• Journal of Information Technology Applications and Management
• /
• 제20권4호
• /
• pp.221-234
• /
• 2013

In this paper, we report bankruptcy risk level forecasting result for automobile parts manufacturing industry. With the premise that upstream supply risk and downstream demand risk could impact on automobile parts industry bankruptcy level in advance, we draw upon industry input-output table to use the economic indicators which could reflect the extent of supply and demand risk of the automobile parts industry. To verify the validity of each economic indicator, we applied simple linear regression for each indicators by varying the time lag from one month (t-1) to 12 months (t-12). Finally, with the valid indicators obtained through the simple regressions, the composition of valid economic indicators are derived using stepwise linear regression. Using the monthly automobile parts industry bankruptcy frequency data accumulated during the 5 years, R-square values of the stepwise linear regression results are 68.7%, 91.5%, 85.3% for the 3, 6, 9 months time lag cases each respectively. The computational testing results verifies the effectiveness of our approach in forecasting bankruptcy risk forecasting of the automobile parts industry.

• 산업융합연구
• /
• 제15권1호
• /
• pp.17-32
• /
• 2017

The purpose of this study is to evaluate financial models that can predict corporate bankruptcy with diverse studies on evaluation models. The study uses discriminant analysis, logistic model, decision tree, neural networks as analyses tools with 18 input variables as major financial factors. The study found meaningful variables such as current ratio, return on investment, ordinary income to total assets, total debt turn over rate, interest expenses to sales, net working capital to total assets and it also found that prediction performance of suggested method is a bit low compared to that in literature review. It is because the studies in the past uses the data set on the listed companies or companies audited from outside. And this study uses data on the companies whose credibility is not verified enough. Another finding is that models based on decision tree analysis and discriminant analysis showed the highest performance among many bankruptcy forecasting models.

• 경영과학
• /
• 제33권3호
• /
• pp.105-117
• /
• 2016

In this paper, we present empirical testing result to examine the validity of inbound supply and outbound demand risk factors in the sense of early predicting the firm's bankruptcy risk level. The risk factors are drawn from industry uncertainty attributes categorized as uncertainties of input market (inbound supply), and product market (outbound demand). On the basis of input-output table, industry level inbound and outbound sectors are identified to formalize supply chain structures, relevant inbound and outbound uncertainty attributes and corresponding risk factors. Subsequently, publicly available macro-economic indicators are used to appropriately quantify these risk factors. Total 68 industry level bankruptcy risk forecasting results are presented with the average R-square scores of between 53.4% and 37.1% with varying time lag. The findings offers useful insights to incorporate supply chain risk to the body of firm's bankruptcy risk level prediction literature.

• 지능정보연구
• /
• 제20권1호
• /
• pp.35-48
• /
• 2014

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.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1996년도 춘계공동학술대회논문집; 공군사관학교, 청주; 26-27 Apr. 1996
• /
• pp.733-736
• /
• 1996

Neural Network(NN) is known to be suitable for forecasting corporate bankruptcy because of discriminant capability. Bankruptcy prediciton on NN by now has mostly been studied based on financial indices at specific point of time. However, the financial profile of corporates fluctuates within a certain range with the elapse of time. Besides, we need a lot of data of different bankrupt types in order to apply NN for better bankruptcy prediciton. Therefore, we have decided to focus on textiles and clothing industries for bankruptcy prediction with limited data. One part of the collected data was used for training and calibration, and the other was used for verification. The model makes a learning with extended data from financial indices at specific point of time. The trained model has been tested and we could get a high hitting ratio relatively.

• 경영과학
• /
• 제14권2호
• /
• pp.91-111
• /
• 1997

Neural Network(NN) is known to be suitable for forecasting corporate bankruptcy because of discriminant capability. Bandkruptcy prediction on NN by now has mostly been studied based on financial indices at specific point of time. However, the financial profile of corporates fluctuates within a certain range with the elapse of time. Besides, we need a lot of data of different bankrupt types in order to apply NN for better bankruptcy prediction. Therefore, We have decided to focus on textile and clothing industries for bankruptcy prediction with limited data. One part of the collected data was used for training and calibration, and the other was used for verification. The model makes a learning with extended data from financial indices at specific point of time. The trained model has been tested and we could get a high hitting ratio relatively.

• 한국경영과학회지
• /
• 제14권2호
• /
• pp.91-91
• /
• 1989

Neural Network(NN) is known to be suitable for forecasting corporate bankruptcy because of discriminant capability. Bandkruptcy prediction on NN by now has mostly been studied based on financial indices at specific point of time. However, the financial profile of corporates fluctuates within a certain range with the elapse of time. Besides, we need a lot of data of different bankrupt types in order to apply NN for better bankruptcy prediction. Therefore, We have decided to focus on textile and clothing industries for bankruptcy prediction with limited data. One part of the collected data was used for training and calibration, and the other was used for verification. The model makes a learning with extended data from financial indices at specific point of time. The trained model has been tested and we could get a high hitting ratio relatively.

• International journal of advanced smart convergence
• /
• 제12권1호
• /
• pp.53-58
• /
• 2023

With the fast development of artificial intelligence day by day, users are demanding explanations about the results of algorithms and want to know what parameters influence the results. In this paper, we propose a model for bankruptcy prediction with interpretability using the SHAP framework. SHAP (SHAPley Additive exPlanations) is framework that gives a visualized result that can be used for explanation and interpretation of machine learning models. As a result, we can describe which features are important for the result of our deep learning model. SHAP framework Force plot result gives us top features which are mainly reflecting overall model score. Even though Fully Connected Neural Networks are a "black box" model, Shapley values help us to alleviate the "black box" problem. FCNNs perform well with complex dataset with more than 60 financial ratios. Combined with SHAP framework, we create an effective model with understandable interpretation. Bankruptcy is a rare event, then we avoid imbalanced dataset problem with the help of SMOTE. SMOTE is one of the oversampling technique that resulting synthetic samples are generated for the minority class. It uses K-nearest neighbors algorithm for line connecting method in order to producing examples. We expect our model results assist financial analysts who are interested in forecasting bankruptcy prediction of companies in detail.

• 지능정보연구
• /
• 제23권3호
• /
• pp.139-153
• /
• 2017

기업의 부도는 이해관계자들뿐 아니라 사회에도 경제적으로 큰 손실을 야기한다. 따라서 기업부도예측은 경영학 연구에 있어 중요한 연구주제 중 하나로 다뤄져 왔다. 기존의 연구에서는 부도 예측을 위해 다변량판별분석, 로짓분석, 신경망분석 등 다양한 방법론을 이용하여 모형의 부도 예측력을 높이고 과적합의 문제를 해결하고자 시도하였다. 하지만 기존의 연구들이 시간적 요소를 고려하지 않아 발생할 수 있는 문제점들을 갖고 있음에도 불구하고 부도 예측에 있어서 동적 모형을 이용한 연구는 활발히 진행되고 있지 않으며 따라서 동적 모형을 이용하여 부도예측모형이 더욱 개선될 여지가 있다는 점을 확인할 수 있었다. 이에 본 연구에서는 RNN(Recurrent Neural Network)을 이용하여 시계열 재무 데이터의 동적 변화를 반영한 모형을 만들었으며 기존의 부도예측모형들과의 비교분석을 통해 부도 예측력의 향상에 도움이 된다는 것을 확인할 수 있었다. 모형의 유용성을 검증하기 위해 KIS Value의 재무 데이터를 이용하여 실험을 수행하였고 비교모형으로는 다변량판별분석, 로짓분석, SVM, 인공신경망을 선정하였다. 실험 결과 제안된 모형이 비교 모형에 비해 우수한 예측력을 보이는 것으로 나타났다. 따라서 본 연구는 변수들의 변화를 포착하는 동적 모형을 부도예측에 새롭게 제안하여 부도예측 연구의 발전에 기여할 수 있을 것으로 기대된다.

• Journal of Information Technology Applications and Management
• /
• 제22권2호
• /
• pp.201-217
• /
• 2015

In this paper, we report computational testing result to examine the validity of firm's bankruptcy risk estimation through quantification of supply chain risk. Supply chain risk in this study refers to upstream supply risk and downstream demand risk, To assess the firm's risk affected by supply chain risk, we adopt unit of analysis as industry level. since supply and demand relationships of the firm could be generalized by the industry input-output table and the availability of various valid economic indicators which are chronologically calculated. The research model to estimate firm's risk level is the linear regression model to assess the industry bankruptcy risk estimation of the focal firm's industry with the independent variables which could quantitatively reflect demand and supply risk of the industry. The publicly announced macro economic indicators are selected as the candidate independent variables and validated through empirical testing. To validate our approach, in this paper, we confined our research scope to steel industry sector and its related industry sectors, and implemented the research model. The empirical testing results provide useful insights to further refine the research model as the valid forecasting mechanism to capture firm's future risk estimation more accurately by adopting supply chain industry risk aspect, in conjunction with firm's financial and other managerial factors.