Application of Data Mining to Predict Credit Status Using Fuzzy Classification Method  

Oleh:

Mansur, Agus ; RIZKI, MUHAMMAD ; Sulistio, Joko

Jenis: Article from Proceeding
Dalam koleksi: APCOMS 2009: The 2nd Asia-Pacific Conference on Manufacturing System: Reconfigurable Manufacturing System for Facing Turbulent Manufacturing Environment, November 4th-5th, 2009, Yogyakarta, Indonesia, page IX.8-14.
Topik: Data Mining; Prediction; Credit Status;
Fulltext: APCOMS GIX-2.pdf (335.95KB)

Isi artikel

In the implementation of loans activities cases of bad debts that cause losses in the financial institutions concerned are often founded. The prediction of potential debtor’s credit status becomes urgently needed to overcome these problems. This study aims to predict future behavior pattern of debtors related with payment accuracy by using data mining techniques with fuzzy classification method. Classification is a process to find models that explain or distinguish data classes. In this research, the debtor’s status of credit noted as output variables (dependent) while the candidate profile debtors noted as input variables (independent). In this model, data is divided into two parts, training and testing data. Training data is used to determine separation function between first and second class. While, testing data is used to predict the output, therefore, classification errors could be eventually determined. Result from this research is DSS that will facilitate financial institutions in decisions making related to the credit status analysis.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali