Non-Performing Loan Prediction for Credit Application Analysis Using Feature Selection and Ensemble Methods

David Jefri Aruan; Rusdah Rusdah; Ahmad Pudoli

doi:10.36080/idealis.v9i2.3851

Authors

David Jefri Aruan Magister Ilmu Komputer, Fakultas Teknologi Informasi, Universitas Budi Luhur, Jakarta, Indonesia
Rusdah Rusdah Magister Ilmu Komputer, Fakultas Teknologi Informasi, Universitas Budi Luhur, Jakarta, Indonesia
Ahmad Pudoli Teknik Informatika, Fakultas Teknologi Informasi, Universitas Budi Luhur, Jakarta, Indonesia

DOI:

https://doi.org/10.36080/idealis.v9i2.3851

Keywords:

Collectability, Credit Application, Ensemble Method, Feature Selection, Hyperparameter Tuning, Non-Performing Loans

Abstract

Non-Performing Loans (NPL) are a fundamental indicator of a financial institution's asset health, reflecting loans that fail to meet interest or principal payment obligations as agreed. A high NPL ratio negatively impacts a bank's financial performance, such as decreased profitability as measured by Return on Assets (ROA) and decreased liquidity. Bank Indonesia sets an NPL tolerance limit of 5% of total credit provided by banking financial institutions. Therefore, a predictive model is needed that can detect the possibility of customers experiencing NPLs early. This study aims to identify relevant factors in predicting NPLs and create an NPL prediction model based on these factors. The contribution of this study lies in combining the results of three feature selection techniques: Chi-Square, Mutual Information, and Random Forest feature importance, using the average score eliminated by the Recursive Feature Elimination technique. Several ensemble algorithms, namely Random Forest, XGBoost, Gradient Boosting, and LightGBM, were explored to produce the best-performing model. Then, hyperparameter tuning was performed on the best model. The Random Forest model produced the best performance, with 92.17% accuracy, 78.1% precision, 98.1% recall, and 95.5% AUC. Hyperparameter tuning was shown to improve recall, thus improving the model's ability to measure how much positive data (Current class) was successfully predicted by the model. The results of this study can assist management in making credit decisions. Thus, it is hoped that it can help reduce the number of NPL cases.

Downloads

Download data is not yet available.

References

[1] J. C. Chandra, A. E. Putri, A. Z. Ongko, and E. T. Manurung, “The Effect of Non-Performing Loan (NPL) on Net Income at PT Bank Central Asia Tbk,” International Journal for accountancy, vol. 12, no. 1, pp. 2610–2616, 2025.

[2] D. S. Bhakti, A. Prasetyo, and P. Arsi, “Implementation of Hyperparameter Tuning in Random Forest Algorithm for Loan Approval Prediction,” Jurnal Teknik Informatika (Jutif), vol. 5, no. 4, pp. 63–69, 2024, doi: 10.52436/1.jutif.2024.5.4.2032.

[3] T. Segal, “Nonperforming Loan (NPL) Definitions, Types, Causes, Consequences,” Aug. 02, 2025. Accessed: Aug. 07, 2025. [Online]. Available: https://www.investopedia.com/terms/n/nonperformingloan.asp

[4] S. Masrom, R. A. Rahman, N. H. M. Shukri, N. A. Yahya, M. Z. A. Rashid, and N. B. Zakaria, “The nexus of corruption and non-performing loan: machine learning approach,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 32, no. 2, pp. 838–844, 2023, doi: 10.11591/ijeecs.v32.i2.pp838-844.

[5] M. A. Elnaggar, M. A. EL Azeem, and F. A. Maghraby, “Machine Learning Model for Predicting Non-performing Agricultural Loans,” in Advances in Intelligent Systems and Computing, Springer, 2020, pp. 395–404. doi: 10.1007/978-3-030-44289-7_37.

[6] A. Soomro, “Loan Default Prediction Using Machine Learning Algorithms: A Systematic Literature Review 2020 -2023,” Pakistan Journal of Life and Social Sciences (PJLSS), vol. 22, no. 2, 2024, doi: 10.57239/PJLSS-2024-22.2.00469.

[7] A. Soomro, H. Zakariyah, S. M. A. Aftab, M. Muflehi, A. Shah, and S. Meraj, “Loan Default Prediction Using Machine Learning Algorithms: A Systematic Literature Review 2020–2023,” Pak. J. Life Soc. Sci., vol. 22, no. 2, pp. 6234–6253, 2024, doi: 10.57239/PJLSS-2024-22.2.00469.

[8] M. Abdullah, M. A. F. Chowdhury, A. Uddin, and S. Moudud‐Ul‐Huq, “Forecasting nonperforming loans using machine learning,” J. Forecast., vol. 42, no. 7, pp. 1664–1689, 2023, doi: 10.1002/for.2977.

[9] J. P. Noriega, L. A. Rivera, and J. A. Herrera, “Machine Learning for Credit Risk Prediction: A Systematic Literature Review,” Data (Basel)., vol. 8, no. 11, 2023, doi: 10.3390/data8110169.

[10] M. Annisa and Rusdah, “Prediction of Non-Performing Loans for Credit Application Analysis of Rural Bank Using Random Forest,” in 2022 9th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), IEEE, Oct. 2022, pp. 111–114. doi: 10.23919/EECSI56542.2022.9946628.

[11] M. Muhajir and J. Widiastuti, “Random Forest Method to Customer Classification Based on Non-Performing Loan in Micro Business,” Jurnal Online Informatika, vol. 7, no. 2, pp. 177–183, 2022, doi: 10.15575/join.v7i2.842.

[12] D. B. Saputra, V. Atina, and F. E. Nastiti, “Penerapan Model CRISP-DM pada Prediksi Nasabah Kredit Menggunakan Algoritma Random Forest,” IDEALIS : InDonEsiA journaL Information System, vol. 7, no. 2, pp. 240–247, 2024, doi: 10.36080/idealis.v7i2.3244.

[13] A. C. Mawarni, R. Rusdah, L. L. Hin, and D. Anubhakti, “Deteksi Dini Gejala Awal Penyakit Diabetes Menggunakan Algoritma Random Forest,” IDEALIS : InDonEsiA journaL Information System, vol. 6, no. 2, pp. 165–171, 2023, doi: 10.36080/idealis.v6i2.3018.

[14] T. Chaturvedi, S. Halder, U. S. kumar, N. Das, and S. Bittu, “Comparative Performance Analysis of Machine Learning Algorithms for Non-Performing Loan Prediction,” in 2025 International Conference on Computational, Communication and Information Technology (ICCCIT), IEEE, Feb. 2025, pp. 13–18. doi: 10.1109/ICCCIT62592.2025.10928008.

[15] H. Begum, A. H. M. Z. Haq, and N. A. Shilpa, “machine Learning for Non-Performing Loan Prediction: Enhancing Credit Risk Management,” in The 1st International Online Conference on Risk and Financial Management, MDPI, Jun. 2025.

[16] W. Andriani, Gunawan, and N. N. P. W. Naja, “Analisis perbandingan machine learning untuk prediksi kelayakan kredit perbankan pada Bank BRI Tegal,” IT-Explore: Jurnal Penerapan Teknologi Informasi dan Komunikasi, vol. 4, no. 1, pp. 82–92, 2025, doi: 10.24246/itexplore.v4i1.2025.pp82-92.

[17] N. Hazizah, Sharipuddin, and A. Feranika, “Implementasi Algoritma Random Forest Dalam Klasifikasi Risiko Gagal Bayar Kartu Kredit Pada Nasabah Bank,” Jurnal Manajemen Teknologi Dan Sistem Informasi (JMS), vol. 5, no. 1, pp. 1050–1059, 2025, doi: 10.33998/jms.2025.5.1.2384.

[18] J. P. Noriega, L. A. Rivera, and J. A. Herrera, “Machine Learning for Credit Risk Prediction: A Systematic Literature Review,” Data (Basel)., vol. 8, no. 11, p. 169, 2023, doi: 10.3390/data8110169.

[19] D. Pebrianti, H. Kurniawan, L. Bayuaji, and R. Rusdah, “XgBoost Hyper-Parameter Tuning Using Particle Swarm Optimization for Stock Price Forecasting,” Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, vol. 9, no. 4, pp. 1179–1195, 2024, doi: 10.26555/jiteki.v9i4.27712.

[20] Rusdah, B. A. Bregastantyo, and J. E. Riwurohi, “Prognosis Model of The Treatment Period of Tuberculosis Patients with Medication Compliance Parameters using The Gradient Boosting Algorithm,” in 2023 6th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), Batam: IEEE, Dec. 2023, pp. 220–225. doi: 10.1109/ISRITI60336.2023.10467254.

[21] F. Ardiansyah, F. Hamdan, S. Sugiyanto, and I. Wahyu Siadi, “Klasifikasi Customer Relationship Management Menggunakan Dataset KDD Cup 2009 dengan Teknik Reduksi Dimensi,” Komputika : Jurnal Sistem Komputer, vol. 11, no. 2, pp. 193–202, 2022, doi: 10.34010/komputika.v11i2.6498.

[22] F. Gorunescu, “Data Mining Techniques in Computer-Aided Diagnosis : Non-Invasive Cancer Detection,” World Acad. Sci. Eng. Technol., vol. 34, pp. 280–283, 2007, doi: doi.org/10.5281/zenodo.1059721.