommendation Accuracy

RBP

NDCG

MRR

Rating Prediction Accuracy

Resource Consumption

Time

Memory

Power

Leaderboard Table

This provides quick numeric access to the model results by mean metric. Note, however, that simple means can be misleading!

Top-N Recommendation

		RBP	NDCG	RecipRank
model	variant
als-implicit	random-best	0.143	0.380	0.430
flexmf-bpr	hyperopt-best	0.142	0.372	0.442
als-implicit	hyperopt-best	0.142	0.375	0.428
uknn-implicit	default	0.141	0.369	0.436
als-implicit	optuna-best	0.140	0.369	0.418
uknn-implicit	hyperopt-best	0.138	0.365	0.414
uknn-implicit	optuna-best	0.138	0.365	0.414
uknn-implicit	random-best	0.137	0.362	0.413
flexmf-logistic	optuna-best	0.134	0.362	0.419
flexmf-bpr	optuna-best	0.131	0.355	0.410
flexmf-warp	hyperopt-best	0.130	0.350	0.414
flexmf-logistic	hyperopt-best	0.127	0.346	0.399
implicit-bpr	optuna-best	0.120	0.330	0.397
flexmf-warp	optuna-best	0.120	0.330	0.371
iknn-implicit	optuna-best	0.118	0.307	0.403
iknn-implicit	hyperopt-best	0.118	0.306	0.405
iknn-implicit	random-best	0.118	0.306	0.405
implicit-bpr	random-best	0.116	0.323	0.389
implicit-bpr	hyperopt-best	0.116	0.323	0.388
iknn-implicit	default	0.112	0.295	0.387
flexmf-bpr	random-best	0.112	0.320	0.365
implicit-bpr	default	0.111	0.310	0.368
flexmf-warp	random-best	0.107	0.295	0.344
flexmf-logistic	random-best	0.106	0.305	0.358
als-implicit	default	0.094	0.292	0.259
popular	default	0.063	0.192	0.207
flexmf-explicit	optuna-best	0.038	0.118	0.149
flexmf-explicit	random-best	0.032	0.106	0.132
als-biased	optuna-best	0.030	0.102	0.122
als-biased	hyperopt-best	0.025	0.093	0.103
als-biased	default	0.021	0.083	0.084
bias	hyperopt-best	0.021	0.083	0.076
bias	optuna-best	0.020	0.082	0.075
bias	random-best	0.020	0.082	0.075
flexmf-explicit	default	0.018	0.075	0.071
iknn-explicit	hyperopt-best	0.011	0.060	0.045
iknn-explicit	random-best	0.011	0.060	0.044
iknn-explicit	optuna-best	0.011	0.060	0.044
flexmf-explicit	hyperopt-best	0.010	0.056	0.042
iknn-explicit	default	0.010	0.059	0.039
uknn-explicit	optuna-best	0.004	0.050	0.024
uknn-explicit	hyperopt-best	0.004	0.050	0.024
flexmf-bpr	default	0.003	0.020	0.015
flexmf-warp	default	0.003	0.021	0.016
flexmf-logistic	default	0.003	0.018	0.012
als-biased	random-best	0.002	0.046	0.018
uknn-explicit	default	0.002	0.039	0.016
bias	default	0.001	0.044	0.016
uknn-explicit	random-best	0.001	0.036	0.014

Rating Prediction

		RMSE	MAE
model	variant
iknn-explicit	default	0.877	0.733
iknn-explicit	hyperopt-best	0.878	0.734
iknn-explicit	optuna-best	0.878	0.734
iknn-explicit	random-best	0.878	0.734
als-biased	default	0.885	0.743
als-biased	optuna-best	0.887	0.743
als-biased	hyperopt-best	0.888	0.743
als-biased	random-best	0.888	0.744
flexmf-explicit	optuna-best	0.896	0.756
flexmf-explicit	default	0.896	0.749
flexmf-explicit	hyperopt-best	0.899	0.755
flexmf-explicit	random-best	0.899	0.759
uknn-explicit	random-best	0.905	0.759
uknn-explicit	hyperopt-best	0.906	0.759
uknn-explicit	optuna-best	0.906	0.759
uknn-explicit	default	0.908	0.760
bias	random-best	0.918	0.776
bias	optuna-best	0.918	0.776
bias	hyperopt-best	0.918	0.777
bias	default	0.919	0.774