AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Multi-Level Deep Cascade Trees for Conversion Rate Prediction in Recommendation System

Hong Wen, Jing Zhang, Quan Lin, Keping Yang, Pipei Huang

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 38 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use level-by-level cascade learning with cross-entropy leaf features instead of a single GBDTCVR prediction · Offline test setAUC: 0.7692 -> 0.7942Improved
Add parallel diverse ldcTree ensemblesldcTree · Offline test setAUC: 0.7942 -> 0.8121Improved
Add staged use of weak- and strong-correlation featuresEldcTree · Offline test setAUC: 0.8121 -> 0.8315Improved
Increase tree depth from 4 to 8 (ablation)ldcTree · Validation setAUC: 0.783 -> 0.794Improved
Increase tree depth from 6 to 8 (ablation)ldcTree · Validation setAUC: 0.789 -> 0.794Improved
Increase tree depth from 8 to 10 (ablation)ldcTree · Validation setAUC: 0.794 -> 0.797Improved
Increase tree depth from 8 to 10 (ablation)ldcTree · Validation setTime Cost(s): 15 -> 26Hurt
Use ldcTree instead of Naive GBDTOnline CVR prediction · Online recommendation system, four daysCVR: 104.3%, 104.1%, 103.8%, 103.9%Improved
Add ensemble structure to ldcTreeOnline CVR prediction · Online recommendation system, four daysCVR: 107.1%, 107.4%, 106.3%, 106.8%Improved
Use F-EldcTree in place of the baseline modelOnline CVR prediction · Online recommendation systemCVR: 12 percentImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy