Search for: All records

In the quest for equitable resource distribution within food banks and their partner agencies, understanding the dependencies of these agencies on food banks emerges as a critical factor. This study investigates the intricate dynamics influencing agency dependency ratios, exploring the complex factors that shape the demand for food resources. Leveraging historical self-reported dependency ratio data, this preliminary study employs predictive modeling using Multiple Linear Regression to forecast agency dependencies on food banks. The primary objective is to discern the underlying factors that significantly impact agency dependency ratios. Employing Least Absolute Shrinkage and Selection Operator (LASSO) as a feature selection technique, the study identifies the key variables that capture the essence of the dataset. Identifying the variables that contribute the most to the model paves the way for robust predictive modeling. This study offers a comprehensive approach to understanding and predicting agency dependencies on food banks. The findings hold significant implications for non-profit hunger relief organizations, aiding in strategic decision- making for equitable resource distribution. 

Hunger relief organizations often estimate food demand using food distribution data. Leveraging Visual Analytics (VA) and historical data, we examine how underlying factors like unemployment, poverty rate, and median household income affect forecasts for aid recipients’ food demand. Our study reveals that incorporating these factors enhances forecast accuracy. Visual Analytics empowers decision-makers to integrate field knowledge with computational insights, enabling more informed decisions. This innovative approach presents a valuable tool for charitable organizations to strategically improve forecasting precision in the dynamic landscape of hunger relief. 

Food banks are key players in the fight against hunger. The complexity of the food bank operations data makes decision-making very challenging. Data visualization can allow food bank operations managers to quickly and easily understand the data and make evidence-based decisions. However, poorly designed visualizations could be confusing and/or misleading. This study uses eye-tracking technology to understand how users interact with various food bank data visualizations and use eye-tracking data to better design those visualizations. The findings of this study will have an impact on improving the effectiveness and efficiency of the food bank operations.