A NEW FUZZY CLUSTERING ALGORITHM FOR EVALUATING THE PERFORMANCE OF NON-BANKING FINANCIAL INSTITUTIONS IN ROMANIA

作者：Costea Adrian^*; Bleotu Vasile

来源：Economic Computation and Economic Cybernetics Studies and Research, 2012, 46(4): 179-199.

• fuzzy logic
• clustering
• Fuzzy C-Means algorithm
• linguistic variables
• weights
• non-banking financial institutions
• performance evaluation models

In this article we propose a modified version of Fuzzy C-Means (FCM) clustering algorithm in order to better allocate the uncertain observations in the clusters. We change the objective function of the classic FCM by attaching different weights to the distances between observations and the clusters' centers. We apply the modified FCM (Weighting FCM) to model the performance of non-banking financial institutions (NFIs) in Romania. We extend the experiment from our previous work by improving NFIs' performance dataset from 3 to 8 performance ratios and from 44 to 769 observations. The results show a significant improvement in pattern allocation with the new proposed algorithm.

• 出版日期2012