efficiency;
e-business;
dot com;
principal components analysis;
data envelopment analysis;
inputs/outputs selection;
web metrics;
D O I:
10.1016/j.dss.2003.08.004
中图分类号:
TP18 [人工智能理论];
学科分类号:
081104 ;
0812 ;
0835 ;
1405 ;
摘要:
This paper uses Data Envelopment Analysis (DEA), a non-parametric approach to the estimation of production functions, in order to assess efficiency in dot com firms. These firms have two objectives: to make an impact in the Internet and to obtain revenues from their activities. For this reason, the outputs have been two: unique visitors-a web metric-and revenues. DEA efficiencies have been obtained under various input/output combinations. A ranking of dot com firms in terms of relative efficiency has been obtained. A method based on multivariate analysis has been proven to be successful at showing the strengths and weaknesses of individual dot com firms. It is shown that there is a relationship between the type of e-business (e-tailers, search/portal, content/communities), and the way in which efficiency is obtained. The paper suggests a new approach to the problem of deciding which inputs and outputs the model should contain. (C) 2003 Elsevier B.V. All rights reserved.