Click Through Rate Prediction On Ipinyou
評価指標
AUC
LogLoss
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | AUC | LogLoss | Paper Title | Repository |
|---|---|---|---|---|
| OptInter | 0.7825 | 0.005604 | Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction | |
| PNN* | 0.7661 | - | Product-based Neural Networks for User Response Prediction | |
| FNN | 0.7619 | - | Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction | |
| IPNN | 0.7914 | - | Product-based Neural Networks for User Response Prediction | |
| OPNN | 0.8174 | - | Product-based Neural Networks for User Response Prediction | |
| DCNv3 | 0.7856 | 0.005535 | FCN: Fusing Exponential and Linear Cross Network for Click-Through Rate Prediction | |
| OptInter-M | 0.7800 | 0.00564 | Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction |
0 of 7 row(s) selected.