Klasifikasi Kelayakan Kredit Berbasis Machine Learning: Evaluasi Komparatif K-Nearest Neighbor dan Naive Bayes

Herwin Herwin; Supriadi Sahibu; Respaty Namruddin

doi:10.54065/artificial.1974

Authors

Herwin Herwin Universitas Handayani Makassar
Supriadi Sahibu Universitas Handayani Makassar
Respaty Namruddin Universitas Handayani Makassar

DOI:

https://doi.org/10.54065/artificial.1974

Keywords:

Credit Scoring, Gaussian Naive Bayes, Kelayakan Kredit, K-Nearest Neighbor, Machine Learning

Abstract

Penilaian kelayakan kredit memerlukan metode yang mampu mengolah karakteristik pemohon secara konsisten serta mempertimbangkan risiko kesalahan klasifikasi. Penelitian ini bertujuan mengklasifikasikan kelayakan kredit menggunakan algoritma K-Nearest Neighbor (KNN) dan Gaussian Naive Bayes serta membandingkan kinerjanya berdasarkan accuracy, precision, recall, dan F1-score. Data yang digunakan berupa 14.897 data historis pengajuan kredit dengan fitur hasil rekayasa berupa Debt Service Ratio (DSR), disposable income, Loan to Value (LTV), serta indikator kelayakan usia, status rumah, dan tunggakan. Data dibagi menggunakan train-test split dengan proporsi 80% data latih dan 20% data uji. Model KNN diuji pada beberapa nilai K dan diperoleh K=5 sebagai konfigurasi terbaik. Hasil evaluasi menunjukkan bahwa KNN memperoleh accuracy sebesar 94,66% dan weighted F1-score sebesar 94,84%, lebih tinggi dibandingkan Gaussian Naive Bayes yang memperoleh accuracy 91,11% dan weighted F1-score 93,39%. Namun, Gaussian Naive Bayes menunjukkan kemampuan lebih baik dalam mendeteksi kelas Tidak Layak dengan recall sebesar 100%, sedangkan KNN hanya 30,10%. Temuan ini menunjukkan adanya trade-off antara kinerja klasifikasi secara keseluruhan dan kemampuan mendeteksi pemohon berisiko. KNN lebih sesuai untuk klasifikasi agregat, sedangkan Gaussian Naive Bayes dapat dipertimbangkan ketika deteksi kelas Tidak Layak menjadi prioritas. Hasil klasifikasi selanjutnya dapat dimanfaatkan sebagai alat bantu dalam proses penilaian kredit.

References

Afandi, A., Agtriadi, H. B., Luqman, L., & Susanti, M. (2024). Advanced credit scoring with Naive Bayes algorithm: Improving accuracy and reliability in financial risk assessment. Jurnal E-Komtek, 8(2), 399–409. https://doi.org/10.37339/e-komtek.v8i2.2160

Amarnadh, V., & Moparthi, N. R. (2023). Comprehensive review of different artificial intelligence-based methods for credit risk assessment in data science. Intelligent Decision Technologies, 17(4). https://doi.org/10.3233/IDT-230190

Anwar, M., Nidar, S. R., Widianto, S., & Layyinaturrobaniyah. (2021). Lending rationale of financial institution and fintech on the perception of borrowers: A qualitative study. Jurnal Dinamika Manajemen, 12(2), 291–309. https://doi.org/10.15294/jdm.v12i2.31896

Chen, Y., Calabrese, R., & Martin-Barragan, B. (2024). Interpretable machine learning for imbalanced credit scoring datasets. European Journal of Operational Research, 312(1), 357–372. https://doi.org/10.1016/j.ejor.2023.06.036

Dumitrescu, E., Hué, S., Hurlin, C., & Tokpavi, S. (2022). Machine learning for credit scoring: Improving logistic regression with non-linear decision-tree effects. European Journal of Operational Research, 297(3), 1178–1192. https://doi.org/10.1016/j.ejor.2021.06.053

Emmanuel, I., Sun, Y., & Wang, Z. (2024). A machine learning-based credit risk prediction engine system using a stacked classifier and a filter-based feature selection method. Journal of Big Data, 11, Article 23. https://doi.org/10.1186/s40537-024-00882-0

Hayashi, Y. (2022). Emerging trends in deep learning for credit scoring: A review. Electronics, 11(19), 3181. https://doi.org/10.3390/electronics11193181

Jemai, J., & Zarrad, A. (2023). Feature selection engineering for credit risk assessment in retail banking. Information, 14(3), 200. https://doi.org/10.3390/info14030200

Khayatun, S., Sutrisno, C. T. S., & Suharti, M. (2021). Pengaruh prinsip 5C terhadap pemahaman kredit pada Kantor Pusat PT BPR BKK Pati (Perseroda) Kabupaten Pati. Excellent, 8(2). https://doi.org/10.36587/exc.v8i2.1118

Kusuma, I. G. N. A., Pradipta, I. M., Santosa, I. M. A., & Dharmendra, I. K. (2023). Penanganan ketidakseimbangan data pada klasifikasi pengaduan masyarakat. Jurnal Teknologi Informasi dan Komputer, 9(5). https://doi.org/10.36002/jutik.v9i5.2643

Lenka, S. R., Bisoy, S. K., Priyadarshini, R., & Sain, M. (2022). Empirical analysis of ensemble learning for imbalanced credit scoring datasets: A systematic review. Wireless Communications and Mobile Computing, 2022, 6584318, 1–18. https://doi.org/10.1155/2022/6584318

Liu, W., Fan, H., & Xia, M. (2022). Credit scoring based on tree-enhanced gradient boosting decision trees. Expert Systems with Applications, 189, 116034. https://doi.org/10.1016/j.eswa.2021.116034

Liu, Y., Huang, F., Ma, L., Zeng, Q., & Shi, J. (2024). Credit scoring prediction leveraging interpretable ensemble learning. Journal of Forecasting, 43(2), 286–308. https://doi.org/10.1002/for.3033

Misral, M., & Finowa, R. (2021). Penilaian pemberian kredit untuk meminimalisir resiko kredit pada Bank BRI Unit Tampan Kota Pekanbaru. Jurnal Akuntansi dan Ekonomika, 11(1), 139–149. https://doi.org/10.37859/jae.v11i1.2558

Muangthanang, C., Mungsing, S., & Chirawichitcha, N. (2024). Credit risk prediction model using feature engineering and machine learning techniques. International Scientific Journal of Engineering and Technology, 8(1), 19–26. https://doi.org/10.25126/isjet.202512499

Nwafor, C. N., Nwafor, O., & Brahma, S. (2024). Enhancing transparency and fairness in automated credit decisions: An explainable novel hybrid machine learning approach. Scientific Reports, 14, 25174. https://doi.org/10.1038/s41598-024-75026-8

Pamungkas, F. T., & Zulfikar, A. A. (2021). Peran Otoritas Jasa Keuangan (OJK) dalam mengawasi adanya fraud dalam bisnis investasi dalam perspektif hukum ekonomi Islam. Jurnal Penegakan Hukum dan Keadilan, 2(1), 19–40. https://doi.org/10.18196/jphk.v2i1.9507

Quan, J., & Sun, X. (2024). Credit risk assessment using the factorization machine model with feature interactions. Humanities and Social Sciences Communications, 11, 234. https://doi.org/10.1057/s41599-024-02700-7

Rayhan, M. A. (2026). Implementation of Naive Bayes and Support Vector Machine for SMS Spam Classification Using the SMS Spam Collection Dataset. Journal Artificial: Informatika Dan Sistem Informasi, 4(2), 197–212. https://doi.org/10.54065/artificial.1249

Sahroni, M. Y., Setifani, N. A., & Fitriana, D. N. (2021). Analisis perbandingan algoritma Naïve Bayes, k-Nearest Neighbor dan Neural Network untuk permasalahan class-imbalanced data pada kasus credit card fraud dataset. Teknologi: Jurnal Ilmiah Sistem Informasi, 11(2). https://doi.org/10.26594/teknologi.v11i2.2393

Santoso, T., Hardiawan, D., Dwiputra, M., Sapulette, M., & Setiawan, M. (2023). Evidence of credit rationing in Indonesia: Income class and collateral. Economics Development Analysis Journal, 11(4), 507–523. https://doi.org/10.15294/edaj.v11i4.55287

Saputra, Z., Supahri, H. A., Ismanizan, R., & Rahmaddeni. (2024). Perbandingan algoritma KNN (K-Nearest Neighbors), Naïve Bayes, dan SVM (Support Vector Machine) untuk klasifikasi pemberian pinjaman nasabah. Jurnal Ilmiah Sistem Informasi dan Teknik Informatika (JISTI), 7(1), 67–75. https://doi.org/10.57093/jisti.v7i1.182

Shi, S., Tse, R., Luo, W., D’Addona, S., & Pau, G. (2022). Machine learning-driven credit risk: A systemic review. Neural Computing and Applications, 34, 14327–14339. https://doi.org/10.1007/s00521-022-07472-2

Sholihaningtias, D. N. (2023). Rekomendasi kelayakan penerima kredit menggunakan metode TOPSIS dengan pembobotan ROC. Jurnal SAINTEKOM: Sains, Teknologi, Komputer dan Manajemen, 13(1), 88–99. https://doi.org/10.33020/saintekom.v13i1.376

Ulfah, M., Saragih, T. H., Kartini, D., Mazdadi, M. I., & Abadi, F. (2023). Penerapan MWMOTE untuk mengatasi ketidakseimbangan kelas pada klasifikasi risiko kredit. Jurnal Informatika Polinema, 9(4), 477–486. https://doi.org/10.33795/jip.v9i4.1331

Wafda, A. (2024). Integrasi Machine Learning dalam Ritel: Tinjauan Komprehensif tentang Prediksi Harga, Analisis Data Pelanggan, dan Pemanfaatan Media Sosial. Journal Artificial: Informatika Dan Sistem Informasi, 2(2), 90–106. https://doi.org/10.54065/artificial.543

Wijaya, A., Rivaldo, M., & Pribadi, M. R. (2024). Analisis sentimen terhadap aplikasi Mitra Darat menggunakan algoritma Naive Bayes Classifier dan K-Nearest Neighbor. Informatik: Jurnal Ilmu Komputer, 20(3), 112–117. https://doi.org/10.52958/iftk.v20i3.7967

Xia, Y., Li, Y., He, L., Xu, Y., & Meng, Y. (2021). Incorporating multilevel macroeconomic variables into credit scoring for online consumer lending. Electronic Commerce Research and Applications, 49, 101095. https://doi.org/10.1016/j.elerap.2021.101095

Yang, C., Dong, Y., Lu, J., & Peng, Z. (2023). Solving imbalanced data in credit risk prediction: A comparison of resampling strategies for different machine learning classification algorithms, taking threshold tuning into account. Proceedings of the 2022 5th International Conference on Machine Learning and Machine Intelligence, 30–40. https://doi.org/10.1145/3568199.3568204

Yustikasari, Y., Mubarok, H., & Rianto, R. (2022). Comparative analysis performance of K-Nearest Neighbor algorithm and Adaptive Boosting on the prediction of non-cash food aid recipients. Scientific Journal of Informatics, 9(2), 179–188. https://doi.org/10.15294/sji.v9i2.32369

Zhang, X., & Yu, L. (2024). Consumer credit risk assessment: A review from the state-of-the-art classification algorithms, data traits, and learning methods. Expert Systems with Applications, 237, 121484. https://doi.org/10.1016/j.eswa.2023.121484