Contextual Budget Bandit for Food Rescue Volunteer Engagement

2025-09-12

AI Summary

Volunteer-based food rescue platforms face a fundamental trade-off between participation equity and geographic fairness: existing algorithms that boost volunteer engagement exacerbate service disparities across communities. To address this, we propose the Contextual Budget Bandit framework—the first to jointly model context-aware decision-making, budget constraints, and state evolution—and design the Mitosis algorithm, which guarantees theoretical optimality under sparse volunteer settings. Our approach integrates contextual multi-armed bandits, dynamic budget allocation, and heuristic optimization. Evaluated on both synthetic and real-world datasets, our method increases total food rescued by 12.7% and reduces the geographic Gini coefficient by 34.5% relative to baselines, thereby achieving significant co-optimization of operational efficiency and spatial fairness.

Technology Category

• Search and Optimization: Algorithm Configuration
• Machine Learning: Online Learning & Bandits
• Game Theory and Economic Paradigms: Fair Division

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Volunteer-based food rescue platforms tackle food waste by matching surplus food to communities in need. These platforms face the dual problem of maintaining volunteer engagement and maximizing the food rescued. Existing algorithms to improve volunteer engagement exacerbate geographical disparities, leaving some communities systematically disadvantaged. We address this issue by proposing Contextual Budget Bandit. Contextual Budget Bandit incorporates context-dependent budget allocation in restless multi-armed bandits, a model of decision-making which allows for stateful arms. By doing so, we can allocate higher budgets to communities with lower match rates, thereby alleviating geographical disparities. To tackle this problem, we develop an empirically fast heuristic algorithm. Because the heuristic algorithm can achieve a poor approximation when active volunteers are scarce, we design the Mitosis algorithm, which is guaranteed to compute the optimal budget allocation. Empirically, we demonstrate that our algorithms outperform baselines on both synthetic and real-world food rescue datasets, and show how our algorithm achieves geographical fairness in food rescue.

Problem

• Addressing geographical disparities in volunteer engagement
• Maximizing food rescue while maintaining volunteer participation
• Optimizing budget allocation for equitable community service

Innovation

• Contextual Budget Bandit for budget allocation
• Heuristic algorithm for fast empirical performance
• Mitosis algorithm for optimal allocation guarantee