Asia-Pacific Journal of Business Venturing and Entrepreneurship (벤처창업연구)

The Korean Society of Business Venturing (한국벤처창업학회)
권호 표지

Study on Predicting the Designation of Administrative Issue in the KOSDAQ Market Based on Machine Learning Based on Financial Data

머신러닝 기반 KOSDAQ 시장의 관리종목 지정 예측 연구: 재무적 데이터를 중심으로

  • Received : 2022.01.03
  • Accepted : 2022.02.23
  • Published : 2022.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

This paper investigates machine learning models for predicting the designation of administrative issues in the KOSDAQ market through various techniques. When a company in the Korean stock market is designated as administrative issue, the market recognizes the event itself as negative information, causing losses to the company and investors. The purpose of this study is to evaluate alternative methods for developing a artificial intelligence service to examine a possibility to the designation of administrative issues early through the financial ratio of companies and to help investors manage portfolio risks. In this study, the independent variables used 21 financial ratios representing profitability, stability, activity, and growth. From 2011 to 2020, when K-IFRS was applied, financial data of companies in administrative issues and non-administrative issues stocks are sampled. Logistic regression analysis, decision tree, support vector machine, random forest, and LightGBM are used to predict the designation of administrative issues. According to the results of analysis, LightGBM with 82.73% classification accuracy is the best prediction model, and the prediction model with the lowest classification accuracy is a decision tree with 71.94% accuracy. As a result of checking the top three variables of the importance of variables in the decision tree-based learning model, the financial variables common in each model are ROE(Net profit) and Capital stock turnover ratio, which are relatively important variables in designating administrative issues. In general, it is confirmed that the learning model using the ensemble had higher predictive performance than the single learning model.

본 연구는 다양한 머신러닝 기법을 통해 코스닥(KOSDAQ) 시장 내 관리종목 지정을 예측할 수 있는 모델에 대해 연구하였다. 증권시장 내 기업이 관리종목으로 지정이 되면 시장에서는 이를 부정적인 정보로 인식하여 해당 기업과 투자자에게 손실을 가져오게 된다. 본 연구를 통해 기업의 재무적 데이터를 바탕으로 조기에 관리종목 지정을 예측하고, 투자자들의 포트폴리오 리스크 관리에 도움을 주기 위한 머신러닝 접근이 타당한지 살펴본다. 본 연구를 위해 활용한 독립변수는 수익성, 안정성, 활동성, 성장성을 나타내는 21개의 재무비율을 활용하였으며, K-IFRS가 적용된 2011년부터 2020년까지 관리종목과 비관리종목의 기업의 재무 데이터를 표본으로 추출하였다. 로지스틱 회귀분석, 의사결정나무, 서포트 벡터 머신, 랜덤 포레스트, LightGBM을 활용하여 관리종목 지정 예측 연구를 수행하였다. 연구결과는 분류 정확도가 82.73%인 LightGBM이 가장 우수한 예측 모형이었으며 분류 정확도가 가장 낮은 예측 모형은 정확도가 71.94%인 의사결정나무였다. 의사결정나무 기반 학습 모형의 변수 중요도의 상위 3개 변수를 확인한 결과 각 모형에서 공통적으로 나온 재무변수는 ROE(당기순이익), 자본금회전율(Capital stock turnover ratio)로 해당 재무변수가 관리종목 지정에 있어 상대적으로 중요한 변수임을 확인하였다. 대체적으로 앙상블을 이용한 학습 모형이 단일 학습 모형보다 예측 성능이 높은 것을 확인하였다. 기존 선행연구가 K-IFRS에 대한 고려를 하지 않았고, 다소 제한된 머신러닝에 의존하였다. 따라서 본 연구의 필요성과 함께 현실적 요구를 충족시키는 결과를 제시하였음을 알 수 있으며, 시장참여자들에게 있어 관리종목 지정에 대한 사전 예측을 확인할 수 있도록 기여했다고 볼 수 있다.

Keywords

Acknowledgement

이 논문은 2020년도 광운대학교 교내학술연구비 지원에 의해 연구되었음(2020-0323). 또한, 이 논문은 2019년 대한민국 교육부와 한국연구재단의 지원을 받아 수행된 연구임(NRF-2019S1A3A2098438)

References

  1. Alaka, H. A., Oyedele, L. O., Owolabi, H. A., Ajayi, S. O., Bilal, M., & Akinade, O. O.(2016). Methodological approach of construction business failure prediction studies: a review. Construction Management and Economics, 34(11), 808-842. https://doi.org/10.1080/01446193.2016.1219037
  2. Altman, E. I.(1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The journal of finance, 23(4), 589-609. https://doi.org/10.1111/j.1540-6261.1968.tb00843.x
  3. Barboza, F., Kimura, H., & Altman, E.(2017). Machine learning models and bankruptcy prediction. Expert Systems with Applications, 83, 405-417. https://doi.org/10.1016/j.eswa.2017.04.006
  4. Beaver, W. H.(1966). Financial ratios as predictors of failure. Journal of Accounting Research, 4, 71-111. https://doi.org/10.2307/2490171
  5. Breiman, L.(2001). Random forests. Machine learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
  6. Campbell, J. Y., Hilscher, J., & Szilagyi, J.(2008). In search of distress risk. Journal of Finance, 63(6), 2899-2939. https://doi.org/10.1111/j.1540-6261.2008.01416.x
  7. Chava, S. & Jarrow, R. A.(2004). Bankruptcy Prediction with industry effects. Review of Finance, 8(4), 537-569. https://doi.org/10.1093/rof/8.4.537
  8. Cho, J. Y., Joo, J. W., & Han, I. G.(2021). The prediction of export credit guarantee accident using machine learning. Journal of Intelligence and Information Systems, 27(1), 83-102. https://doi.org/10.13088/JIIS.2021.27.1.083
  9. Cho, K. I., & Kim, Y. M.(2021). Comparison of bankruptcy prediction models using statistical learning at multiple times. Journal of the Korean Data And Information Science Society, 32(3), 487-499. https://doi.org/10.7465/jkdi.2021.32.3.487
  10. DataScience.(2020). Gradient boosting-what you need to know, Data Science. Retrived from https://datascience.eu/machine-learning/gradient-boosting-what-you-need-to-know.
  11. Devi, S. S., & Radhika, Y.(2018). A survey on machine learning and statistical techniques in bankruptcy prediction. International Journal of Machine Learning and Computing, 8(2), 133-139. https://doi.org/10.18178/ijmlc.2018.8.2.676
  12. Duffie, D., Saita, L., & Wang, K.(2007). Multi-period corporate default prediction with stochastic covariates. Journal of financial economics, 83(3), 635-665. https://doi.org/10.1016/j.jfineco.2005.10.011
  13. Eom, H. N., Kim, J. S., & Choi, S. O.(2020). Machine learning-based corporate default risk prediction model verification and policy recommendation: Focusing on improvement through stacking ensemble model. Journal of Intelligence and Information Systems, 26(2), 105-129. https://doi.org/10.13088/JIIS.2020.26.2.105
  14. James, G., Witten, D., Hastie, T., & Tibshirani, R.(2013). An introduction to statistical learning in R. New York: Springer.
  15. Jeon, B. U., Kang, J. S., & Chung, K. Y.(2021). AutoML and CNN-based soft-voting ensemble classification model for road traffic emerging risk detection. Journal of Convergence for Information Technology, 11(7), 14-20. https://doi.org/10.22156/CS4SMB.2021.11.07.014
  16. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Y. Qiwei, & Liu, T. Y.(2017). LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, 30, 3146-3154.
  17. Kim, H. J., Ryu, D. J., & Cho, H.(2019). Corporate default predictions and machine learning. The Korean Journal of Financial Engineering, 18(3), 131-152. https://doi.org/10.35527/kfedoi.2019.18.3.006
  18. Kim, I. H., & Lee, K. S.(2020). Tree based ensemble model for developing and evaluating automated valuation models: The case of Seoul residential apartment.Journal of the Korean Data And Information Science Society, 31(2), 375-389. https://doi.org/10.7465/jkdi.2020.31.2.375
  19. Kim, I. S., In, C. Y., & Lee, M. G.(2016). The effect of administrative issues on the audit report lag. Academic Society of Global Business Administration, 13(1), 257-279. https://doi.org/10.38115/asgba.2016.13.1.257
  20. Kim, I.(2005). Financial characteristics and disignating firms subject to administrative issues. Korean Business Review, 18(2), 179-196.
  21. Kwon, K. H., Kwak, J. W., Cho, M. K., & Kim, J. D.(2012). The Effect of designation as issues for administration on audit hours and audit fees. Tax Accounting Research, 32, 23-45. https://doi.org/10.35349/tar.2012..32.002
  22. Kim, M. C.(2004). Characteristics analysis on the stock return of issues for administration. Tax Accounting Review, 14, 229-245.
  23. Kim, S. J., & Moon, B. Y.(2018). The effect of designated auditor upon the earnings management issue of administrated firms. Korea Accounting Information Association, 36(2), 1-24.
  24. Kim, S. Y.(2010). A legal study on Substantial Investigation of Delisting. Kookmin Law Review, 22(2), 9-58. https://doi.org/10.17251/legal.2010.22.2.9
  25. Kim, T. H., & Eom, C. J.(1997) Rate of return and risk factor of issues for administration. The Journal of Finance and Banking, 3(1), 93-133.
  26. Lee, H. M., Jeon, G. S., & Jang, J. A.(2020). Predicting of the severity of car traffic accidents on a highway using light gradient boosting model. The Journal of the Korea institute of electronic communication sciences, 15(6), 1123-1130. https://doi.org/10.13067/JKIECS.2020.15.6.1123
  27. Martinez, I., & Serve, S.(2017). Reasons for delisting and consequences: A literature review and research agenda. Journal of Economic Surveys, 31(3), 733-770. https://doi.org/10.1111/joes.12170
  28. Moon, J. G., & Hwangbo, Y.(2014). An empirical study on a firm's fail prediction model by considering whether there are embezzlement, malpractice and the largest shareholder changes or not. Asia-Pacific Journal of Business Venturing and Entrepreneurship, 9(1), 119-132. https://doi.org/10.16972/APJBVE.9.1.201402.119
  29. Nam, G. J., Lee, D. M., & Chen, L.(2019). An empirical study on the failure factors of startups using non-financial information. Asia-Pacific Journal of Business Venturing and Entrepreneurship, 14(1), 139-149. https://doi.org/10.16972/apjbve.14.1.201902.139
  30. Nam, K. Y.(2018). A Performance Comparison of Bankruptcy Prediction Model using Data Mining Tools and Techniques. Master's Thesis, Pusan National University, Korea
  31. Ohlson, J. A.(1980). Financial ratios and the probabilistic prediction of bankruptcy. Journal of accounting research, 109-131.
  32. Pang, S. N., & Zhu, H. Q.(2020). Empirical research on financial distress forecast model of Chinese listed companies. Journal Finance and Accounting Accountiong Information, 20(4), 137-157. https://doi.org/10.29189/KAIAJFAI.20.4.7
  33. Park, C. R., & Seo, Y. M.(2015). Financial characteristics of the designated companies of issues for administration' in KOSPI market. Korean Journal of Accounting Research, 20(6), 173-192.
  34. Park, J. S.(2012). KOSDAQ Firm's earnings management using classification shifting. Korean Management Consulting Review, 12(3), 103-126.
  35. Pyo, Y. I., & Kim, I.(2002). Intra-industry information transfer at the time of administrative issues. Korean Management Review, 31(3), 751-767.
  36. Ryu, Y. R., An, S. B., & Ji, S. H.(2020). A study on the earnings management using the discretionary recognition of deferred corporate tax assets due to K-IFRS adoption. Korean International Accounting Review, 92, 183-207.
  37. Shin, C. H.(2021). Case study on performance decline of one of Kakao kids and avoidance of designation as administrative issue. Korea Business Review, 25(1), 105-134. https://doi.org/10.17287/kbr.2021.25.1.105
  38. Shin, D. I., & Kwahk, K. Y.(2018). Development of a detection model for the companies designated as administrative issue in KOSDAQ market. Journal of Intelligence and Information Systems, 24(3), 157-176. https://doi.org/10.13088/JIIS.2018.24.3.157
  39. Shumway, T.(2001). Forecasting bankruptcy more accurately: a simple hazard model. Journal of Business, 74(1), 101-124. https://doi.org/10.1086/209665
  40. Soh, S. K. & Yum, J. I.(2013). Delisting risk in the KOSDAQ market and earnings management. Korean Accounting Review, 38(4), 1-30.
  41. Sohn, S. K., & Oh, M. J.(2008). Accounting informativeness of administrative issues. Yonsei Business Review, 45(2), 127-146.
  42. Yoo, H. B., Tak, K. J., & Mun, J. S.(2021). A Study on the factors and overcoming methods of extinction of provinces in Korea: the exploration with machine learning methods. The Korean Journal of Local Government Studies, 24(4), 443-476. https://doi.org/10.20484/klog.24.4.18
  43. Zmijewski, M. E.(1984). Methodological issues related to the estimation of financial distress prediction models. Journal of Accounting Research, 22, 59-82. https://doi.org/10.2307/2490859