Cornell techniques engineers examined information from a busy New York state meals bank and, utilizing a brand new algorithm, discovered methods to higher distribute and allocate meals, and elevate vitamin amongst its patrons within the course of.
“In order to serve thousands of people and combat food insecurity, our algorithm helps food banks manage their food resources more efficiently – and patrons get more nutrition,” stated lead writer Faisal Alkaabneh, Ph.D. ’20, Cornell’s first doctoral graduate in techniques engineering.
Alkaabneh and his adviser, Oliver Gao, professor of civil and environmental engineering, are co-authors of “A Unified Framework for Efficient, Effective and Fair Resource Allocation by Food Banks Using an Approximate Dynamic Programming Approach,” printed June 29 within the journal Omega.
The researchers reviewed information of the Meals Bank of the Southern Tier, which serves six counties in upstate New York. In 2019, the meals bank distributed 10.9 million meals to about 21,700 folks every week. Practically 19% of its patrons are seniors and about 41% are youngsters, in response to the group’s information.
Final 12 months, the meals bank distributed 2.eight million kilos of recent fruit via 157 companion businesses, and moved about 3.four million kilos of meals via native cellular pantries.
The algorithm Gao and his crew used to find out tips on how to allocate a number of meals classes effectively, primarily based upon pantry requests, demonstrated a 7.73% enchancment in effectivity from 2018 to 2019, in comparison with commonplace meals bank allocation practices. Their calculations additionally confirmed a 3% enchancment in vitamin utilizing a greater diversity of meals, Alkaabneh stated.
Most meals banks face multi-dimensional complexities, as they coordinate a number of meals classes to distribute finite assets resembling canned items, recent produce, meats and dairy.
“One pound of beef is not the same as a pound of vegetables or a pound of bread,” Alkaabneh stated. “It’s so challenging from a mathematical perspective. When you have more than one similar dimension, the problem becomes exponentially more difficult to solve.”
In accordance with Gao, the important thing goal was concisely and mathematically defining the issue.
“It’s a complex equity, efficiency and effectiveness issue,” he stated. “We will simply clear up a mathematical model if the one focus is on effectivity, or effectiveness. However we confronted exponential, multi-dimensional complexity, frequent for many meals banks.
“We hope our research is used as a baseline model for food banks improving practices,” he stated. “and boosting nutrition and policies to help people at risk for hunger.”
Becoming a member of Gao and Alkaabneh on the paper was Ali Diabat of New York College. Funding for the analysis was offered by Cornell.