Enhancing Credit Risk Classification Using LightGBM with Deep Feature Synthesis

  • Sarah Rosdiana Tambunan Institut Teknologi Del, Indonesia
  • Junita Amalia Institut Teknologi Del, Indonesia
  • Kristina Margaret Sitorus Institut Teknologi Del, Indonesia
  • Yehezchiel Abed Rafles Sibuea Institut Teknologi Del, Indonesia
  • Lucas Ronaldi Hutabarat Institut Teknologi Del, Indonesia
Keywords: Credit Risk, P2P Lending, Feature Engineering, Feature Selection, LightGBM

Abstract

In the digital financial services era, Peer-to-Peer (P2P) lending has emerged as a significant innovation in fintech. However, credit risk remains a major concern due to the potential for payment failures, which can cause losses for platforms and investors. This research explores the impact of Deep Feature Synthesis (DFS) on credit risk classification and evaluates the performance of the Light Gradient Boosting Machine (LightGBM) algorithm with and without DFS. The data used in this study was sourced from Kaggle, a peer-to-peer lending company based in San Francisco, California, United States. The dataset contains 74 attributes, with a total of 887,379 rows. DFS automatically generates new attributes, while LightGBM is used for selecting the most important features, aiming to optimize credit risk predictions and simplify the model's complexity. The results of credit risk classification models using DFS and without it. Findings reveal that DFS enhances the accuracy of the credit risk classification, achieving a 0.99 accuracy rate compared to 0.97 without DFS, achieving a recall and F1-score of 0.94 and 0.96 with DFS and 0.68 and 0.81 without DFS. These results suggest that DFS is an effective feature engineering technique for boosting credit risk model performance. This research contributes significantly to the P2P lending industry by demonstrating that combining DFS with LightGBM can improve credit risk management, making it a valuable approach for financial platforms.

Downloads

Download data is not yet available.

References

J. C. Westland, T. Q. Phan, and T. Tan, “Private Information, Credit Risk and Graph Structure in P2P Lending Networks,” pp. 1–31, 2018.

Y. Wang, Y. Zhang, Y. Lu, and X. Yu, “A Comparative Assessment of Credit Risk Model Based on Machine Learning ——a case study of bank loan data,” Procedia Comput. Sci., vol. 174, pp. 141–149, 2020, doi: 10.1016/j.procs.2020.06.069.

D. Li, S. Na, T. Ding, and C. Liu, “Credit risk management of p2p network lending,” Teh. Vjesn., vol. 28, no. 4, pp. 1145–1151, 2021, doi: 10.17559/TV-20200210110508.

A. Fatahuddin, P. Studi Akuntansi, and F. Ekonomi dan Bisnis, “Analisis Risiko pada Platform,” pp. 209–218, 2020.

F. Doko, S. Kalajdziski, and I. Mishkovski, “Credit Risk Model Based on Central Bank Credit Registry Data,” J. Risk Financ. Manag., vol. 14, no. 3, 2021, doi: 10.3390/jrfm14030138.

S. Kokate and M. S. R. Chetty, “Credit risk assessment of loan defaulters in commercial banks using voting classifier ensemble learner machine learning model,” Int. J. Saf. Secur. Eng., vol. 11, no. 5, pp. 565–572, 2021, doi: 10.18280/IJSSE.110508.

C. Guan, H. Suryanto, A. Mahidadia, M. Bain, and P. Compton, “Responsible Credit Risk Assessment with Machine Learning and Knowledge Acquisition,” Human-Centric Intell. Syst., vol. 3, no. 3, pp. 232–243, 2023, doi: 10.1007/s44230-023-00035-1.

S. Lessmann, B. Baesens, H. V. Seow, and L. C. Thomas, “Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research,” Eur. J. Oper. Res., vol. 247, no. 1, pp. 124–136, 2015, doi: 10.1016/j.ejor.2015.05.030.

V. Hassija et al., “Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence,” Cognit. Comput., vol. 16, no. 1, pp. 45–74, 2024, doi: 10.1007/s12559-023-10179-8.

Z. Liu, Y. Wang, F. Feng, Y. Liu, Z. Li, and Y. Shan, “A DDoS Detection Method Based on Feature Engineering and Machine Learning in Software-Defined Networks,” Sensors, vol. 23, no. 13, 2023, doi: 10.3390/s23136176.

J. M. Kanter and K. Veeramachaneni, “Deep feature synthesis: Towards automating data science endeavors,” Proc. 2015 IEEE Int. Conf. Data Sci. Adv. Anal. DSAA 2015, no. c, 2015, doi: 10.1109/DSAA.2015.7344858.

J. Yang et al., “Automatic Feature Engineering-Based Optimization Method for Car Loan Fraud Detection,” Discret. Dyn. Nat. Soc., vol. 2021, 2021, doi: 10.1155/2021/6077540.

N. Thomas Rincy and R. Gupta, “Feature Selection Techniques and its Importance in Machine Learning: A Survey,” 2020 IEEE Int. Students’ Conf. Electr. Electron. Comput. Sci. SCEECS 2020, 2020, doi: 10.1109/SCEECS48394.2020.189.

S. K. Trivedi, “A study on credit scoring modeling with different feature selection and machine learning approaches,” Technol. Soc., vol. 63, no. September, p. 101413, 2020, doi: 10.1016/j.techsoc.2020.101413.

R. Saxena, S. K. Sharma, M. Gupta, and G. C. Sampada, “A Novel Approach for Feature Selection and Classification of Diabetes Mellitus: Machine Learning Methods,” Comput. Intell. Neurosci., vol. 2022, 2022, doi: 10.1155/2022/3820360.

S. B. Coşkun and M. Turanli, “Credit risk analysis using boosting methods,” J. Appl. Math. Stat. Informatics, vol. 19, no. 1, pp. 5–18, 2023, doi: 10.2478/jamsi-2023-0001.

Published
2024-12-17
Abstract views: 227 times
Download PDF: 140 times
How to Cite
Tambunan, S., Amalia, J., Sitorus, K., Sibuea, Y., & Hutabarat, L. (2024). Enhancing Credit Risk Classification Using LightGBM with Deep Feature Synthesis. Journal of Information Systems and Informatics, 6(4), 2599-2610. https://doi.org/10.51519/journalisi.v6i4.902
Section
Articles