DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems
Open paper
Benchmark
Model
Rank
Results
click-through-rate-prediction-on-criteo
DCN V2
#12
AUC: 0.8115
Log Loss: 0.4406
click-through-rate-prediction-on-kkbox
DCNv2
#6
AUC: 0.8531
Rank counts only results with a code link.