Analisis Perbandingan Linear Regression dan Random Forest Regression untuk Prediksi Batas Kredit: Pendekatan Optimasi Hyperparameter

Algies Rifkha Fadillah; Mohamad Nurkamal Fauzan

doi:10.33795/jip.v10i4.5700

Authors

Algies Rifkha Fadillah Universitas Logistik dan Bisnis Internasional
Mohamad Nurkamal Fauzan Universitas Logistik dan Bisnis Internasional

DOI:

https://doi.org/10.33795/jip.v10i4.5700

Keywords:

linear regression, random forest regression, optimasi hyperparameter, batas pinjaman kredit

Abstract

Penelitian ini mengeksplorasi penggunaan Linear Regression dan Random Forest Regression untuk memprediksi batas maksimal pinjaman kredit dalam industri keuangan. Metode ini digunakan untuk membandingkan performa prediksi dengan dua set fitur yang berbeda. Setelah melakukan optimasi hyperparameter menggunakan Optuna, hasil menunjukkan bahwa Random Forest Regression memberikan akurasi prediksi yang lebih tinggi dibandingkan Linear Regression, dengan nilai RMSE terendah sebesar 7.90% dan MAE terendah sebesar 4.72%. Penggunaan 4 fitur menunjukkan sedikit peningkatan dalam akurasi dibandingkan 7 fitur, meskipun tidak signifikan. Hasil ini menyarankan penggunaan Random Forest Regression untuk meningkatkan keakuratan dalam menetapkan batas kredit, mengurangi risiko kredit, dan meningkatkan stabilitas lembaga keuangan. Dengan demikian, pengoptimalan hyperparameter dengan Optuna dapat meningkatkan performa prediksi model regresi dalam konteks ini.

Downloads

Download data is not yet available.

References

Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019). Optuna: A Next-generation Hyperparameter Optimization Framework. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2623–2631. https://doi.org/10.1145/3292500.3330701

Ayhan, T., & Uçar, T. (2022). Determining customer limits by data mining methods in credit allocation process. International Journal of Electrical and Computer Engineering, 12(2), 1910–1915. https://doi.org/10.11591/ijece.v12i2.pp1910-1915

Ganga, A., Vijayalakshmi, S., & Kalpana, R. A. (2021). Deciding bank client’s credit limit and home loan using machine learning. Advances in Parallel Computing, 38, 288–293. https://doi.org/10.3233/APC210053

Hussain, Almarzooq., U., bin, W. (2024). Automating hyperparameter optimization in geophysics with Optuna: A comparative study. Geophysical Prospecting, 72(5), 1778–1788. https://doi.org/10.1111/1365-2478.13484

I.O. Аrtemieva, Igor S. Bondaruk, І. O. M. (2022). Credit as a necessary economic tool of economic relationships between financial companies and banks. Ekonomìčnì Gorizonti, 4(22), 67–78. https://doi.org/https://www.doi.org/10.31499/2616-5236.4(22).2022.267019

Karl, L. (2023). Simple Linear Regression. International Series in Management Science/Operations Research, 57–90. https://doi.org/10.1007/978-3-031-21480-6_4

M.S., Nidhya., Nidhi, Saraswat., Prashant, K. (2024). Leveraging Adaptive Hyper Parameter Tuning for Automated Machine Learning. International Conference on Optimization Computing and Wireless Communication (ICOCWC), 1–7. https://doi.org/10.1109/ICOCWC60930.2024.10470671

Maryam, Hassanali., Mohammadreza, Soltanaghaei., Taghi, Javdani, Gandomani., Farsad, Zamani, B. (2024). Software development effort estimation using boosting algorithms and automatic tuning of hyperparameters with Optuna. Journal of Software: Evolution and Process. https://doi.org/https://doi.org/10.1002/smr.2665

Narayana Darapaneni, Akshay Kumar, Archanna Dixet, M. S. (2022). Loan Prediction Software for Financial Institutions. Interdisciplinary Research in Technology and Management (IRTM), 1–8. https://doi.org/https://doi.org/10.1109/IRTM54583.2022.9791797

Oksana Savko, Juliia Bui, Y. S. (2022). Lending activity development of financial companies in the service sector of individual and legal entities. Ìnfrastruktura Rinku, 65. https://doi.org/https://www.doi.org/10.3284

/infrastruct65-6

Olufemi Ogunleye, J. (2023). Predictive Data Analysis Using Linear Regression and Random Forest. IntechOpen. https://doi.org/10.5772/intechopen.107818

P. Meghana et al. (2024). Analysis of Neural Network Algorithm in Comparison to Multiple Linear Regression and Random Forest Algorithm. 2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS), 437–443. https://doi.org/10.1109/ICETSIS61505.2024.10459496

Piracha, S., Hiba, H., Farooq, U., Fatima, U., Aslam, F., Ishaq, A., & Sial, H. (2022). New Insights and Different Economic Factors in Banking Sectors and Current Challenges. Scholars Bulletin, 8(2), 75–78. https://doi.org/10.36348/sb.2022.v08i02.005

V., Ignatenko., Anton, Surkov., Sergei, K. (2024). Random forests with parametric entropy-based information gains for classification and regression problems. PeerJ, 10. https://doi.org/10 doi: 10.7717/peerj-cs.1775

Zhang, M., & Wang, M. (2018). Review of the Management Theory and Method of Loan Limitation. Atlantis Press, 130(Ifmeita 2017), 1–5. https://doi.org/10.2991/ifmeita-17.2018.1