Implementasi Backpropagation dalam Memprediksi Kebangkrutan Bank di Indonesia  

Oleh:

Santoso, Albertus Joko ; Chrestanti, Ruth

Jenis: Article from Journal - ilmiah nasional
Dalam koleksi: Jurnal Teknologi Industri vol. 6 no. 4 (Oct. 2002), page 195-202.
Topik: Bankruptcy Prediction; Bank Bankruptcy Indicator; Artyicial Neural Network; Backpropagarion; Momentum

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: JJ83.3 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

Artificial Neural Network (ANN) is means that can be trained to recognize pattern and behavior of a system through learning process. ANN will learn the past data of system, until it has ability to make a decision of data that has not been learned before. Through recognition of past pattern, then ANN can be used to predict the future. This journal presents one of the implementation of ANN in the field of Economics, that is. bank bankruptcy prediction in Indonesia. The learning algorithm that is used in the ANN model is Backpropagation with momentum. The inputs for the ANN model are five financial ratios and a dummy variable that are considered as bank bankruptcy indicators in Indonesia, that is, BMPK, RORA, PBAP, ROA, FBS, and KRLC. The data that is used are one and two years prior bank bankruptcy, the purpose of this is to see how well the ANN model can predict bankruptcy uses data of one and two years prior bankruptcy. The results of the ANN model testing with different net’s parameters and different fiscal years, showed that the ANN model could predict bank bankruptcy in Indonesia used data of one year prior bankruptcy, but the ANN model could not predict well used data of two years prior bankruptcy.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali