The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Comparative study of prediction models for corporate bond rating

국내 회사채 신용 등급 예측 모형의 비교 연구

  • Received : 2018.03.29
  • Accepted : 2018.05.02
  • Published : 2018.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Prediction models for a corporate bond rating in existing studies have been developed using various models such as linear regression, ordered logit, and random forest. Financial characteristics help build prediction models that are expected to be contained in the assigning model of the bond rating agencies. However, the ranges of bond ratings in existing studies vary from 5 to 20 and the prediction models were developed with samples in which the target companies and the observation periods are different. Thus, a simple comparison of the prediction accuracies in each study cannot determine the best prediction model. In order to conduct a fair comparison, this study has collected corporate bond ratings and financial characteristics from 2013 to 2017 and applied prediction models to them. In addition, we applied the elastic-net penalty for the linear regression, the ordered logit, and the ordered probit. Our comparison shows that data-driven variable selection using the elastic-net improves prediction accuracy in each corresponding model, and that the random forest is the most appropriate model in terms of prediction accuracy, which obtains 69.6% accuracy of the exact rating prediction on average from the 5-fold cross validation.

회사채 신용 등급 예측 모형에 대한 연구는 신용 평가 기관이 회사채 신용 등급 평가에 사용될 것이라 예상 되는 여러 재무적 특성 변수들을 기반으로 진행되었으며 선형 회귀 모형(linear regression), 순위 로짓(ordered logit), 순위 프로빗(ordered probit), 서포트 벡터 기계(support vector machine), 랜덤 포레스트(random forest) 등 다양한 모형들을 적용하여 개발되었다. 하지만 기존 연구들에서 고려한 회사채 신용 등급은 연구에 따라 5등급에서 20등급까지 다른 등급 구간을 적용하였으며 분석에 이용된 표본 자료의 기간 및 대상도 상이하여 예측 성능의 공정한 비교에 어려움이 있다. 따라서 본 연구에서는 2013년부터 2017년까지의 회사채 신용 등급 자료와 기존 연구들에서 사용된 재무 지표들을 통합하여 기존에 발표된 예측 모형들을 동일한 자료에 적용하고 예측 성능을 비교하였다. 추가적으로 Elastic-net 벌점화 회귀 모형 및 순위 로짓, 순위 프로빗 모형을 적합하여 LASSO 벌점이 선택됨을 확인하였으며 LASSO 벌점을 고려한 예측 모형이 대응하는 기존의 예측 모형들보다 향상된 성능을 보임을 확인하였다. 본 연구의 수행 결과, 랜덤 포레스트를 이용한 예측 모형이 15등급 기준 검증 자료에서 정확한 등급 예측률이 69.6%로 다른 모형과 비교하여 높은 예측 성능을 나타내었다.

Keywords

References

  1. Akaike, H. (1974). A new look at the statistical model identification, IEEE Transactions on Automatic Control, 19, 716-723. https://doi.org/10.1109/TAC.1974.1100705
  2. Altman, E. I. and Katz, S. (1976). Statistical bond rating classification using financial and accounting data. In Proceeding of the Conference on Topical Research in Accounting, NYU Press, 205-239.
  3. Breiman, L. (1996). Bagging predictors, Machine Learning, 24, 123-140.
  4. Ederington, L. H. (1986). Why split ratings occur, Financial Management, 15, 37-47. https://doi.org/10.2307/3665276
  5. Horrigan, J. O. (1966). The determination of long-term credit standing with financial ratios, empirical research in accounting: selected studies, Supplement to Journal of Accounting Research, 4, 44-62. https://doi.org/10.2307/2490168
  6. Huang, Z., Chen, H., Hsu, C. J., Chen, W. H., and Wu, S. (2004). Credit rating analysis with support vector machines and neural networks: a market comparative study, Decision Support Systems, 37, 534-558.
  7. Jeong, C. J. (2011). The empirical study on factors affecting corporate credit ratings (Unpublished master's thesis), Kyonggi University, Suwon, Korea.
  8. Kaplan, R. S. and Urwitz, G. (1979). Statistical models of bond ratings: a methodological inquiry, Journal of Business, 52, 231-261. https://doi.org/10.1086/296045
  9. Kim, J. S. and Choi, Y. M. (2006). Development of a bond rating prediction model based on financial and stock price-based variables, Study on Accounting, Taxation & Auditing, 43, 185-217.
  10. Kim, K. J. and Kim, J. S. (2002). Development of bond rating prediction model for effective interest rate estimation, Korean Accounting Journal, 11, 81-100.
  11. Kim, M. J. (2012). Ensemble learning with support vector machines for bond rating, Journal of Intelligence and Information System, 18, 29-45.
  12. Kim, S. J. and Ahn, H. (2016). Application of random forests to corporate credit rating prediction, The Journal of Business and Economics, 32, 187-211.
  13. Kim, S. T., Lee, J. J., and Hong, J. B. (2006). The prediction model of bond-rating with ordered logit analysis, Journal of the Korean Data Analysis Society, 8, 641-654.
  14. Ko, D. P. and Kim, H. M. (2002). Using financial health index approach to credit analysis, Industrial Management Review, 25, 231-254.
  15. Pinches, G. E. and Mingo, K. A. (1973). A multivariate analysis of industrial bond ratings, Journal of Finance, 28, 1-18. https://doi.org/10.1111/j.1540-6261.1973.tb01341.x
  16. Seo, Y. H. (2015). The effect of revenue-expense matching on corporate bond ratings (Unpublished master's thesis), Chung-Ang University, Seoul, Korea.
  17. Tibshirani, R. (1996). Regression shrinkage and selection via the lasso, Journal of the Royal Statistical Society. Series B: Statistical Methodology, 58, 267-288.
  18. West, R. R. (1970). An alternative approach to predicting corporate bond ratings, Journal of Accounting Research, 8, 118-125. https://doi.org/10.2307/2674717
  19. Wurm, M. J., Rathouz, P. J., and Hanlon B. M. (2017). Regularized ordinal regression and the ordinalNet R package, arXiv preprint arXiv:1706.05003.
  20. Zou, H. and Hastie, T. (2005). Regularization and variable selection via the elastic net, Journal of the Royal Statistical Society. Series B, 67, 301-320. https://doi.org/10.1111/j.1467-9868.2005.00503.x