Click Through Rate Prediction On Dianping

AUC

Log Loss

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	AUC	Log Loss	Paper Title
Wide & Deep	0.8361	0.3364	Wide & Deep Learning for Recommender Systems
DeepFM	0.8481	0.3333	DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
PNN	0.8445	0.3424	Product-based Neural Networks for User Response Prediction
DNN	0.8318	-	xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
xDeepFM	0.8639	0.3156	xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems

0 of 5 row(s) selected.