PREDIKSI TINGKAT KELANCARAN PEMBAYARAN KREDIT UNTUK MEMBANTU PENGAMBILAN KEPUTUSAN MENGGUNAKAN ALGORITMA LONG SHORT-TERM MEMORY

Muhammad Rafly Purnama, . (2025) PREDIKSI TINGKAT KELANCARAN PEMBAYARAN KREDIT UNTUK MEMBANTU PENGAMBILAN KEPUTUSAN MENGGUNAKAN ALGORITMA LONG SHORT-TERM MEMORY. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (231kB)
[img] Text
AWAL.pdf
Download (2MB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (291kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (488kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (339kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (605kB)
[img] Text
BAB 5.pdf
Download (270kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (235kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (135kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (653kB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (8MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (543kB)

Abstract

The increasing demand for credit amidst growing financial needs in society requires financial institutions to conduct thorough analyses of customers' repayment abilities. Non-performing loans can lead to significant losses and threaten the sustainability of financial institutions if not properly managed. This study aims to predict the smoothness of credit payments to support decision-making in credit approval using the Long Short-Term Memory (LSTM) algorithm. The main issue addressed in this research is the high risk of bad credit due to the manual analysis of extensive customer historical data. The methodology includes collecting historical data from company PT Bank Negara Indonesia (Persero) Tbk, data preprocessing, normalization, sequence generation, as well as model training and evaluation using the Root Mean Square Error (RMSE) metric. The results show that the LSTM model can provide fairly accurate predictions of credit payment performance, with the best RMSE score of 0.0198.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2110511057] [Pembimbing 1: Indra Permana Solihin] [Pembimbing 2: Jayanta] [Penguji 1: Didit Widiyanto] [Penguji 2: Radinal Setyadinsa]
Uncontrolled Keywords: Credit, LSTM, Machine Learning, Prediction, RMSE.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > T Technology (General)
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: MUHAMMAD RAFLY PURNAMA
Date Deposited: 20 Aug 2025 08:45
Last Modified: 20 Aug 2025 08:45
URI: http://repository.upnvj.ac.id/id/eprint/37680

Actions (login required)

View Item View Item