FoodRL: A Reinforcement Learning Ensembling Framework For In-Kind Food Donation Forecasting

TL;DR

FoodRL is a reinforcement learning ensemble framework that improves in-kind food donation forecasting accuracy for food banks, especially during disruptions, enabling better resource allocation and social impact.

Contribution

The paper introduces FoodRL, a novel RL-based meta-learning framework that dynamically clusters and weights diverse models for improved forecasting under volatile conditions.

Findings

Outperforms baseline models during disruptions

Enables redistribution of 1.7 million additional meals annually

Demonstrates effectiveness across different regional food banks

Abstract

Food banks are crucial for alleviating food insecurity, but their effectiveness hinges on accurately forecasting highly volatile in-kind donations to ensure equitable and efficient resource distribution. Traditional forecasting models often fail to maintain consistent accuracy due to unpredictable fluctuations and concept drift driven by seasonal variations and natural disasters such as hurricanes in the Southeastern U.S. and wildfires in the West Coast. To address these challenges, we propose FoodRL, a novel reinforcement learning (RL) based metalearning framework that clusters and dynamically weights diverse forecasting models based on recent performance and contextual information. Evaluated on multi-year data from two structurally distinct U.S. food banks-one large regional West Coast food bank affected by wildfires and another state-level East Coast food bank consistently impacted by hurricanes, FoodRL consistently outperforms baseline methods, particularly during periods of disruption or decline. By delivering more reliable and adaptive forecasts, FoodRL can facilitate the redistribution of food equivalent to 1.7 million additional meals annually, demonstrating its significant potential for social impact as well as adaptive ensemble learning for humanitarian supply chains.