OPTIMALISASI PENILAIAN KELAYAKAN KREDIT DENGAN ALGORITMA BACKPROPAGATION

Authors

  • Mai Sarah Nur Lubis Universitas Budi Darma, Medan
  • Putri Ramadhani Universitas Budi Darma, Medan
  • Pristiwanto Universitas Budi Darma, Medan

DOI:

https://doi.org/10.23969/jp.v9i04.18159

Keywords:

ANN, backpropagation, SBI bank

Abstract

The implementation of the backpropagation algorithm in customer loan eligibility using Artificial Neural Networks (ANN) with the backpropagation method represents an effective approach for evaluating and predicting loan eligibility. This algorithm allows the use of historical data to train a model capable of identifying complex patterns in customer data, including payment behavior, credit history, and other relevant factors. By leveraging this technique, financial institutions can enhance accuracy in assessing credit risk, optimize loan decisions, and reduce the risk of non-performing loans. Loan eligibility assessment is a crucial aspect in the banking industry for minimizing credit risk and increasing profitability. This study proposes a loan eligibility assessment method using the Backpropagation algorithm within Artificial Neural Networks (ANN). The method aims to identify customer eligibility based on historical data and related features such as income, credit history, and age. The research findings indicate that the ANN Backpropagation model can provide accurate predictions of customer loan eligibility with lower error rates compared to traditional methods. These findings suggest that applying the ANN Backpropagation algorithm can enhance the effectiveness of the credit assessment process, minimize credit default risk, and potentially optimize loan decisions in the banking industry.

Downloads

Download data is not yet available.

References

Afif, F., Swedia, R., & Cahyanti, M. (2019). IMPLEMENTASI ALGORITMA ASSOCIATION RULE UNTUK PROMOSI PRODUK BERBASIS WEBSITE PADA BENGKEL DELTA JAYA MOTOR. Jurnal Ilmiah Teknologi Dan Rekayasa, 24(2).

Halim, S., & Wibisono, A. M. (2004). Penerapan Jaringan Saraf Tiruan Untuk Peramalan. Jurnal Teknik Industri, 2(2), 106–114. https://doi.org/10.9744/jti.2.2.106-114

Indah, S., & Setiawan, A. (2011). Penerapan Jaringan Saraf Tiruan Metode Backpropagation Menggunakan VB 6. ULTIMATICS, III(2), 23–28.

Nugroho, P. (2021). Prediksi Nasabah Bank Menggunakan Algoritma Backpropagation. Jurnal Mahasiswa Aplikasi Teknologi …, 3(3), 89–94.

Okprana, H., & Winanjaya, R. (2022). Analisis Pengaruh Komposisi Data Training dan Testing Terhadap Akurasi Algoritma Resilient Backpropagation (RProp). Brahmana : Jurnal Penerapan Kecerdasan Buatan, 4(1), 89–95.

Pangaribuan, Y., & Sagala, M. (2017). Menerapkan Jaringan Saraf Tiruan untuk Mengenali Pola Huruf Menggunakan Metode Perceptron. Jurnal Teknik Informatika Unika St. Thomas, 02(479), 53–59.

Putro. (2020). Tutorial Gender Classification Using The You Look Only Once (YOLO). In (Vol. 1). Kreatif.

Solikhun, S., Safii, M., & Trisno, A. (2017). Jaringan Saraf Tiruan Untuk Memprediksi Tingkat Pemahaman Sisiwa Terhadap Matapelajaran Dengan Menggunakan Algoritma Backpropagation. J-SAKTI (Jurnal Sains Komputer Dan Informatika), 1(1), 24. https://doi.org/10.30645/j-sakti.v1i1.26

Wibawa, M. S. (2018). Pengaruh Fungsi Aktivasi , Optimisasi dan Jumlah Epoch Terhadap Performa Pengaruh Fungsi Aktivasi , Optimisasi dan Jumlah Epoch Terhadap Performa Jaringan Saraf Tiruan. JURNAL SISTEM DAN INFORMATIKA, 4(1).

Yanto, M., Informatika, T., & Komputer, F. I. (2017). PENERAPAN JARINGAN SYARAF TIRUAN DENGAN ALGORITMA PERCEPTRON PADA POLA PENENTUAN NILAI STATUS KELULUSAN. Jurnal TEKNOIF, 5(2), 79–87.

Downloads

Published

2024-11-27