Click Through Rate Prediction On Avazu

Métriques

AUC

LogLoss

Résultats

Résultats de performance de divers modèles sur ce benchmark

			Paper Title
OptInter	0.8062	0.3637	Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction
OptInter-M	0.8060	0.3638	Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction
CELS	0.8001	0.3678	Cognitive Evolutionary Search to Select Feature Interactions for Click-Through Rate Prediction
DCNv3	0.7970	0.3695	FCN: Fusing Exponential and Linear Cross Network for Click-Through Rate Prediction
CETN	0.7962	-	CETN: Contrast-enhanced Through Network for CTR Prediction
OptFS	0.795	0.3709	Optimizing Feature Set for Click-Through Rate Prediction
OptEmbed	0.7902	0.374	OptEmbed: Learning Optimal Embedding Table for Click-through Rate Prediction
Sparse Deep FwFM	0.7897	0.3748	DeepLight: Deep Lightweight Feature Interactions for Accelerating CTR Predictions in Ad Serving
FGCNN+IPNN	0.7883	0.3746	Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction
Fi-GNN	0.7762	0.3825	Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction
AutoInt	0.7752	0.3823	AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks
FinalMLP + MMBAttn	0.7666	-	MMBAttn: Max-Mean and Bit-wise Attention for CTR Prediction
DNN + MMBAttn	0.765	-	MMBAttn: Max-Mean and Bit-wise Attention for CTR Prediction
AFN+	0.7555	-	Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions
FLEN	0.75	-	FLEN: Leveraging Field for Scalable CTR Prediction

0 of 15 row(s) selected.

Click Through Rate Prediction On Avazu | SOTA | HyperAI