더블 앙상블 기법을 이용한 기술사업성평가 기반의 중소기업 부실 예측 연구
Using Double Ensemble Techniques to Predict the Insolvency of SMEs based on Technological Feasibility Assessment Information
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
본 연구에서는 비재무정보인 기술사업성평가 정보와 더블 앙상블 기법을 활용하여 중소기업에 대한 부실예측모형을 구축하는 실험을 진행하였다. 여기에서 분석 데이터셋을 중소기업의 기술유형을기준으로 일반형, 기술개발형, 임가공형으로 구분하고, 분석 데이터에 있는 건전기업과 부실기업의샘플 비율을 동일하게 구성하기 위해 오버샘플링 기법인 SMOTE를 적용하여 데이터 균형화를 실시하였다. 더블 앙상블 기법에 적용할 기본 예측모형을 선별하기 위해 기계학습 알고리즘인 로지스틱회귀, 의사결정나무, 베이지안넷, 인공신경망을 사용하였다. 그 결과 일반형과 임가공형에서는 베이지안넷 모형이 각각 84.65%와 76.98%의 가장 높은 적중률을 기록하였다. 기술개발형에서는 의사결정나무 모형이 73.27%의 가장 높은 적중률을 보여주었다. 이때 일반형에서는 10개, 기술개발형에서는 13개, 임가공형에서는 9개의 중요 변수를 발견하였다. 더블 앙상블 기법에 기술유형별 최고의 성능을 보인 예측모형을 활용할 경우 일반형과 임가공형에서는 적중률이 소폭 상승하였고 기술개발형에서는 다소 높은 적중률 상승 효과를 얻을 수 있었다. 본 연구를 통하여 기술사업성평가 정보만으로도 중소기업의 부실예측이 가능하고 중소기업의 기술유형별로 부실에 영향을 주는 중요변수가 서로 다른 것을 알 수 있었다. 또한 더블 앙상블 기법이 중소기업의 부실예측모형의 적중률 향상에 효과가 있음을 확인하였다.
Abstract
This study aims to build an insolvency prediction model for SMEs using the technological feasibility assessment information and double ensemble techniques. We divided the analysis dataset into general type, technology development type, and toll processing type based on the technology type of SMEs. In addition, we conducted the data balancing technique by applying SMOTE, an oversampling technique, to configure the same ratio of samples of health and insolvent companies for each analysis dataset. We used machine learning algorithms such as logistic regression, decision tree, Bayesian net, and artificial neural network to build the best prediction model for the double ensemble techniques. As a result, the Bayesian net model recorded the highest prediction rates of 84.65% and 76.98%, respectively, in the general and toll processing types. The decision tree model showed the highest prediction rate of 73.27% in the technology development type. We found ten important variables in the general type, thirteen variables in the technology development type, and nine variables in the toll processing type. In the case of applying the double ensemble techniques, we found that the prediction rate slightly increased in the general and toll processing types and obtained a relatively high prediction rate in the technology development type. The results showed that it is possible to predict the insolvency of SMEs only with technological feasibility assessment information, and important variables affecting insolvency were different for each technology type of SME. In addition, the double ensemble techniques effectively improved the prediction rate in the insolvency prediction model for SMEs.
참고문헌 (53)
- 김량형, "데이터마이닝 기법을 이용한 기업부실화 예측 모델 개발과 예측 성능 향상에 관한 연구", Information Systems Review, 18(2), pp.173~198 (2016), 한국경영정보학회[DOI]
- 김소정, "심층신경망의 설명가능성과 하이퍼파라미터 특성에 관한 연구 -중소기업 신용평가를 중심으로-", 중소기업금융연구, 42(1), pp.3~37 (2022), 신용보증기금[DOI]
- 김준경, "국가 예산과정책목표: 1993 년도" (1993), 한국개발연구원
- 김태호, "중소기업의 기술평가등급과 재무성과 간의 연관성", 대한경영학회지, 22(5), pp.2789~2808 (2009), 대한경영학회
- 김희오, "중소기업 정책자금 지원현황 및 차별화 방안: 중소기업진흥공단을 중심으로", 의사결정학연구, 23(2), pp.113~133 (2015)
- 신동령, "기업부실예측에 있어 생산성지표의 유용성에 관한 연구", 생산성연구: 국제융합학술지, 20(2), pp.1~24 (2006), 한국생산성학회
- 옥중경, "유전자 알고리즘 기반의 기업부실예측 통합모형", 지능정보연구, 15(4), pp.99~120 (2009), 한국지능정보시스템학회
- 이재식, "기술금융시장에서의 신뢰성있는 기술평가 정보와 신용평가 정보의 최적화 결합에 관한 연구", 디지털융복합연구, 15(1), pp.199~208 (2017), 한국디지털정책학회[DOI]
- 임형준, "기업 특성별 기술평가정보의 부도예측력 검증:관계형성 여부, 업력, 규모를 중심으로", 한국경제의 분석, 22(1), pp.81~142 (2016), 한국경제의 분석패널
- 임혜진, "거시경제변수가 신용보증 성과에 미치는 영향에 관한 연구 – 신용보증 부실률을 중심으로", 중소기업금융연구, (가을), pp.39~67 (2009)
- 조남옥, "Bankruptcy Prediction Modeling Using Qualitative Information Based on Big Data Analytics", 지능정보연구, 22(2), pp.33~56 (2016), 한국지능정보시스템학회
- 조영삼, "중소기업정책금융의 주요쟁점과 정책과제" (2008), 산업연구원
- 창업진흥원, "창업지원기업 정밀분석" (2019)
- 최정원, "텍스트마이닝 방법론을 활용한 기업 부도 예측 연구", 생산성연구: 국제융합학술지, 29(1), pp.201~228 (2015), 한국생산성학회[DOI]
- 허광복, "중소기업 경영 및 회계 투명성 강화에 대한 제언", Korea Business Review, 16(1), pp.35~50 (2012), 한국경영학회
- Abbasi, A, "Metafraud: A meta-learning framework for detecting financial fraud", MIS Quarterly, 36(4), pp.1293~1327 (2012)
- Ahmeti, L, "The predictive power of financial ratios on bankruptcy: A quantitative study of non-listed limited liability SMEs companies in Sweden", Master, pp.2020
- Altman, E. I, "Financial ratios, discriminant analysis and the prediction of corporate bankruptcy", The Journal of Finance, 23(4), pp.589~609 (1968)
- "Financial and non-financial variables as long-horizon predictors of bankruptcy" (2015)[URL]
- Altman, E. I, "The value of non-financial information in small and medium-sized enterprise risk management", The Journal of Credit Risk, 6(2), pp.1~33 (2010)
- Altman, E. I, "Modelling credit risk for SMEs: Evidence from the US market", Abacus, 43(3), pp.332~357 (2007)
- Barboza, F, "Machine learning models and bankruptcy prediction", Expert Systems with Applications, 83, pp.405~417 (2017)
- Beaver, W. H, "Financial ratios as predictors of failure", Journal of Accounting Research, 4, pp.71~111 (1966)
- Bhimani, A, "The role of financial, macroeconomic, and non-financial information in bank loan default timing prediction", European Accounting Review, 22(4), pp.739~763 (2013)
- Blanco-Oliver, A, "Improving bankruptcy prediction in micro-entities by using nonlinear effects and non-financial variables", Finance a úvěr-Czech Journal of Economics and Finance, 65(2), pp.144~166 (2015)
- Chawla, N. V, "SMOTE: Synthetic minority over-sampling technique", Journal of Artificial Intelligence Research, 16, pp.321~357 (2002)
- Chou, C. H, "Hybrid genetic algorithm and fuzzy clustering for bankruptcy prediction", Applied Soft Computing, 56, pp.298~316 (2017)
- Chuang, C. L, "Application of hybrid case-based reasoning for enhanced performance in bankruptcy prediction", Information Science, 236, pp.174~185 (2013)
- Cultrera, L, "Bankruptcy prediction: The case of Belgian SMEs", Review of Accounting and Finance, 15(1), pp.101~119 (2016)
- Dash, M, "Feature selection for classification", Intelligent Data Analysis, 1(3), pp.131~156 (1997)
- Dimitras, A. I, "A survey of business failures with anemphasis on prediction methods and industrial applications", European Journal of Operational Research, 90(3), pp.487~513 (1996)
- Freund, Y, "A decision-theoretic generalization of on-line learning and an application to boosting", Journal of Computer and System Sciences, 55(1), pp.119~139 (1997)
- Giannopoulos, V, "Predicting SME loan delinquencies during recession using accounting data and SME characteristics: The case of Greece", Intelligent Systems in Accounting, Finance and Management, 26(2), pp.71~82 (2019)
- Grunert, J, "The role of non-financial factors in internal credit ratings", Journal of Banking & Finance, 29(2), pp.509~531 (2005)
- He, H, "Learning from imbalanced data", IEEE Transactions on Knowledge and Data Engineering, 21(9), pp.1263~1284 (2009)
- Kwon, J, "Double Ensemble Approaches to Predicting Firms’ Credit Rating", PACIS 2013 Proceedings, pp.158~ (2013)
- Linna, T, "Insolvency proceedings from a sustainability perspective", International Insolvency Review, 28(2), pp.210~232 (2019)
- Lugovskaya, L, "Predicting default of Russian SMEs on the basis of financial and non-financial variables", Journal of Financial Services Marketing, 14(4), pp.301~313 (2010)
- Mathew, J, "Classification of imbalanced data by oversampling in kernel space of support vector machines", IEEE transactions on neural networks and learning systems, 29(9), pp.4065~4076 (2018)
- Meyer, P. A, "Prediction of bank failures", The Journal of Finance, 25(4), pp.853~868 (1970)
- Mitchell, F, "Problems, challenges and opportunities: the small business as a setting for management accounting research", Management Accounting Research, 11(4), pp.385~390 (2000)
- Naidu, G. P, "Bankruptcy prediction using neural networks", proceedings of 2nd International Conference on Inventive Systems and Control (ICISC), pp.248~251 (2018)
- Ohlson, J.A, "Financial ratios and the probabilistic prediction of bankruptcy", Journal of Accounting Research, 18(1), pp.109~131 (1980)
- Pervan, I, "The relative importance of financial ratios and nonfinancial variables in predicting of insolvency", Croatian Operational Research Review, 4, pp.187~197 (2013)
- Pompe, P. P, "The prediction of bankruptcy of small-and medium-sizedindustrial firms", Journal of Business Venturing, 20(6), pp.847~868 (2005)
- Quinn, M, "Routines in management accounting research: further exploration", Journal of Accounting & Organizational Change, 7(4), pp.337~357 (2011)
- Ropega, J, "The reasons and symptoms of failure in SME", International Advances in Economic Research, 17(4), pp.476~483 (2011)
- Said, A. A, "An empirical investigation of the performance consequences of nonfinancial measures", Journal of Management Accounting Research, 15(1), pp.193~223 (2003)
- Sánchez-Lasheras, F, "A hybrid device for the solution of sampling bias problems in the forecasting of firms’ bankruptcy,”", Expert Systems with Applications, 39(8), pp.7512~7523 (2012)
- Son, H, "Data analytic approach for bankruptcy prediction", Expert Systems with Applications, 138, pp.112816~ (2019)
- Svabova, L, "Business failure prediction for Slovak small and medium-sized companies", Sustainability, 12(11), pp.4572~ (2020)
- Wang, G, "An improved boosting based on feature selection for company bankruptcy prediction", Expert Systems with Applications, 41(5), pp.2353~2361 (2014)
- Witten, I. H, "Data mining: Practical machine learning tools and techniques" (2005), Morgan Kaufmann Publishers
