IPNN

Reported on 5 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Miscellaneous5 results

Click-Through Rate PredictiononCriteo
Log Loss· 2016-11-01
0.45323
best: 0.4358 (QNN-α)
SOTA
Product-based Neural Networks for User Response Prediction arXiv:1611.00144
Click-Through Rate PredictiononiPinYou
AUC· 2016-11-01
0.7914
best: 0.8174 (OPNN)
Product-based Neural Networks for User Response Prediction arXiv:1611.00144
Click-Through Rate PredictiononCompany*
AUC· 2016-11-01
0.8664
best: 0.8715 (DeepFM)
Product-based Neural Networks for User Response Prediction arXiv:1611.00144
Click-Through Rate PredictiononCompany*
Log Loss· 2016-11-01
0.02637
best: 0.02618 (DeepFM)
Product-based Neural Networks for User Response Prediction arXiv:1611.00144
Click-Through Rate PredictiononCriteo
AUC· 2016-11-01
0.7972
best: 0.8163 (QNN-α)
Product-based Neural Networks for User Response Prediction arXiv:1611.00144