Research map / Learning theory and algorithms / Fairness
Allocating Interventions Based on Predicted Outcomes: A Case Study on Homelessness Services
Amanda Kube, Sanmay Das, Patrick J. Fowler
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 actual allocation with BART-based optimal capacitated assignment | Homeless service allocation · Predicted re-entry rate | predicted re-entry (%): 43.72% -> 31.88% (27.08% reduction) | Improved |
| Add constraint capping any household's predicted re-entry increase at 5 pp (ablation) | Optimal allocation · Predicted re-entry rate | predicted re-entry (%): 31.88% -> 37.38% | Hurt |
| Add 5 pp constraint (ablation) | Optimal allocation · Households harmed | share of households with higher re-entry probability (%): 32.62% -> 19.08% | Improved |
| Assign to homelessness prevention vs other services | Households · Re-entry probability | percentage point change: -11.55 pp, CI [8.17,13.67] | Improved |
Closest papers by meaning
- Evaluating Index-based Treatment Allocation in Underresourced Communities (AAAI 2025 · similarity 0.87)
- Allocation Requires Prediction Only if Inequality Is Low (ICML 2024 · similarity 0.87)
- Preventing Eviction-Caused Homelessness through ML-Informed Distribution of Rental Assistance (AAAI 2024 · similarity 0.87)
- Predictive Modeling of Homeless Service Assignment: A Representation Learning Approach (AAAI 2025 · similarity 0.86)
- Comparing Targeting Strategies for Maximizing Social Welfare with Limited Resources (ICLR 2025 · similarity 0.84)
- Discretionary Trees: Understanding Street-Level Bureaucracy via Machine Learning (AAAI 2024 · similarity 0.84)
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.
