Model Machine Learning Berbasis Perilaku Pembayaran Angsuran untuk Prediksi Gagal Bayar KPR Subsidi
DOI:
https://doi.org/10.26418/jp.v11i3.100857Keywords:
KPR Subsidi, Masyarakat Berpenghasilan Rendah, Pembayaran Angsuran, Prediksi Gagal Bayar, Machine LearningAbstract
Penelitian ini menyajikan rancangan dan pembuktian pemanfaatan model machine learning untuk prediksi gagal bayar sesuai definisi Otoritas Jasa Keuangan pada produk KPRS (Kredit Pemilikan Rumah Subsidi) berbasis perilaku pembayaran angsuran pada segmen MBR (Masyarakat Berpenghasilan Rendah). Berbeda dengan sebagian besar penelitian terdahulu yang berfokus pada application scoring saat pengajuan atau pencairan kredit dengan data statis nasabah seperti kemampuan finansial, riwayat peminjaman, informasi pekerjaan, agunan dan data statis lainnya, studi ini menargetkan kredit yang sudah berjalan (on-book) dengan memanfaatkan jejak historis pembayaran angsuran sebagai sumber utama sinyal risiko. Dataset berasal dari salah satu bank penyalur KPRS. Dengan teknik rekayasa fitur, data pembayaran angsuran diubah menjadi fitur tabular yang merangkum perilaku pembayaran (misalnya konsistensi nominal, kelancaran waktu bayar dan pola keterlambatan) yang kemudian dipelajari oleh beberapa metode machine learning, antara lain Multilayer Perceptron, Random Forest, XGBoost dan Logistic Regression. Data mencakup 8.116 akun dan 409.130 catatan transaksi dengan evaluasi menggunakan train set periode 2017–2022 (6.585 akun) dan test set 2023–2024 (1.217 akun). Model terbaik dicapai oleh MLP dengan performa AUC ≈ 0,997 pada test set dengan F1 Score maksimum pada threshold 0,3013 memberikan precision 0,7907, recall 0,9444 dan F1 0,8608. Hasil ini menunjukkan bahwa untuk pinjaman KPRS yang sudah berjalan, pola perilaku pembayaran angsuran semata—tanpa perlu menambahkan informasi mengenai kondisi usaha, kondisi finansial, agunan, maupun karakteristik lain nasabah—dapat dimanfaatkan untuk membangun model machine learning yang mampu memprediksi risiko gagal bayar secara akurat dan dapat memberikan early warning pada portofolio KPRS, sehingga tindakan pencegahan seperti intervensi, reminder atau kunjungan lapangan diharapkan dapat dilakukan secara lebih terarah dan efisien.References
Fortiena, E, Wisana, I, “Subsidi Perumahan, Migrasi dan Permintaan Rumah Studi Kasus Program Kpr Bersubsidi di Indonesia,” Jurnal Kebijakan Ekonomi: Vol. 16: Iss. 2, Article 7. 2021.
M. Azis and G. N. Mariskha, “Pembiayaan Kredit Pemilikan Rumah (Kpr) Subsidi Untuk Meningkatkan Kesejahteraan Masyarakat Berpenghasilan Rendah,” Niqosiya: Journal of Economics and Business Research, vol. 3, no. 1, May 2023, doi: 10.21154/niqosiya.v3i1.1717.
H. Fauzan Takalamingan et al., “Analisis Penerapan Sistem Dan Prosedur Pemberian Kredit Pemilikan Rumah (Kpr) Subsidi Pada Bank Tabungan Negara Cabang Manado,” 2018.
D. Krasovytskyi and A. Stavytskyy, “Predicting Mortgage Loan Defaults Using Machine Learning Techniques,” Ekonomika, vol. 103, no. 2, pp. 140–160, 2024, doi: 10.15388/Ekon.2024.103.2.8.
E. Gothai, R. R. Rajalaxmi, R. Thamilselvan, and K. Sridhar, “Enhanced Loan Approval Prediction System using Ensemble Machine Learning Techniques,” in 3rd International Conference on Automation, Computing and Renewable Systems, ICACRS 2024 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 1182–1187. doi: 10.1109/ICACRS62842.2024.10841604.
M.-T. Hung and H.-C. Lo, “Risk Analysis of Mortgage Loan Default for Bank Customers and AI Machine Learning,” Journal of Applied Finance & Banking, pp. 33–50, Oct. 2024, doi: 10.47260/jafb/1463.
A. Sadhwani, K. Giesecke, and J. Sirignano, “Deep Learning for Mortgage Risk,” Journal of Financial Econometrics, vol. 19, no. 2, pp. 313–368, 2021, doi: 10.1093/jjfinec/nbaa025.
N. A. Aji and A. Dhini, Credit Scoring Through Data Mining Approach : A Case Study of Mortgage Loan In Indonesia. IEEE, 2019.
B. Gao, “Financial Loan Default Risk Prediction Based on Big Data Analysis,” in 2024 IEEE 4th International Conference on Power, Electronics and Computer Applications, ICPECA 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 398–403. doi: 10.1109/ICPECA60615.2024.10471076.
I. Aruleba and Y. Sun, “Effective Credit Risk Prediction Using Ensemble Classifiers With Model Explanation,” IEEE Access, vol. 12, pp. 115015–115025, 2024, doi: 10.1109/ACCESS.2024.3445308.
I. Aruleba and Y. Sun, “An Improved Ensemble Method With Data Resampling for Credit Risk Prediction,” IEEE Access, vol. 13, pp. 71275–71287, 2025, doi: 10.1109/ACCESS.2025.3563432.
M. R. Putri, I. G. P. S. Wijaya, F. P. A. Praja, A. Hadi, and F. Hamami, “The Comparison Study of Regression Models (Multiple Linear Regression, Ridge, Lasso, Random Forest, and Polynomial Regression) for House Price Prediction in West Nusa Tenggara,” in ICADEIS 2023 - International Conference on Advancement in Data Science, E-Learning and Information Systems: Data, Intelligent Systems, and the Applications for Human Life, Proceeding, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/ICADEIS58666.2023.10270916.
Elena, D. Sullivan, H. Christophe, H. Sessi, and Tokpavi, “Machine Learning for Credit Scoring: Improving Logistic Regression with Non-Linear Decision-Tree Effects., 2021.
Z. Callen, C. Thayer, and A. Merrick, “Enhancing Financial Credit Assessment Accuracy with Deep Learning: A Multi-Layer Perceptron Approach.”
B. Masomian and S. Mohsen Mirhosseini, “A model for validating bank customers using multilayer perceptron neural network and imperialist competitive algorithm (ICA),” Int. J. Nonlinear Anal. Appl. In Press, pp. 2008–6822, doi: 10.22075/ijnaa.2023.31084.4561.
Otoritas Jasa Keuangan, Peraturan Otoritas Jasa Keuangan Republik Indonesia. Indonesia, 2019.
Farida, E. T. Wisudaningsih, and W. Aqidah, “Implementasi KPR Bersubsidi Melalui Skema FLPP (Fasilitas Liquiditas Pembiayaan Perumahan) di PT. Trah Wali Nagari,” Jurnal Informatika Ekonomi Bisnis, pp. 46–53, Mar. 2023, doi: 10.37034/infeb.v5i1.204.
H. Hodges, J. A. Connell, C. Garrity, and J. Pope, “Deep Learning, Feature Selection and Model Bias with Home Mortgage Loan Classification,” in International Conference on Pattern Recognition Applications and Methods, Science and Technology Publications, Lda, 2024, pp. 248–255. doi: 10.5220/0012326800003654.
P. Kumar Maroju, “Optimizing Mortgage Loan Processing in Capital Markets: A Machine Learning Approach 1,” International Journal of Innovations in Scientific Engineering www.ijise.in (IJISE) 2023, no. 17, [Online]. Available: www.ijise.in
U. A. Bispo and M. S. Tessmann, “Does Deep Learning with Multilayer Perceptron Perform Well in Predicting Credit Risk?,” Journal of Applied Finance & Banking, pp. 1–12, Aug. 2025, doi: 10.47260/jafb/1541.
J. Alvi, I. Arif, and K. Nizam, “Advancing financial resilience: A systematic review of default prediction models and future directions in credit risk management,” Heliyon, vol. 10, no. 21, Nov. 2024, doi: 10.1016/j.heliyon.2024.e39770.
