DocumentCode :
3120899
Title :
DEA based hierarchical structure evaluation and visualization method
Author :
Inoue, Kazushige ; Ichinotsubo, Takeo ; Aoki, Shingo
Author_Institution :
Dept. of Comput. Sci. & Intell. Syst., Osaka Prefecture Univ., Sakai, Japan
fYear :
2011
fDate :
27-30 June 2011
Firstpage :
1701
Lastpage :
1704
Abstract :
Data Envelopment Analysis (DEA) is a method for evaluating the management efficiency of Decision Making Units (DMUs) relatively. However, when the number of inputs and outputs items is increased, the results of evaluation value are similar regretfully. In order to evaluate Japanese universities which have various activities, this study proposed the hierarchical structure DEA model which is divided into some activities (finance, achievement, attractiveness, research, and education). Hierarchical structure has constructed by some layers based on the theory that the efficiencies of lower layer can not exceed the ones of upper layer. In addition, this paper proposed the visualization method that the analyst can visually understand which field is strong or weak. Using proposed DEA model and visualizing method, the numerical study showed us to be able to understand the feature of each university.
Keywords :
data envelopment analysis; data visualisation; decision making; educational institutions; nonparametric statistics; DEA based hierarchical structure evaluation; DMU; Japanese university; data envelopment analysis; decision making units; hierarchical structure DEA model; management efficiency; visualization method; Analytical models; Data envelopment analysis; Data models; Data visualization; Education; Finance; Intelligent systems; Data Envelopment Analysis; Decision Support System; Vissualizaiion Method;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Fuzzy Systems (FUZZ), 2011 IEEE International Conference on
Conference_Location :
Taipei
ISSN :
1098-7584
Print_ISBN :
978-1-4244-7315-1
Electronic_ISBN :
1098-7584
Type :
conf
DOI :
10.1109/FUZZY.2011.6007530
Filename :
6007530
Link To Document :
بازگشت