OPTIMASI ARTIFICIAL NEURAL NETWORK MENGGUNAKAN PARTICLE SWARM OPTIMIZATION UNTUK PREDIKSI KREDIT MACET

Khoirul, Anwar and Abdul, Syukur and Ricardus Anggi, Pramunendar OPTIMASI ARTIFICIAL NEURAL NETWORK MENGGUNAKAN PARTICLE SWARM OPTIMIZATION UNTUK PREDIKSI KREDIT MACET. OPTIMASI ARTIFICIAL NEURAL NETWORK MENGGUNAKAN PARTICLE SWARM OPTIMIZATION UNTUK PREDIKSI KREDIT MACET.

[img] Text
OPTIMASI_ARTIFICIAL_NEURAL_NETWORK_MENGG-57200233.pdf

Download (585kB)

Abstract

The emergence of data storage technology has facilitated the ability of financial institutions to store all information regarding the characteristics and behavior of electronic credit applicants' payments. In a well-developed financial system, crisis management is ahead and risk predictions are behind. The main objective of risk prediction is to use financial information, such as business financial statements, transaction records and customer payments, and others. Credit is the main source of income for a bank and is also the biggest source of risk. Wherein one of the important decisions that financial institutions must make in granting credit is deciding whether to provide loans to customers or not. This decision basically boils down to the problem of making the right decision to distinguish good and bad customers. Until now, this distinction was made only by checking the form data from the applicant. The results of the testing conducted by the researcher, with the Credit Risk Data of Bank Nurja Muamalah Paiton Probolinggo, used the artificial neural network algorithm based on Particle Swarm Optimization (PSO) when the dataset was tested using only ann accuracy rate of 76.21%, and at the time artificial neural network combined with particle swarm optimation there was an increase in the level of accuracy of 1,66% to 77.87%. Keywords: Prediction, Credit Risk, Optimization, Artificial Neural Network, Particle Swarm Optimation

Item Type: Article
Uncontrolled Keywords: Prediction, Credit Risk, Optimization, Artificial Neural Network, Particle Swarm Optimation
Subjects: T Technology > TN Mining engineering. Metallurgy
Divisions: Fakultas Teknologi Informasi > Rekayasa Perangkat Lunak
Depositing User: M.Kom Khoirul Anwar
Date Deposited: 25 Jul 2020 04:26
Last Modified: 25 Jul 2020 04:26
URI: http://repository.unmerpas.ac.id/id/eprint/21

Actions (login required)

View Item View Item