머신러닝기법을 통한 해운기업 부실예측 연구
Machine Learning Models and Failure Prediction on Shipping Companies
0
조회
0
다운로드
7
인용
0
참고문헌
키워드
초록
본 연구는 반복적인 해운업 부실을 조기에 감지하고 선제적인 대응 방안을 마련하고자 머신러닝기법을 적용한 부실예측모형을 개발하여 제안하였다. 로짓, 랜덤 포레스트, 서포트 벡터머신, 릿지, 라쏘 등 총 5개의 머신러닝기법을 사용하여 모형 간 예측성능을 비교하였다. 2000년부터 2019년까지 우리나라 외항운송기업을 대상으로 예측인자를 Altman’s K-score의 구성지표, 해운기업 부실에 뛰어난 예측력을 지닌 것으로 알려진 재무지표 및 해운시황변수로 설정하여 부실예측모형을 구성하였다. 분석 결과, 라쏘와 로짓이 다른 기법에 비해 뛰어난 예측성능을 보여줬으며, 머신러닝기법을 적용하여 부실예측모형을 구축하는 것이 모형 예측력 향상에 도움이 될 수 있음을 확인할 수 있었다.
Abstract
In this study, we aim to develop the failure prediction model for Korea’s shipping companies. We test machine learning models (logit, random forest, support vector machines, ridge, lasso) to predict failure one year prior to the event and compare their performance. We use data from 2000 to 2019 on Korean ocean-going shipping firms. We include Altman’s K-score variables, financial ratios that are known to have predictive ability regarding the failure of shipping companies, and shipping industry-specific variables as predictors for the failure prediction model. By comparing accuracy, sensitivity, specificity, type 1 error, type 2 error, and area under curve of each model, we find that lasso and logit outperform the other techniques, suggesting that applying the machine learning technique would enhance the predictive ability of the failure prediction model on shipping companies.
참고문헌 (38)
- 해양수산업 전망모형 개발연구(III), "권장한", 한국해양수산개발원, 57~72 (2021)
- 김동현, "머신러닝을 이용한 기관 출력 예측 방법에 관한 연구", 해양환경안전학회지, 25(7), pp.851~857 (2019), 해양환경안전학회[DOI]
- 박성화, "한국 해운기업의 부실예측 연구", 해운물류연구, 33(4), pp.823~852 (2018), 한국해운물류학회[DOI]
- 스트레스 테스트를 통한 우리나라 해운․조선기업의 안정성 분석, "박성화", 한국해양수산개발원, 11~15 (2020)
- 박승록, "STATA 를 이용한 응용계량경제학", pp.385~389 (2020), 박영사
- 박희정, "로지스틱회귀분석을 이용한 코스닥기업의 부실예측모형 연구", 한국콘텐츠학회 논문지, 9(3), pp.305~311 (2009), 한국콘텐츠학회
- 이광수, "韓國海運企業의 經營的 特性이 財務構造에 미치는 影響에 관한 實證硏究", 해운물류연구, (43) (2004), 한국해운물류학회
- 이재득, "릿지 회귀와 라쏘 회귀 모형에 의한 부산 전략산업의 지역경제 효과에 대한 머신러닝 예측", 한국항만경제학회지, 37(1), pp.197~215 (2021), 한국항만경제학회
- 경제발전경험모듈화사업 금융위기 조기경보시스템, "이항용", 기획재정부, 31~32 (2015)
- 최필선, "머신러닝 기법을 이용한 대졸자 취업예측 모형", 직업능력개발연구, 21(1), pp.31~54 (2018), 한국직업능력연구원[DOI]
- Abebe, M., "Machine learning approaches for ship speed prediction towards energy efficient shipping", Applied Sciences, 10(7), pp.1~17 (2020)
- Alexandridis, George, "A survey of shipping finance research: Setting the future research agenda", Transportation Research Part E : Logistics and Transportation Review, 115, pp.164~212 (2018)
- Altman, E. I., "Financial ratios, discriminant analysis and the prediction of corporate bankruptcy", The Journal of finance, 23, pp.589~609 (1968)
- Distress Classification for Korean Firms, Credit Bank and Management, "Altman, E. I.", Bank of Korea, 379~410 (1996)
- Barboza, F., "Machine learning models and bankruptcy prediction", Expert Systems with Applications, 83, pp.405~417 (2017)
- Shipping Risk Survey 2020, "BDO", ~ (2020)
- Beaver, W. H., "Financial ratios as predictors of failure", Journal of Accounting Research, pp.71~111 (1966)
- Cesa-Bianchi, A., "Foreign booms, domestic busts : The global dimension of banking crises", Journal of Financial Intermediation, 37, pp.58~74 (2019)
- Choi, J. S., "Development of Early Warning Index in Korean Shipping Industry by Using Signal Approach", Maritime Policy and Management, 45(8), pp.1007~1020 (2018)
- Clintworth, M., "Financial risk assessment in shipping: a holistic machine learning based methodology", Maritime Economics & Logistics, pp.1~32 (2021)
- Haider, J., "Predicting corporate failure for listed shipping companies", Maritime Economics & Logistics, 21(3), pp.415~438 (2019)
- Hill, R. C., "Principles of econometrics", pp.557~558 (2018), John Wiley & Sons
- Hu, Z., "Prediction of fuel consumption for enroute ship based on machine learning", IEEE Access, 7, pp.119497~119505 (2019)
- 김상봉, "부도에측모형을 이용한 기업부실화의 원인분석", 시장경제연구, 40(1), pp.85~106 (2011), 지암남덕우경제연구원
- Kliestik, T., "Bankruptcy prevention : new effort to reflect on legal and social changes", Science and Engineering Ethics, 24(2), pp.791~803 (2018)
- Lozinskaia, A., "Determinants of the probability of default : the case of the internationally listed shipping corporations", Maritime Policy &Management, 44(7), pp.837~858 (2017)
- Maione, C., "Comparative study of data mining techniques for the authentication of organic grape juice based on ICP-MS analysis", Expert Systems with Applications, 49, pp.60~73 (2016)
- Mitroussi, K., "Performance drivers of shipping loans : An empirical investigation", International Journal of Production Economics, 171, pp.438~452 (2016)
- 남현정, "Default Risk and Firm Value of Shipping & Logistics Firms in Korea", The Asian Journal of Shipping and Logistics, 33(2), pp.61~65 (2017), 한국해운물류학회
- Noble, W. S., "What is a support vector machine?", Nature biotechnology, 24(12), pp.1565~1567 (2006)
- Ohlson, J. A., "Financial ratios and the probabilistic prediction of bankruptcy", Journal of Accounting Research, pp.109~131 (1980)[DOI]
- Park, S., "Empirics of Korean Shipping Companies’Default Predictions", Risks, 9(9), pp.1~17 (2021)
- Shin, S. H., "Lessons from bankruptcy of Hanjin Shipping Company in chartering", Maritime Policy & Management, 46(2), pp.136~155 (2019)
- Stopford, M., "Maritime Economics", pp.93~133 (2008), Routledge
- Tian, Y., "Recent advances on support vector machines research", Technological and Economic Development of Economy, 18(1), pp.5~33 (2012)
- Zmijewski, Mark E., "Methodological issues related to the estimation of financial distress prediction models", Journal of Accounting Research, pp.59~82 (1984)