Veri Zarflama Analizinde Karar Verme Birimlerinin Sıralanmasına Yeni Yaklaşımlar

Abstract

In this thesis, two new ranking methods have been proposed in the scope of Data Envelopment Analysis (DEA) which is used to evaluate the relative effectiveness of Decision Making Units (DMUs) with multiple inputs and outputs. The methods called CSE (Changed Super Efficiency) and ASES (Area of Super Efficiency Score Graph) are able to rank efficient and inefficient DMUs. The two proposed methods also include procedures that calculate their own efficiency score and perform a complete ranking. In addition, as opposed to previous methods, both methods rank all types of efficient DMUs fairly, not just special types. The CSE method includes a comprehensive evaluation procedure that takes into account both the initial scores of the DMUs and their impact on each other. As a result, DMUs are preferred when they achieve good scores at the beginning and have effect on others. In the proposed ASES method, DMUs are evaluated by analyzing the change in their efficiency scores by removal of other DMUs from the data set. Both methods take the positions of the DMUs in the data set, their competitors, proximity to the efficient frontier, clustering and extreme points into account. The proposed methods are first applied to example problems and analyzed with the help of graphs. In applications, rankings were carried out using real data.