OPTIMALISASI AKURASI PREDIKSI PERSETUJUAN PINJAMAN UANG MENGGUNAKAN ALGORITMA RANDOM FOREST

Ade Irwan; Rudi Kurniawan; Bani Nurhakim; Edi Tohidi

Authors

Ade Irwan STMIK IKMI Cirebon, Indonesia
Rudi Kurniawan STMIK IKMI Cirebon, Indonesia
Bani Nurhakim STMIK IKMI Cirebon, Indonesia
Edi Tohidi STMIK IKMI Cirebon, Indonesia

Keywords:

Random Forest, Hyperparameter Optimization, Grid Search, Credit Risk Assessment, Loan Approval Prediction

Abstract

Permasalahan utama dalam sistem penilaian kelayakan pinjaman adalah belum optimalnya akurasi model prediksi yang digunakan oleh lembaga keuangan, sehingga berpotensi meningkatkan risiko kredit bermasalah. Penelitian ini dilakukan untuk menjawab kebutuhan tersebut dengan mengoptimalkan algoritma Random Forest melalui pendekatan hyperparameter optimization guna meningkatkan performa model dibandingkan model dasar (baseline). Optimalisasi dilakukan menggunakan Grid Search dengan memvariasikan parameter n_estimators dan max_depth, kemudian divalidasi menggunakan cross-validation untuk menilai kestabilan dan generalisasi model. Tahapan penelitian meliputi akuisisi data persetujuan pinjaman, pembersihan dan praproses data, pelatihan model baseline Random Forest, penerapan Grid Search untuk memperoleh parameter terbaik, serta evaluasi kinerja model menggunakan metrik akurasi, F1-score, ROC-AUC, dan confusion matrix. Proses optimasi melalui Grid Search mengonfirmasi bahwa perubahan parameter tidak memberikan peningkatan performa karena model sudah berada pada kondisi optimal, namun optimasi tetap berguna untuk memastikan kestabilan prediksi di berbagai kombinasi parameter. Secara keseluruhan, penelitian ini memperkuat temuan sebelumnya bahwa Random Forest merupakan algoritma yang sangat andal untuk memodelkan risiko kredit, terutama karena ketahanannya terhadap noise dan kemampuan menangani fitur yang beragam. Penelitian ini juga memiliki kontribusi terhadap tujuan Sustainable Development Goals (SDGs), khususnya SDG 8 (Pekerjaan Layak dan Pertumbuhan Ekonomi) dan SDG 9 (Industri, Inovasi, dan Infrastruktur) melalui peningkatan keandalan sistem keuangan digital, serta SDG 1 (Tanpa Kemiskinan) dengan mendukung akses kredit yang lebih adil dan akurat. Dengan demikian, hasil penelitian ini dapat menjadi landasan bagi pengembangan sistem pendukung keputusan berbasis kecerdasan buatan untuk meningkatkan akurasi penilaian kelayakan pinjaman sekaligus mendorong efisiensi proses penilaian risiko di sektor keuangan. Dataset yang digunakan dalam penelitian ini terdiri dari sebanyak 4269 data pengajuan persetujuan pinjaman yang diperoleh dari kaggle. Data tersebut digunakan sebagai dasar dalam proses pelatihan dan pengujian model. Penelitian ini bertujuan untuk menganalisis performa algoritma Random Forest dalam memprediksi persetujuan pinjaman serta mengevaluasi pengaruh optimasi hyperparameter terhadap peningkatan kinerja model. Pendekatan yang digunakan meliputi pembangunan model baseline Random Forest dan model yang dioptimasi menggunakan teknik Grid Search dengan variasi parameter n_estimators dan max_depth.Hasil eksperimen menunjukkan bahwa model baseline telah mencapai performa yang sangat tinggi. Proses optimasi hyperparameter tidak memberikan peningkatan signifikan terhadap nilai akurasi, namun berperan dalam memastikan kestabilan dan konsistensi model. Oleh karena itu, penelitian ini menunjukkan bahwa Random Forest merupakan algoritma yang andal dalam memprediksi persetujuan pinjaman, baik sebelum maupun setelah proses optimasi.

References

C. Liu, Y. Ming, Y. Xiao, W. Zheng, and C. Hsu, “Finding the Next Interesting Loan for Investors on a Peer-to-Peer Lending Platform,” Ieee Access, vol. 9, pp. 111293–111304, 2021, doi: 10.1109/access.2021.3103510.

D. Moldovan, “Algorithmic Decision Making Methods for Fair Credit Scoring,” Ieee Access, vol. 11, pp. 59729–59743, 2023, doi: 10.1109/access.2023.3286018.

M. Rizinski, H. Peshov, K. Mishev, L. Chitkushev, I. Vodenska, and D. Trajanov, “Ethically Responsible Machine Learning in Fintech,” Ieee Access, vol. 10, pp. 97531–97554, 2022, doi: 10.1109/access.2022.3202889.

Z. Zhang, H. A. Hamadi, E. Damiani, C. Y. Yeun, and F. Taher, “Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research,” Ieee Access, vol. 10, pp. 93104–93139, 2022, doi: 10.1109/access.2022.3204051.

H. Rahman, R. S. D’Cruze, M. U. Ahmed, R. Sohlberg, T. Sakao, and P. Funk, “Artificial Intelligence-Based Life Cycle Engineering in Industrial Production: A Systematic Literature Review,” Ieee Access, vol. 10, pp. 133001–133015, 2022, doi: 10.1109/access.2022.3230637.

R. Molina, V. Gil-Costa, M. L. Crespo, and G. Ramponi, “High-Level Synthesis Hardware Design for FPGA-Based Accelerators: Models, Methodologies, and Frameworks,” Ieee Access, vol. 10, pp. 90429–90455, 2022, doi: 10.1109/access.2022.3201107.

E. Acar, E. Bakış, and M. Yılmaz, “Automatic Recognition of Illegal Substations by Employing Logit-Boost Algorithm and LSTM With the Help of Different Landsat-8 OLI Image Spectral Band Parameters: A Case Study in Sason, Turkey,” Ieee Access, vol. 11, pp. 112293–112306, 2023, doi: 10.1109/access.2023.3323694.

T. M. Alam et al., “An Investigation of Credit Card Default Prediction in the Imbalanced Datasets,” Ieee Access, vol. 8, pp. 201173–201198, 2020, doi: 10.1109/access.2020.3033784.

S. T. Kadkhoda and B. Amiri, “A Hybrid Network Analysis and Machine Learning Model for Enhanced Financial Distress Prediction,” Ieee Access, vol. 12, pp. 52759–52777, 2024, doi: 10.1109/access.2024.3387462.

J. Barros, F. Cunha, C. Martins, P. Pedrosa, and P. Cortez, “Predicting Weighing Deviations in the Dispatch Workflow Process: A Case Study in a Cement Industry,” Ieee Access, vol. 11, pp. 8119–8135, 2023, doi: 10.1109/access.2022.3232299.

R. Alasbahi and X. Zheng, “An Online Transfer Learning Framework With Extreme Learning Machine for Automated Credit Scoring,” Ieee Access, vol. 10, pp. 46697–46716, 2022, doi: 10.1109/access.2022.3171569.

Y. Jin, W. Zhang, X. Wu, Y. Liu, and Z. Hu, “A Novel Multi-Stage Ensemble Model With a Hybrid Genetic Algorithm for Credit Scoring on Imbalanced Data,” Ieee Access, vol. 9, pp. 143593–143607, 2021, doi: 10.1109/access.2021.3120086.

Y. Zhong and H. Wang, “Internet Financial Credit Scoring Models Based on Deep Forest and Resampling Methods,” Ieee Access, vol. 11, pp. 8689–8700, 2023, doi: 10.1109/access.2023.3239889.

W. Yotsawat, P. Wattuya, and A. Srivihok, “A Novel Method for Credit Scoring Based on Cost-Sensitive Neural Network Ensemble,” Ieee Access, vol. 9, pp. 78521–78537, 2021, doi: 10.1109/access.2021.3083490.

Y. Yu, G. C. Wan, and M. S. Tong, “A Novel Wireless Propagation Model Based on Bi-LSTM Algorithm,” Ieee Access, vol. 10, pp. 43837–43847, 2022, doi: 10.1109/access.2022.3169174.

E. Casiraghi et al., “Explainable Machine Learning for Early Assessment of COVID-19 Risk Prediction in Emergency Departments,” Ieee Access, vol. 8, pp. 196299–196325, 2020, doi: 10.1109/access.2020.3034032.

D. Rani, N. S. Gill, P. Gulia, F. Arena, and G. Pau, “Design of an Intrusion Detection Model for IoT-Enabled Smart Home,” Ieee Access, p. 1, 2023, doi: 10.1109/access.2023.3276863.

F. Matloob et al., “Software Defect Prediction Using Ensemble Learning: A Systematic Literature Review,” Ieee Access, vol. 9, pp. 98754–98771, 2021, doi: 10.1109/access.2021.3095559.

X. Dastile and T. Çelik, “Making Deep Learning-Based Predictions for Credit Scoring Explainable,” Ieee Access, vol. 9, pp. 50426–50440, 2021, doi: 10.1109/access.2021.3068854.

R. Ghorbani and R. Ghousi, “Comparing Different Resampling Methods in Predicting Students’ Performance Using Machine Learning Techniques,” Ieee Access, vol. 8, pp. 67899–67911, 2020, doi: 10.1109/access.2020.2986809.

N. Quang, A. Selamat, O. Krejcar, E. Herrera‐Viedma, and H. Fujita, “Deep Learning for Phishing Detection: Taxonomy, Current Challenges and Future Directions,” Ieee Access, vol. 10, pp. 36429–36463, 2022, doi: 10.1109/access.2022.3151903.

R. Baembitov and M. Kezunović, “State of Risk Prediction for Management and Mitigation of Vegetation and Weather Caused Outages in Distribution Networks,” Ieee Access, vol. 11, pp. 113864–113875, 2023, doi: 10.1109/access.2023.3324609.

D. Al-Fraihat, Y. Sharrab, A.-R. Al-Ghuwairi, H. Alshishani, and A. Algarni, “Hyperparameter Optimization for Software Bug Prediction Using Ensemble Learning,” Ieee Access, vol. 12, pp. 51869–51878, 2024, doi: 10.1109/access.2024.3380024.

F. Khan, S. Kanwal, S. Alamri, and B. Mumtaz, “Hyper-Parameter Optimization of Classifiers, Using an Artificial Immune Network and Its Application to Software Bug Prediction,” Ieee Access, vol. 8, pp. 20954–20964, 2020, doi: 10.1109/access.2020.2968362.

F. A. Ghaleb, F. Saeed, M. Al-Sarem, S. N. Qasem, and T. Al-Hadhrami, “Ensemble Synthesized Minority Oversampling-Based Generative Adversarial Networks and Random Forest Algorithm for Credit Card Fraud Detection,” Ieee Access, vol. 11, pp. 89694–89710, 2023, doi: 10.1109/access.2023.3306621.

M. Y. Ansari, V. Chandrasekar, A. V Singh, and S. P. Dakua, “Re-Routing Drugs to Blood Brain Barrier: A Comprehensive Analysis of Machine Learning Approaches With Fingerprint Amalgamation and Data Balancing,” Ieee Access, vol. 11, pp. 9890–9906, 2023, doi: 10.1109/access.2022.3233110.

A. Raza, K. Munir, M. Almutairi, and R. Sehar, “Novel Class Probability Features for Optimizing Network Attack Detection With Machine Learning,” Ieee Access, vol. 11, pp. 98685–98694, 2023, doi: 10.1109/access.2023.3313596.

A. Abdellatif, H. Abdellatef, J. Kanesan, C. Chow, J. H. Chuah, and H. M. Gheni, “An Effective Heart Disease Detection and Severity Level Classification Model Using Machine Learning and Hyperparameter Optimization Methods,” Ieee Access, vol. 10, pp. 79974–79985, 2022, doi: 10.1109/access.2022.3191669.