This paper presents an experimental study on bank performance prediction base on financial report. This research use Support Vector Machine (SVM), Probabilistic Neural Network (PNN) and Radial Basis Function Neural Network (RBFN) methods to experiment the bank performance prediction. To improve accuracy prediction of both neural network methods, this research use Principal Component Analysis (PCA) to get best feature. This research work based on the bank’s financial report and financial variables predictions of several banks that registered in Bank Indonesia. The experimental results show that the accuracy rate of bank performance prediction of PCA-PNN or PCA-RBFN methods are higher than SVM method for Bank Persero, Bank Non Devisa and Bank Asing categories. But, the accuracy rate of SVM method is higher than PCA-PNN or PCA-RBFN methods for Bank Pembangunan Daerah and Bank Devisa categories. The accuracy rate of PCA-PNN method for all bank categories is comparable to that PCA-RBFN method.
Copyrights © 2011