Profitability Analysis Of Banks By Using Clustering Method: An Application On Turkish Banking Sector

Clustering analysis is currently one of the most popular and advanced mathematical grouping methods both in finance and other existing sciences. The purpose of cluster analysis is to determine the units similar to each other in terms of their characteristics studied, and to define their clustering structures. The banking sector is the most important partner of organizations and countries against developing world economy and fluctuations in global competitive environment. The importance of profitability is clear for banks so in this study we want to cluster banks in Istanbul Stock Exchange based on profitability. There are three public banks, eleven private banks and twelve foreign banks in Turkey. This study aims to cluster 26 banks, listed in the Istanbul Stock Exchange by using profitability ratios. Four profitability ratios employed in the clustering were obtained through the end of the financial statements of the banks. The financial statements are taken from the internet sites of the Banks Association of Turkey. The average of the values of the profitability ratios belonging to the years 2003-2013 were used as the data of the analysis. As a result of the k-cluster analysis, the first, second and third clusters consist of 11, 2, 11 banks respectively. We have found the most similar banks and the less similar banks in our data set and also it is concluded that banks have formed a homegenous structure with the banks except existing groups (public, private and foreign).