Research map / Learning theory and algorithms / Matrix and tensor methods
Cost-Sensitive Learning to Rank
Ryan McBride, Ke Wang, Zhouyang Ren, Wenyuan Li
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 |
|---|---|---|---|
| Replace NDCG-based LambdaMART with Cost-Sensitive MART | LambdaMART · Customers Outages k=10 | RCS@k: 6.0% -> 19.2% | Improved |
| Replace LambdaMART with CS-MART | LambdaMART · Forest Fires k=11 | RCS@k: 25.2% -> 18.3% | Hurt |
| Replace Coordinate Ascent with CS-Coordinate Ascent | Coordinate Ascent · Crime k=6 | RCS@k: 46.8% -> 97.6% | Improved |
| Replace AdaRank with CS-AdaRank | AdaRank · Customers Outages k=10 | RCS@k: 1.7% -> 13.8% | Improved |
| Replace AdaRank with CS-AdaRank | AdaRank · Concrete k=10 | RCS@k: 87.9% -> 84.0% | Hurt |
| Replace RankNet with CR-RankNet | RankNet · High-Risk Outages k=10 | RCS@k: 3.1% -> 7.0% | Improved |
| Replace ListNet with CR-ListNet | ListNet · Forest Fires k=6 | RCS@k: 9.7% -> 25.5% | Improved |
| Replace ListNet with CR-ListNet | ListNet · Concrete k=19 | RCS@k: 81.6% -> 80.0% | Hurt |
| Use CS-MART instead of regression-based Random Forests | Random Forests · Customers Outages k=10 | RCS@k: 11.9% -> 19.2% | Improved |
| Use CS-MART instead of Linear Regression | Linear Regression · High-Risk Outages k=10 | RCS@k: 0.8% -> 11.3% | Improved |
| Remove list-level cost-sensitivity, keeping only cost reweighting (CS-MART to CR-MART) (ablation) | CS-MART · Customers Outages k=10 | RCS@k: 19.2% -> 12.8% | Hurt |
| Remove list-level cost-sensitivity (CS-C. Ascent to CR-C.Ascent) (ablation) | CS-C. Ascent · Customers Outages k=50 | RCS@k: 26.2% -> 19.5% | Hurt |
Closest papers by meaning
- Active Learning for Cost-Sensitive Classification (ICML 2017 · similarity 0.83)
- Online Learning to Rank with Top-k Feedback (JMLR 2017 · similarity 0.82)
- Cost-Aware Near-Optimal Policy Learning (AAAI 2025 · similarity 0.81)
- One-Shot Strategic Classification Under Unknown Costs (ICML 2024 · similarity 0.80)
- Cost-Aware Learning (NeurIPS 2026 · similarity 0.80)
- Learning Classifiers That Induce Markets (ICML 2025 · similarity 0.80)
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.
