DOI QR코드

DOI QR Code

Bankruptcy Forecasting Model using AdaBoost: A Focus on Construction Companies

적응형 부스팅을 이용한 파산 예측 모형: 건설업을 중심으로

  • Heo, Junyoung (Department of Computer Engineering, Hansung University) ;
  • Yang, Jin Yong (Department of Computer Engineering, Hansung University)
  • 허준영 (한성대학교 컴퓨터공학과) ;
  • 양진용 (한성대학교 컴퓨터공학과)
  • Received : 2013.09.02
  • Accepted : 2014.01.08
  • Published : 2014.03.28

Abstract

According to the 2013 construction market outlook report, the liquidation of construction companies is expected to continue due to the ongoing residential construction recession. Bankruptcies of construction companies have a greater social impact compared to other industries. However, due to the different nature of the capital structure and debt-to-equity ratio, it is more difficult to forecast construction companies' bankruptcies than that of companies in other industries. The construction industry operates on greater leverage, with high debt-to-equity ratios, and project cash flow focused on the second half. The economic cycle greatly influences construction companies. Therefore, downturns tend to rapidly increase the bankruptcy rates of construction companies. High leverage, coupled with increased bankruptcy rates, could lead to greater burdens on banks providing loans to construction companies. Nevertheless, the bankruptcy prediction model concentrated mainly on financial institutions, with rare construction-specific studies. The bankruptcy prediction model based on corporate finance data has been studied for some time in various ways. However, the model is intended for all companies in general, and it may not be appropriate for forecasting bankruptcies of construction companies, who typically have high liquidity risks. The construction industry is capital-intensive, operates on long timelines with large-scale investment projects, and has comparatively longer payback periods than in other industries. With its unique capital structure, it can be difficult to apply a model used to judge the financial risk of companies in general to those in the construction industry. Diverse studies of bankruptcy forecasting models based on a company's financial statements have been conducted for many years. The subjects of the model, however, were general firms, and the models may not be proper for accurately forecasting companies with disproportionately large liquidity risks, such as construction companies. The construction industry is capital-intensive, requiring significant investments in long-term projects, therefore to realize returns from the investment. The unique capital structure means that the same criteria used for other industries cannot be applied to effectively evaluate financial risk for construction firms. Altman Z-score was first published in 1968, and is commonly used as a bankruptcy forecasting model. It forecasts the likelihood of a company going bankrupt by using a simple formula, classifying the results into three categories, and evaluating the corporate status as dangerous, moderate, or safe. When a company falls into the "dangerous" category, it has a high likelihood of bankruptcy within two years, while those in the "safe" category have a low likelihood of bankruptcy. For companies in the "moderate" category, it is difficult to forecast the risk. Many of the construction firm cases in this study fell in the "moderate" category, which made it difficult to forecast their risk. Along with the development of machine learning using computers, recent studies of corporate bankruptcy forecasting have used this technology. Pattern recognition, a representative application area in machine learning, is applied to forecasting corporate bankruptcy, with patterns analyzed based on a company's financial information, and then judged as to whether the pattern belongs to the bankruptcy risk group or the safe group. The representative machine learning models previously used in bankruptcy forecasting are Artificial Neural Networks, Adaptive Boosting (AdaBoost) and, the Support Vector Machine (SVM). There are also many hybrid studies combining these models. Existing studies using the traditional Z-Score technique or bankruptcy prediction using machine learning focus on companies in non-specific industries. Therefore, the industry-specific characteristics of companies are not considered. In this paper, we confirm that adaptive boosting (AdaBoost) is the most appropriate forecasting model for construction companies by based on company size. We classified construction companies into three groups - large, medium, and small based on the company's capital. We analyzed the predictive ability of AdaBoost for each group of companies. The experimental results showed that AdaBoost has more predictive ability than the other models, especially for the group of large companies with capital of more than 50 billion won.

2013년 건설 경기 전망 보고서에 따르면 주택건설경기 침체 상황의 지속으로 건설 기업의 유동성 위기가 지속될 것으로 전망된다. 건설업은 파산으로 인한 사회적 파급효과가 다른 산업에 비해 큰 편이지만, 업종의 특성상 다른 산업과는 상이한 자본구조와 부채비율, 현금흐름을 가지고 있어서 기업의 파산 예측이 더 어려운 측면이 있다. 건설업은 레버리지가 큰 산업으로 부채비율이 매우 높은 업종이며 현금흐름이 프로젝트 후반부에 집중되는 특성이 있다. 그리고 경기사이클에 따른 부침이 매우 심하여 경기하강국면에선 파산이 급증하는 양상을 보인다. 건설업이 레버리지 산업인 이상 건설업체의 파산율 증가는 여신을 공여한 은행에 큰 부담으로 작용한다. 그럼에도 그간의 파산예측모델이 주로 금융기관에 집중되어 왔고 건설업종에 특화된 연구는 드물었다. 기업의 재무 자료를 바탕으로 한 파산 예측 모델에 대한 연구는 오래 전부터 다양하게 진행되었다. 하지만, 일반적인 기업 전체를 대상으로 하는 모델이기 때문에, 건설 기업과 같이 유동성이 큰 기업의 예측에는 적절하지 못할 수 있다. 건설 산업은 오랜 사업 기간과 대규모 투자, 그리고 투자금 회수가 오래 걸리는 특징을 갖는 자본 집약 산업이다. 이로 인해 다른 산업과는 상이한 자본 구조를 갖기 마련이고, 다른 산업의 기업 재무 위험도를 판단하는 기준과 동일한 적용이 곤란할 수 있다. 최근에는 기계 학습을 바탕으로 한 기업 파산 예측 연구가 활발하다. 기계 학습의 대표적 응용 분야인 패턴 인식을 기업의 파산 예측에 응용한 것이다. 기업의 재무 정보를 바탕으로 패턴을 작성하고 이 패턴이 파산 위험 군에 속하는지 안전한 군에 속하는지 판단하는 것이다. 전통적인 Z-Score와 기계 학습을 이용한 파산 예측과 같은 기존 연구들은 특정 산업 분야가 아닌 일반적인 기업을 대상으로 하기 때문에 기업들의 특성을 전혀 고려하고 있지 못하다. 본 논문에서는 건설 기업을 규모에 따라 각 기법들의 예측 능력을 비교하여 적응형 부스팅이 가장 우수함을 확인하였다. 본 논문은 건설 기업을 자본금 규모에 따라 세 등급으로 분류하고 각각에 대해 적응형 부스팅의 예측력을 분석하였다. 실험 결과 적응형 부스팅이 다른 기법에 비해 예측 결과가 좋았고, 특히 자본금 규모가 500억 이상인 기업의 경우 아주 우수한 결과를 보였다.

Keywords

References

  1. Alfaro, E., N. Garcia, M. Gamez, and D. Elizondo, "Bankruptcy forecasting: An empirical comparison of AdaBoost and neural networks," Decision Support Systems, Vol.45, No.1(2008), 110-122. https://doi.org/10.1016/j.dss.2007.12.002
  2. Altman, E. I., "Predicting financial distress ofcompanies: revisiting the Z-score and ZETA models," Stern School of Business, New York University (2000), 9-12.
  3. CERIK(Construction Economy Research Institute of Korea), 2013 Construction Market Outlook Report, 2012.
  4. Freund, Y. and R. E. Schapire, "A desiciontheoretic generalization of on-line learning and an application to boosting," Computational learning theory, Vol. 904(1995), 23-37. https://doi.org/10.1007/3-540-59119-2_166
  5. Kim, M. J., "Ensemble Learning for Solving Data Imbalance in Bankruptcy Prediction," Journal of Intelligence and Information Systems, Vol.15, No.3(2009), 1-15.
  6. Min, J. H. and Y. C. Lee, "Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters," Expert Systems with Applications Vol.28, No.4 (2005), 603-614. https://doi.org/10.1016/j.eswa.2004.12.008
  7. NICE, Credit Information Service, Available at http://www.nicednb.com (Accessed 10 March, 2014).
  8. Shin, K. S., T. S. Lee, and H. J. Kim, "An application of support vector machines in bankruptcy prediction model," Expert Systems with Applications, Vol.28, No.1(2005), 127-135. https://doi.org/10.1016/j.eswa.2004.08.009
  9. Shin, T. S. and T. H. Hong, "Corporate Credit Rating based on Bankruptcy Probability Using AdaBoost Algorithm-based Support Vector Machine," Journal of Intelligence and Information Systems, Vol.17, No. 3(2011), 25-41.
  10. Sun, J., B. Liao, and H. Li, "AdaBoost and Bagging Ensemble Approaches with Neural Network as Base Learner for Financial Distress Prediction of Chinese Construction and Real Estate Companies," Recent Patents on Computer Science, Vol.2013, No.6(2013), 47-59.
  11. Tae, C. W. and K. S. Shin, "GA-based Normalization Approach in Back-propagation Neural Network for Bankruptcy Prediction Modeling," Journal of Intelligence and Information Systems, Vol.16, No.3(2010), 1-14.
  12. Verikas, A, Z. Kalsyte, M. Becauskiene, and A. Gelzinis, "Hybrid and ensemble-based soft computing techniques in bankruptcy prediction: a survey," Soft Computing Vol.14, No.9 (2010), 995-1010. https://doi.org/10.1007/s00500-009-0490-5
  13. Wilson, R. L. and R. Sharda, "Bankruptcy prediction using neural networks," Decision Support Systems Vol.11, No.5(1994), 545-557. https://doi.org/10.1016/0167-9236(94)90024-8

Cited by

  1. Predicting Corporate Bankruptcy using Simulated Annealing-based Random Fores vol.24, pp.4, 2014, https://doi.org/10.13088/jiis.2018.24.4.155