Research map / Probabilistic and scientific modeling / Treatment effects
Large-Scale Notification Dispatch with Bundle Treatments and Multi-Outcome Uplift Optimization
Jiajing Xu, Yanyun Li, Yongbao Song, Minqin Zhu, Huxiao Ji, Linchuan Li, Cunyi Zhang, Xuanping Li, Kaiqiao Zhan, Yanan Niu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add ROI prediction network (ablation) | BUOPLR · Synthetic | AUUC: 0.0281 -> 0.0888 | Improved |
| add ROI prediction network (ablation) | BUOPLR · Synthetic | AUCC: 0.4853 -> 0.6479 | Improved |
| add multi-task training (ablation) | BUOPLR · Synthetic | AUUC: 0.0491 -> 0.0888 | Improved |
| add multi-task training (ablation) | BUOPLR · Synthetic | AUCC: 0.4984 -> 0.6479 | Improved |
| add monotonicity module across styles (ablation) | BUOPLR · Synthetic | AUUC: 0.0535 -> 0.0888 | Improved |
| add monotonicity module across styles (ablation) | BUOPLR · Synthetic | AUCC: 0.5517 -> 0.6479 | Improved |
| BUOPLR instead of best baseline uplift model | BUOPLR · CRITEO | AUUC: 0.0054 -> 0.0057 | Improved |
| BUOPLR instead of best baseline uplift model | BUOPLR · Notification | AUUC: 0.0057 -> 0.0089 | Improved |
| BUOPLR instead of DFCL for dispatch | BUOPLR · CRITEO | AUCC: 0.7859 -> 0.8030 | Improved |
| replace TimeWheel with BUOPLR in production | TimeWheel · Online A/B | DAU: +0.504% | Improved |
| replace TimeWheel with BUOPLR in production | TimeWheel · Online A/B | CTR: +3.936% | Improved |
Closest papers by meaning
- Invariant Deep Uplift Modeling for Incentive Assignment in Online Marketing via Probability of Necessity and Sufficiency (ICML 2025 · similarity 0.81)
- Percentile Risk-Constrained Budget Pacing for Guaranteed Display Advertising in Online Optimization (AAAI 2024 · similarity 0.79)
- Rethinking Causal Ranking: A Balanced Perspective on Uplift Model Evaluation (ICML 2025 · similarity 0.78)
- Online and Streaming Algorithms for Constrained k-Submodular Maximization (AAAI 2025 · similarity 0.78)
- Watch and Learn: Learning to Use Computers from Online Videos (CVPR 2026 · similarity 0.77)
- Online Resource Allocation With General Constraints (NeurIPS 2026 · similarity 0.77)
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.
