Research map / Learning theory and algorithms / Prediction and decision losses
Exploring Tradeoffs in Automated School Redistricting: Computational and Ethical Perspectives
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use RecomChain rather than SPATIAL | Automated school redistricting · School District A and B, all school levels | RER (%): 56.53 -> 60.43; 81.17 -> 82.08; 80.43 -> 81.16; 59.24 -> 61.18; 84.56 -> 85.25; 86.47 -> 86.53 | Helped |
| Use RecomChain rather than SPATIAL | Automated school redistricting · School District A, elementary schools | BAL (%): 86.56 -> 88.05 | Helped |
| Use RecomChain rather than SPATIAL | Automated school redistricting · School District A, middle and high schools | BAL (%): 92.71 -> 92.67; 97.42 -> 97.36 | No clear effect |
| Use RecomChain rather than SPATIAL | Automated school redistricting · School District B, all school levels | BAL (%): 90.85 -> 94.25; 91.68 -> 92.20; 91.47 -> 92.47 | Helped |
| Replace Polsby-Popper with retained edge ratio in the compactness objective (ablation) | SPATIAL · School District B, elementary, middle, and high schools | computational time (minute/run): 443.80; 228.67; 119.31 (Polsby-Popper) -> 102.66; 50.07; 65.04 (Retained Edge Ratio) | Helped |
| Replace Polsby-Popper with retained edge ratio in the compactness objective (ablation) | FlipChain and RecomChain · School District B, all school levels | computational time (minute/run): +20.51% efficiency enhancement | Helped |
| Use recombination transitions instead of single-node flips (ablation) | MCMC redistricting framework · School District A and B, all school levels | RER (%): 58.80 -> 60.43; 80.19 -> 82.08; 79.52 -> 81.16; 59.50 -> 61.18; 83.71 -> 85.25; 85.37 -> 86.53 | Helped |
| Increase balance-objective weight α (ablation) | Redistricting objective · School District B, all school levels | retained student ratio | Hurt |
| Increase balance-objective weight α (ablation) | Redistricting objective · School District B, all school levels | student diversity | No clear effect |
| Optimize balance and student diversity without optimizing compactness (ablation) | FlipChain · School District B, all school levels | boundary compactness | Hurt |
| Use recombination transitions instead of single-node flips (ablation) | MCMC redistricting framework · School District B, middle and high schools | retained student ratio | Hurt |
Closest papers by meaning
- Contextual Stochastic Optimization for School Desegregation Policymaking (AAAI 2025 · similarity 0.88)
- Achieving Balanced Representation in School Choice with Diversity Goals (AAAI 2025 · similarity 0.83)
- High School Course Scheduling: Student Preferences and Fairness Constraints (Student Abstract) (AAAI 2025 · similarity 0.83)
- Implications of Distance over Redistricting Maps: Central and Outlier Maps (AAAI 2024 · similarity 0.82)
- Generalized Dimension Reduction Using Semi-Relaxed Gromov-Wasserstein Distance (AAAI 2025 · similarity 0.79)
- Stable Matchings in Practice: A Constraint Programming Approach (AAAI 2024 · similarity 0.78)
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.