Click Through Rate Prediction On Criteo

Métriques

AUC

Log Loss

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	AUC	Log Loss	Paper Title	Repository
IPNN	0.7972	0.45323	Product-based Neural Networks for User Response Prediction	-
OptFS	0.8116	0.4401	Optimizing Feature Set for Click-Through Rate Prediction	-
DCN V2	0.8115	0.4406	DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems	-
FiBiNet++	0.8110	-	FiBiNet++: Reducing Model Size by Low Rank Feature Interaction Layer for CTR Prediction	-
GDCN	0.8161	0.4360	Towards Deeper, Lighter and Interpretable Cross Network for CTR Prediction	-
xDeepFM	0.8052	0.4418	xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems	-
TFNet	0.7991	-	TFNet: Multi-Semantic Feature Interaction for CTR Prediction	-
CETN	0.8148	0.4373	CETN: Contrast-enhanced Through Network for CTR Prediction	-
FNN	0.7963	0.45738	Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction	-
FiBiNET	0.8103	0.4423	-	-
MemoNet	0.8152	-	MemoNet: Memorizing All Cross Features' Representations Efficiently via Multi-Hash Codebook Network for CTR Prediction	-
AutoDeepFM(3rd)	0.8010	0.5405	AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction	-
Wide&Deep	0.7981	0.46772	Wide & Deep Learning for Recommender Systems	-
Fi-GNN	0.8062	0.4453	Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction	-
DeepFM	0.8007	0.45083	DeepFM: A Factorization-Machine based Neural Network for CTR Prediction	-
DeepLight	0.8123	0.4395	DeepLight: Deep Lightweight Feature Interactions for Accelerating CTR Predictions in Ad Serving	-
OptInter	0.8101	0.4417	Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction	-
XCrossNet	0.8067	-	XCrossNet: Feature Structure-Oriented Learning for Click-Through Rate Prediction	-
TF4CTR	0.8150	-	TF4CTR: Twin Focus Framework for CTR Prediction via Adaptive Sample Differentiation	-
NormDNN	0.8107	-	Correct Normalization Matters: Understanding the Effect of Normalization On Deep Neural Network Models For Click-Through Rate Prediction	-

0 of 38 row(s) selected.