Estimating available supermarket commodities for food bank collection in the absence of information
作者：
Highlights：
• Food banks collect usable, yet unsellable commodities donated by supermarkets.
• The amounts of each donated food type is not known prior to collection.
• Four approximation methods are compared to determine which provides best estimates.
• The impacts of approximation methods on transportation costs is also evaluated.
• Neural networks provide good estimations for on-hand food and transportation costs.
摘要
•Food banks collect usable, yet unsellable commodities donated by supermarkets.•The amounts of each donated food type is not known prior to collection.•Four approximation methods are compared to determine which provides best estimates.•The impacts of approximation methods on transportation costs is also evaluated.•Neural networks provide good estimations for on-hand food and transportation costs.
论文关键词：Artificial neural networks,Forecasting,In-kind donations,Data mining,Food bank operations
论文评审过程：Available online 13 December 2014.
论文官网地址：https://doi.org/10.1016/j.eswa.2014.11.068
