Document Type : Research Paper


1 Department of Mathematics, Lahijan Branch, Islamic Azad University, Lahijan, Iran

2 Islamic Azad University, Science and Research Branch, Tehran, Iran

3 Professor, Azad University, Rasht Branch, Department of Mathematics, Gilan, Iran


Today, one of the main problems in many organizations such as banks with many branches, is that the method of evaluating them is not correct. The traditional techniques used to evaluate performance are often single-level and do not provide the manager with enough information to identify the inefficiency causes of inefficient units. In contrast, Bi-level Data Envelopment Analysis (DEA) models solve the problem of ignoring internal relationships. In this paper, first, the factors that had a higher rank were selected as input and output factors with the help of bank experts and the AHP method. Then, the performance of 30 branches of the Central Bank of Iran was evaluated using the leader-follower method and generalizing Russell's non-radial method. In this paper, the intermediate data is desirable and undesirable. The results showed that the proposed model does not have the problems of traditional models and provides a more realistic assessment of the efficiency of bank branches.


Main Subjects