Volume 55, Number 2, March-April 2021
|Page(s)||505 - 520|
|Published online||31 March 2021|
Allocating fixed resources for DMUs with interval data
Research Center for Smarter Supply Chain, School of Business & Dongwu Think Tank, Soochow University, No. 50, Donghuan Road, Suzhou, RJ, China
2 School of Intelligent Systems Science and Engineering, Jinan University (Zhuhai Campus), Zhuhai, China
3 Department of Industrial & Manufacturing Systems Engineering, The University of Hong Kong, Hong Kong, China
4 College of Economics, Shenzhen University, Shenzhen, China
* Corresponding author: firstname.lastname@example.org
Accepted: 17 December 2020
Conventional DEA models tend to allocate the fixed resources to multiple decision-making units (DMUs) and treat the allocated resource as an extra input for every single DMU. However, the existing DEA resource allocation (DEA-RA) methods are applicable exclusively to the DMUs with exact values of inputs and outputs. A lack of precision for the input or output data of DMUs, such as the interval data, would cause a failure of the existing methods to allocate resources to DMUs. In order to resolve this problem, three DEA-RA models are proposed in this paper for different scenarios of decision-making. All of the proposed DEA-RA models are based on a set of common weights. Finally, the proposed models are empirically tested and validated through three examples. As revealed by the results, our proposed models are capable of providing a more fair and practical initial allocation scheme for decision makers.
Mathematics Subject Classification: 90-08 / 91B32
Key words: Resource allocation / interval data / efficiency
© EDP Sciences, ROADEF, SMAI 2021
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.