Performance Assessment and Ranking of Iranian Insurance Companies by a Combined Model with Experts Preferences

This paper presents a combined Data envelopment analysis (DEA) – Principal component analysis (PCA) – Analytical hierarchy process (AHP) to achieve the efficiency scores and ranks of the insurance companies. Fourteen insurance companies with thirteen input and output variables have been considered for the purpose of this study. Since، the DEA model is sensitive to the number of variables in comparison to number of DMUs، to reduce data dimension، the PCA method is used. Obviously، the final ranks from PCA-DEA model is very subjective and only based on the pattern and distribution of data sets. Therefore، for incorporating the expert preferences، the AHP model is combined with two previous models and the final ranking is done by the integrated DEA-PCA-AHP and PCA-DEA model. The results of the proposed model indicates tht three companies Dana، Razi and Dey are top ranks.