Implementasi JST Dalam Menentukan Kelayakan Nasabah Pinjaman KUR Pada Bank Mandiri Mikro Serbelawan Dengan Metode Backpropogation
Abstract: The purpose of this
study was to develop a decision support system that can facilitate in
determining the eligibility of borrowers KUR (Kredit Usaha Rakyat) through
predictive use based on existing data and presents various alternative
solutions in the selection of a feasibility customers in KUR loan. This study
uses Artificial Neural Network applications using Backpropogation method.
Criteria used as an assessment in this study is Collateral, Capacity, Loan
Application Form, Income and Establishment Business License (Business License).
The decision making process consists of two (2) phases where the first phase
and pattern recognition, the second phase is forecast feasibility KUR
customers. pattern recognition and predictive feasibility KUR customers using different
data with the same process using training and testing. The conclusion by the
two architectural models 5-2-1 and 5-3-1, obtained 93% accuracy with
0.0009995807 MSE is the 5-2-1 model architecture. This model is used to predict
the feasibility of KUR customers with accuracy> 90% and MSE truth
0.0009566280.
Penulis: Agus Perdana Windarto
Kode Jurnal: jptinformatikadd170399
