Cooperative mechanism based on data envelopment analysis and artificial neural network to measure efficiency: case study of Iranian ports
by Raheleh Mousavizadeh; Kaveh Khalili-Damghani
International Journal of Applied Decision Sciences (IJADS), Vol. 10, No. 1, 2017

Abstract: Ports are main parts of business and transportation in every country. So, measuring the efficiency of ports is essential. There are several criteria involved in assessment of ports performance. This paper presents a cooperative approach based on data envelopment analysis (DEA) and artificial neural network (ANN) to measure the efficiency and ranking of 11 main ports in Iran. The results show that the DEA-ANN approach outperforms classic DEA approach. The proposed approach provides following advantages: 1) high discrimination power in presence of low number of decision making units (DMUs) and high number of inputs and outputs; 2) suitable estimation of future production function; 3) providing a proper estimation of future efficiency scores; 4) no need to use super-efficiency models to rank the DMUs. The proposed model of this study can help managers to evaluate the performance of DMUs on the basis of future estimated inputs and outputs.

Online publication date: Tue, 24-Jan-2017

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Applied Decision Sciences (IJADS):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com