Click Through Rate Prediction On Avazu
Metriken
AUC
LogLoss
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | AUC | LogLoss |
|---|---|---|
| optembed-learning-optimal-embedding-table-for | 0.7902 | 0.374 |
| a-sparse-deep-factorization-machine-for | 0.7897 | 0.3748 |
| dcnv3-towards-next-generation-deep-cross | 0.7970 | 0.3695 |
| fi-gnn-modeling-feature-interactions-via | 0.7762 | 0.3825 |
| feature-generation-by-convolutional-neural | 0.7883 | 0.3746 |
| mmbattn-max-mean-and-bit-wise-attention-for | 0.7666 | - |
| flen-leveraging-field-for-scalable-ctr | 0.75 | - |
| cognitive-evolutionary-search-to-select | 0.8001 | 0.3678 |
| mmbattn-max-mean-and-bit-wise-attention-for | 0.765 | - |
| memorize-factorize-or-be-naive-learning | 0.8062 | 0.3637 |
| autoint-automatic-feature-interaction | 0.7752 | 0.3823 |
| cetn-contrast-enhanced-through-network-for | 0.7962 | - |
| adaptive-factorization-network-learning | 0.7555 | - |
| memorize-factorize-or-be-naive-learning | 0.8060 | 0.3638 |
| optimizing-feature-set-for-click-through-rate | 0.795 | 0.3709 |