본문 바로가기
KERD
논문KCI 등재

XAI 기반 기업부도예측 분류모델 연구

A Study on Classification Models for Predicting Bankruptcy Based on XAI

문남미|김지홍
한국정보처리학회|2023.08|정보처리학회 논문지 (The Transactions of the Korea Information Processing Society)|제12권 제8호|pp. 333-340

0

조회

0

다운로드

4

인용

0

참고문헌

키워드

빅데이터Big Data앙상블EnsembleeXplainable AIBaggingBoosting분류모델배깅부스팅Classification Model
주제분류컴퓨터학

초록

기업 부도의 효율적인 예측은 금융기관의 적절한 대출 결정과 여신 부실률 감소 측면에서 중요한 부분이다. 많은 연구에서 인공지능 기술을활용한 분류모델 연구를 진행하였다. 금융 산업 특성상 새로운 예측 모델의 성능이 우수하더라도 어떤 근거로 결과를 출력했는지 직관적인 설명이수반되어야 한다. 최근 미국, EU, 한국 등 에서는 공통적으로 알고리즘의 설명요구권을 제시하고 있어 금융권 AI 활용에 투명성을 확보하여야한다. 본 논문에서는 외부에 오픈된 기업부도 데이터를 활용하여 인공지능 기반의 해석 가능한 분류 예측 모델을 제안하였다. 먼저 데이터 전처리작업, 5겹 교차검증 등을 수행하고 로지스틱 회귀, SVM, XGBoost, LightGBM 등 10가지 지도학습 분류모델 최적화를 통해 분류 성능을 비교하였다. 그 결과 LightGBM이 가장 우수한 모델로 확인되었고, 설명 가능한 인공지능 기법인 SHAP을 적용하여 부도예측 과정에 대한 사후 설명을 제공하였다.

Abstract

Efficient prediction of corporate bankruptcy is an important part of making appropriate lending decisions for financial institutionsand reducing loan default rates. In many studies, classification models using artificial intelligence technology have been used. In thefinancial industry, even if the performance of the new predictive models is excellent, it should be accompanied by an intuitive explanationof the basis on which the result was determined. Recently, the US, EU, and South Korea have commonly presented the right to requestexplanations of algorithms, so transparency in the use of AI in the financial sector must be secured. In this paper, an artificialintelligence-based interpretable classification prediction model was proposed using corporate bankruptcy data that was open to the outsideworld. First, data preprocessing, 5-fold cross-validation, etc. were performed, and classification performance was compared throughoptimization of 10 supervised learning classification models such as logistic regression, SVM, XGBoost, and LightGBM. As a result, LightGBMwas confirmed as the best performance model, and SHAP, an explainable artificial intelligence technique, was applied to provide apost-explanation of the bankruptcy prediction process.

참고문헌 (37)

  1. A. Hanif, "Towards explainable artificial intelligence in banking and financial services", arXiv preprint arXiv : 2112. 08441, ~ (2021)
  2. E. I. Altman, "Financial ratios, discriminant analysis and the prediction of corporate bankruptcy", The Journal of Finance, 23(4), pp.589~609 (1968)
  3. J. A. Ohlson, "Financial ratios and the probabilistic prediction of bankruptcy", Journal of Accounting Research, pp.109~131 (1980)
  4. C. Cortes, "Support-vector networks", Machine Learning, 20, pp.273~297 (1995)
  5. G. Wang, "A comparative assessment of ensemble learning for credit scoring", Expert Systems with Applications, 38(1), pp.223~230 (2011)
  6. S. M. Lundberg, "From local explanations to global understanding with explainable AI for trees", Nature Machine Intelligence, 2(1), pp.56~67 (2020)
  7. T. N. Chou, "An explainable hybrid model for bankruptcy prediction based on the decision tree and deep neural network", 2019 IEEE 2nd International Conference on Knowledge Innovation and Invention (ICKII), pp.122~125 (2019), IEEE
  8. M. T. Ribeiro, "‘Why should i trust you?’ Explaining the predictions of any classifier", Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.1135~1144 (2016)
  9. R. Guidotti, "A survey of methods for explaining black box models", ACM computing surveys(CSUR), 51(5), pp.1~42 (2018)
  10. A. Adadi, "Peeking inside the black-box : A survey on explainable artificial intelligence(XAI)", IEEE Access, 6, pp.52138~52160 (2018)
  11. S. M. Lundberg, "A unified approach to interpreting model predictions", Advances in Neural Information Processing Systems, 30 (2017)
  12. F. Barboza, "Machine learning models and bankruptcy prediction", Expert Systems with Applications, 83, pp.405~417 (2017)
  13. H. A. Alaka, "Systematic review of bankruptcy prediction models : Towards a framework for tool selection", Expert Systems with Applications, 94, pp.164~184 (2018)
  14. S. Jones, "Corporate bankruptcy prediction : A high dimensional analysis", Review of Accounting Studies, 22, pp.1366~1422 (2017)
  15. S. B. Jabeur, "CatBoost model and artificial intelligence techniques for corporate failure prediction", Technological Forecasting and Social Change, 166, pp.120658~ (2021)
  16. Y. P. Huang, "A new perspective of performance comparison among machine learning algorithms for financial distress prediction", Applied Soft Computing, 83, pp.105663~ (2019)
  17. P. Carmona, "Predicting failure in the US banking sector : An extreme gradient boosting approach", International Review of Economics & Finance, 61, pp.304~323 (2019)
  18. R. Matin, "Predicting distresses using deep learning of text segments in annual reports", Expert Systems with Applications, 132, pp.199~208 (2019)
  19. H. Son, "Data analytic approach for bankruptcy prediction", Expert Systems with Applications, 138, pp.112816~ (2019)
  20. S. B. Jabeur, "Bankruptcy prediction using partial least squares logistic regression", Journal of Retailing and Consumer Services, 36, pp.197~202 (2017)
  21. Y. Wu, "Feature construction for fraudulent credit card cash-out detection", Decision Support Systems, 127, pp.113155~ (2019)
  22. S. Zhang, "Learning k for knn classification", ACM Transactions on Intelligent Systems and Technology(TIST), 8(3), pp.1~19 (2017)
  23. M. I. Habibie, "Performance analysis and classification using naive bayes and logistic regression on big data", 2022 1st International Conference on Smart Technology, Applied Informatics, and Engineering (APICS), pp.48~52 (2022), IEEE
  24. L. Breiman, "Random forests", Machine Learning, 45, pp.5~32 (2001)
  25. S. K. Yadav, "Data mining : A prediction for performance improvement of engineering students using classification", arXiv preprint arXiv : 1203. 3832, ~ (2012)
  26. T. Chen, "Xgboost : A scalable tree boosting system", Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.785~794 (2016)
  27. J. H. Friedman, "Greedy function approximation : A gradient boosting machine", Annals of Statistics, pp.1189~1232 (2001)
  28. G. Ke, "Lightgbm: A highly efficient gradient boosting decision tree", Advances in Neural Information Processing Systems, 30 (2017)
  29. L. Prokhorenkova, "CatBoost: Unbiased boosting with categorical features", Advances in Neural Information Processing Systems, 31 (2018)
  30. T. Duan, "Ngboost : Natural gradient boosting for probabilistic prediction", International Conference on Machine Learning, pp.2690~2700 (2020), PMLR
  31. G. D. P. Regulation, "General data protection regulation (GDPR)", Intersoft Consulting, ~ (2018)
  32. Artificial Intelligence (AI)R&D Strategy for the Realization of I-Korea 4.0, "Ministry of Science and ICT", ~ (2018)
  33. D. Liang, "Financial ratios and corporate governance indicators in bankruptcy prediction : A comprehensive study", European Journal of Operational Research, 252(2), pp.561~572 (2016)
  34. J. Sun, "Class-imbalanced dynamic financial distress prediction based on AdaboostSVM ensemble combined with SMOTE and time weighting", Information Fusion, 54, pp.128~144 (2020)
  35. J. Fan, "Predicting daily diffuse horizontal solar radiation in various climatic regions of China using support vector machine and tree-based soft computing models with local and extrinsic climatic data", Journal of Cleaner Production, 248, pp.119264~ (2020)
  36. J. D. Rodriguez, "Sensitivity analysis of k-fold cross validation in prediction error estimation", IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(3), pp.569~575 (2009)
  37. A. Tharwat, "Classification assessment methods", Applied Computing and Informatics, 17, pp.1~ (2021)

관련 논문AI추천

금융 합성 데이터를 사용한 기업 부도 예측 모델 연구권혁진, 이한준대한경영정보학회 · 경영과 정보연구2025 · 제44권 제4호데이터 클래스 불균형 상황에서 설명가능 인공지능을 이용한 기업부도예측모델의 적용과 해석에 관한 연구백동현, 윤종철한국산업경영시스템학회 · 한국산업경영시스템학회지2025 · 제48권 제1호데이터 불균형을 고려한 설명 가능한 인공지능 기반 기업부도예측 방법론 연구백동현, 허선우한국산업경영시스템학회 · 한국산업경영시스템학회지2022 · 제45권 제2호설명가능한 인공지능을 활용한 COVID-19 이후 기업신용등급 하락 예측 연구박기윤, 방성식, 서동욱한국금융정보학회 · 금융정보연구2025 · 제14권 제1호설명 가능한 인공지능을 활용한 은행대출연체 예측 모델 연구김연국, 이성우, 최봉진한국전산회계학회 · 전산회계연구2024 · 제22권 제2호기업 신용평가 모형에 설명 가능한 AI 적용을 위한 TabNet 기반 프레임워크: 기업 신용평가 모형 연구를 중심으로김창효, 이군희, 정승호한국중소기업학회 · 중소기업연구2023 · 제45권 제3호

이 간행물의 다른 논문 (4건)

다중 어댑터를 이용한 교차 언어 및 스타일 기반의 제목 생성최용석, 이공주, 박요한pp. 341-354비지도 학습 기반의 임베딩과 오토인코더를 사용한 침입 탐지 방법이준우, 김강석pp. 355-364자유대화의 음향적 특징 및 언어적 특징 기반의성인과 노인 분류 성능 비교한승훈, 강병옥, 동성희pp. 365-370확률적 교차 연산을 이용한 보편적 관계 추출이제승, 김재훈pp. 371-380
원문 보기