TabNet을 활용한 국내 기업의 신용등급 예측에 관한 연구
A Study on Predicting Credit Ratings of Korean Companies using TabNet
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
최근 IT 기술의 발전과 더불어 금융 시장에서의 불확실성이 증대되는 상황에서 기업 신용등급평가의 중요성을 인식하고, 이를 개선하기 위한 새로운 접근 방식으로 딥러닝 모델인 TabNet을제안한다. 이에 본 연구에서는 TabNet을 활용하여 기업 신용등급을 예측하고, 이의 예측 성능을기존 머신러닝 방법론과 상세하게 비교한다. 한국의 주요 증권시장에 상장된 기업들의 재무 데이터를 기반으로 TabNet 알고리즘을 적용하여 신용등급 예측 모델을 구축하고, 다양한 머신러닝 모델과의 성능을 비교 분석하였다. 실험 결과, TabNet 모델은 Precision 0.884, F1이 0.895로 기존의머신러닝 모델들보다 우수한 성능을 보였으며, 고위험 기업을 저위험 기업으로 잘못 분류하는 경우가 다른 머신러닝 모델보다 적어 TabNet의 우수성을 확인하였다. 이는 TabNet이 기업 신용등급예측에 있어 효과적인 도구로 활용될 수 있으며, 금융기관의 신용 위험 관리 및 의사 결정 과정을 지원할 수 있을 것으로 기대한다.
Abstract
This study presents TabNet, a novel deep learning method, to enhance corporate credit rating accuracy amidst growing financial market uncertainties due to technological advancements. By analyzing data from major Korean stock markets, the research constructs a credit rating prediction model using TabNet. Comparing it with traditional machine learning, TabNet proves superior, achieving a Precision of 0.884 and an F1 score of 0.895. It notably reduces misclassification of high-risk companies as low-risk, emphasizing its potential as a vital tool for financial institutions in credit risk management and decision-making.
참고문헌 (21)
- J. H. Park, "Factors Affecting Corporate Insolvency Prediction Based on Explainable Artificial Intelligence", Journal of Digital Contents Society, 24(9), pp.2093~2105 (2023)[DOI]
- X. L. Zheng, "FinBrain : when finance meets AI 2. 0", Frontiers of Information Technology & Electronic Engineering, 20(7), pp.914~924 (2019)[DOI]
- S. Ö. Arik, "TabNet : Attentive Interpretable Tabular Learning", AAAI, 35(8), pp.6679~6687 (2021)[DOI]
- Y. j. Kim, "Initial Credit Ratings and Asymmetric Cost Behavior", KOREAN JOURNAL OF MANAGEMENT ACCOUNTING RESEARCH, 21(2), pp.23~46 (2021)[DOI]
- Y. W. Jeong, "The impact of bond ratings by domestic and foreign credit rating agencies on stock prices", Korean Jouranl of Business Administration, 27(3), pp.371~391 (2014)
- Y. J. Chen, "Forecasting corporate credit ratings using big data from social media", Expert Systems with Applications, 207 (2022)[DOI]
- H. C. Ahn, "Intelligent Credit Rating Model for Korean Companies using Multiclass Support Vector Machines", korean management review, 35(5), pp.1479~1496 (2006)
- I. G. Han, "Development and Application of Intelligent Credit Scoring System : Boram Bank Case", Information Systems Review, 1(1), pp.51~61 (1999)
- Z. Huang, "Credit rating analysis with support vector machines and neural networks : a market comparative study", Decision support systems, 37(4), pp.543~558 (2004)[DOI]
- K. Kumar, "Artificial neural network vs linear discriminant analysis in credit ratings forecast : A comparative study of prediction performances", Review of Accounting and Finance, 5(3), pp.216~227 (2006)[DOI]
- Y. Ye, "A Multiclass Machine Learning Approach to Credit Rating Prediction", 2008 International Symposiums on Information Processing, pp.57~61 (2008)
- S. C. Huang, "Integrating nonlinear graph based dimensionality reduction schemes with SVMs for credit rating forecasting", Expert Systems with Applications, 36(4), pp.7515~7518 (2009)[DOI]
- X. Guo, "A corporate credit rating model using support vector domain combined with fuzzy clustering algorithm", Mathematical Problems in Engineering, 2012, pp.1155~ (2012)[DOI]
- H. C. Wu, "Two-stage credit rating prediction using machine learning techniques", Kybernetes, 43(7), pp.1098~1113 (2014)[DOI]
- S. j. Kim, "Application of Random Forests to Corporate Credit Rating Prediction", The Journal of Industrial Innovation, 32(1), pp.187~211 (2016)
- H. k. Park, "Comparative study of prediction models for corporate bond rating", The Korean Journal of Applied Statistics, 31(3), pp.367~382 (2018)[DOI]
- S. H. Chung, "TabNet-Based Framework for Application of XAI to Corporate Credit Rating Models : On the Credit Rating Model for Enterprise", Asia Pacific Journal of Samall Business, 45(3), pp.45~65 (2023)[DOI]
- S. Ioffe, "Batch normalization : Accelerating deep network training by reducing internal covariate shift", International conference on machine learning, pp.448~456 (2015)
- Y. N. Dauphin, "Language modeling with gated convolutional networks", International conference on machine learning, pp.933~941 (2017)
- A. Martins, "From softmax to sparsemax : A sparse model of attention and multi-label classification", International conference on machine learning, pp.1614~1623 (2016), pmlr
- N. V. Chawla, "SMOTE : Synthetic Minority Over-sampling Technique", Journal of Artificial Intelligence Research, 16, pp.321~357 (2002)[DOI]