• 한국IT서비스학회지
• /
• 제18권1호
• /
• pp.187-200
• /
• 2019

Bankruptcy prediction model is an issue that has consistently interested in various fields. Recently, as technology for dealing with unstructured data has been developed, researches applied to business model prediction through text mining have been activated, and studies using this method are also increasing in bankruptcy prediction. Especially, it is actively trying to improve bankruptcy prediction by analyzing news data dealing with the external environment of the corporation. However, there has been a lack of study on which news is effective in bankruptcy prediction in real-time mass-produced news. The purpose of this study was to evaluate the high impact news on bankruptcy prediction. Therefore, we classify news according to type, collection period, and analyzed the impact on bankruptcy prediction based on sentiment analysis. As a result, artificial neural network was most effective among the algorithms used, and commentary news type was most effective in bankruptcy prediction. Column and straight type news were also significant, but photo type news was not significant. In the news by collection period, news for 4 months before the bankruptcy was most effective in bankruptcy prediction. In this study, we propose a news classification methods for sentiment analysis that is effective for bankruptcy prediction model.

• Asian Journal of Business Environment
• /
• 제11권2호
• /
• pp.27-38
• /
• 2021

Purpose: The study mainly investigates bankruptcy risk and income smoothing tendency of Non-Banking Financial Institutions (NBFIs) in Bangladesh. External parties of NBFIs take investment decisions based on financial reports. Stable and predictable income is one of their preference. On the other hand, poor income is one of the signs of NBFIs having bankruptcy risk. Hence the study tries to find whether the NBFIs having bankruptcy are involved in income smoothing or not. Research design, data and methodology: Data were collected from the annual report of twenty-two listed NBFIs in Bangladesh. Data from 2013 to 2017 were used. Altman's Z score and Eckel's model are used to detecting bankruptcy risk and income smoothing respectively. Results: Result implies that most of the NBFIs which have bankruptcy risk are not involved in income smoothing. Therefore, NBFIs which has bankruptcy risk are involved less with income smoothing. Conclusions: The present study revealed that most of the listed NBFIs in Bangladesh are facing bankruptcy risk. They didn't use any fraudulent technique to show smooth income. The findings will help the investor to take an investment decision on NBFIs in Bangladesh. It will convey signals to the stock market in Bangladesh.

• 지능정보연구
• /
• 제21권3호
• /
• pp.79-99
• /
• 2015

부도 예측은 회계와 재무 분야에서 꾸준히 연구되고 있는 분야이다. 초기에는 주로 다중판별분석(multiple discriminant analysis)와 로짓 분석(logit analysis)과 같은 통계적 방법을 이용하였으나, 1990년대 이후에는 경영 분야의 분류 문제를 위해 많은 연구자들이 인공신경망(back-propagation neural network), 사계기반추론(case-based reasoning), 서포트 벡터 머신(support vector machine) 등과 같은 인공지능을 통한 접근법을 이용하여 통계적 방법보다 분류 성과 측면에서 우수함을 입증해왔다. 기존의 기업의 부도에 관한 연구에서 많은 연구자들이 재무비율을 이용하여 부도 예측 모형을 구축하는 것에 초점을 맞추어왔다. 부도예측에 관한 연구가 꾸준히 진행되고 있는 반면, 부도의 세부적인 유형을 예측하여 제시하는 것에 대한 연구는 미흡한 실정이었다. 따라서 본 연구에서는 수익성, 안정성, 활동성 지표를 중심으로 국내 비외감 건설업 기업들의 부도 여부뿐만 아니라 부도의 세부적인 유형까지 예측 가능한 모형을 개발하고자 한다. 본 연구에서는 부도 유형을 예측하기 위해 두 개의 인공신경망 모형을 결합한 하이브리드 접근법을 제안하였다. 첫 번째 인공신경망 모형은 부도예측을 위한 역전파 인공신경망을 이용한 모형이며, 두 번째 인공신경망 모형은 부도 데이터를 몇 개의 유형으로 분류하는 자기조직화지도(self-organizing map)을 이용한 모형이다. 실험 결과를 통해 정의된 5개의 부도 유형인 심각한 부도(severe bankruptcy), 안정성 부족(lack of stability), 활동성 부족(lack of activity), 수익성 부족(lack of profitability), 회생 가능한 부도(recoverable bankruptcy)는 재무 비율에 따라 유형별로 상이한 특성을 갖는 것을 확인할 수 있었다. 본 연구 결과를 통해 신용 평가 분야의 연구자와 실무자들이 기업의 부도의 유형에 대한 유용한 정보를 얻을 것으로 기대한다.

• 한국병원경영학회지
• /
• 제6권2호
• /
• pp.22-36
• /
• 2001

The hospital bankruptcy rate is increasing, therefore it is very important to predict the bankruptcy using the existing hospital management information. The hospital bankruptcy is often measured in year intervals, called grouped duration data, not by the continuous time elapsed to the bankruptcy. This study introduces a hierarchical generalized linear model(HGLM) for analysis of hospital bankruptcy data. The hazard function for each hospital may be influenced by unobservable latent variables, and these unknown variables are usually termed as random effects or frailties which explain correlations among repeated measures of the same hospital and describe individual heterogeneities of hospitals. Practically, the data of twenty bankrupt and sixty profitable hospitals were collected for five years, and were fitted to HGLM. The results were compared with those of the logit model. While the logit model resulted only in the effects of explanatory variables on the bankruptcy status at specific period, the HGLM showed variables with significant effects over all observed years. It is concluded that the HGLM with a fixed ratio and a period of total asset turnrounds was justified, and could find significant within and between hospital variations.

• 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.

• 산업경영시스템학회지
• /
• 제45권2호
• /
• pp.65-76
• /
• 2022

Recently, not only traditional statistical techniques but also machine learning algorithms have been used to make more accurate bankruptcy predictions. But the insolvency rate of companies dealing with financial institutions is very low, resulting in a data imbalance problem. In particular, since data imbalance negatively affects the performance of artificial intelligence models, it is necessary to first perform the data imbalance process. In additional, as artificial intelligence algorithms are advanced for precise decision-making, regulatory pressure related to securing transparency of Artificial Intelligence models is gradually increasing, such as mandating the installation of explanation functions for Artificial Intelligence models. Therefore, this study aims to present guidelines for eXplainable Artificial Intelligence-based corporate bankruptcy prediction methodology applying SMOTE techniques and LIME algorithms to solve a data imbalance problem and model transparency problem in predicting corporate bankruptcy. The implications of this study are as follows. First, it was confirmed that SMOTE can effectively solve the data imbalance issue, a problem that can be easily overlooked in predicting corporate bankruptcy. Second, through the LIME algorithm, the basis for predicting bankruptcy of the machine learning model was visualized, and derive improvement priorities of financial variables that increase the possibility of bankruptcy of companies. Third, the scope of application of the algorithm in future research was expanded by confirming the possibility of using SMOTE and LIME through case application.

• 보건행정학회지
• /
• 제12권3호
• /
• pp.54-76
• /
• 2002

This study investigated how much EVA which evaluate firm's value can explain hospital bankruptcy prediction as a explanatory variable including financial indicators in Korea. In this study, artificial neural network and logit regression which are traditional statistical were used as the model for bankruptcy prediction. Data used in this study were financial and economic value added indicators of 34 bankrupt and -:4 non-bankrupt hospitals from the Database of Korean Health Industry Development Institute. The main results of this study were as follows: First, there was a significant difference between the financial variable model including EVA and the financial variable model excluding EVA in pre-bankruptcy analysis. Second, EVA could forecast bankruptcy hospitals up to 83% by the logistic analysis. Third, the EVA model outperformed the financial model in terms of the predictive power of hospital bankruptcy. Fourth, The predictive power of neural network model of hospital bankruptcy was more powerful than the legit model. After all the result of this study will be useful to future study on EVA to evaluate bankruptcy hospitals forecast.

• 지능정보연구
• /
• 제22권2호
• /
• pp.33-56
• /
• 2016

대부분의 부도 예측에 관한 연구는 재무 변수를 중심으로 통계적 방법 또는 인공지능 기법을 적용하여 부도 예측 모형을 구축하였다. 그러나 재무비율과 같은 회계 정보를 이용한 부도 예측 모형은 재무 제표 결산 시점과 신용평가 시점 간 시차를 고려하지 않을 뿐만 아니라 해당 산업의 경제적 상황과 같은 외부 환경적인 요소를 반영하기 어렵다는 한계점이 존재하였다. 기업의 부도 여부를 예측하기 위해 정량 정보인 재무 변수만을 이용하는 것에 한계가 있음에도 불구하고 정성 정보를 부도 예측 모형에 반영한 연구는 아직 미흡한 실정이다. 본 연구에서는 재무 변수를 이용하는 기존 부도 예측 모형의 성과를 개선하기 위해 빅데이터 기반의 정성 정보를 추가적인 입력 변수로 활용하는 부도 예측 모형을 제안하였다. 제안 모형의 성과 향상은 정성 정보를 예측 모형에 통합시키기에 적합한 형태로 정보의 유형을 변환시킬 수 있는가에 따라 달려있다. 이에 본 연구에서는 정성 정보 처리를 위한 방법으로 빅데이터 분석 기법 중 하나인 텍스트 마이닝(Text Mining)을 활용하였다. 해당 산업과 관련된 경제 뉴스 데이터로부터 경제 상황에 대한 감성 정보를 추출하기 위해 도메인 중심의 감성 어휘 사전을 구축하고, 구축된 어휘 사전을 기반으로 감성 분석(Sentiment Analysis)을 수행하였다. 형태소 분석 등을 포함한 텍스트 전처리 과정을 거쳐 감성 어휘를 추출하고, 각 어휘에 대한 극성 및 감성 점수를 부여하였다. 분석 결과, 전통적 부도 예측 모형에 경제 뉴스 데이터에서 도출한 정성 정보를 반영하는 것은 모형의 성과를 개선하는 것으로 나타났다. 특히, 경제 상황에 대한 부정적 감정이 기업의 부도 여부를 예측하는 데 더욱 효과적임을 알 수 있었다.

• 보건행정학회지
• /
• 제9권2호
• /
• pp.1-20
• /
• 1999

This study was conducted to investigate the predictors of hospital bankruptcy in Korea and to examine the predictive power for 3 types of statistical models of hospital bankruptcy. Data on 17 financial and 4 non-financial indicators of 30 bankrupt and 30 profitable hospitals in 1. 2, and 3 years before bankruptcy were obtained from the hospital performance databank of Korea Institute of Health Services Management. Significant variables were identified through mean comparison of each indicator between bankrupt and profitable hospitals, and the predictive power of statistical models of hospital bankruptcy were compared. The major findings are as follows. 1. Nine out of 21 indicators - fixed ratio, quick ratio, operating profit to total assets, operating profit to gross revenue, normal profit to total assets,normal profit to gross revenue, net profit to gross revenue, inventories turnrounds, and added value per adjusted patient - were found to be significantly predictitive variables in Logit and Probit models. 2. The predicdtive power of discriminant model of hospital bankruptcy in 1. 2, and 3 years before bankruptcy were 85.4, 79.0, and 83.8% respectively. With regard to the predictive power of the Logit model of hospital bankruptcy, they were 82.3, 75.8, and 80.6% respectively, and of the Probit model. 87.1. 80.6, and 88.7% respectively. 3. The predictive power of the Probit model of hospital bankruptcy is better than the other two predictive models.

• 한국정보시스템학회지:정보시스템연구
• /
• 제14권2호
• /
• pp.277-292
• /
• 2005

This paper uses a data mining approach to develop bankruptcy prediction models suitable for traditional (off-line) companies and electronic (on-line) companies. It observes the differences in the composition prediction models between these two types of companies and provides interpretation of bankruptcy classifications. The bankruptcy prediction models revealed the major variables in predicting bankruptcy to be 'cash flow to total assets' and 'gross value-added to net sales' for traditional off-line companies while 'cash flow to liabilities','gross value-added to net sales', and 'current ratio' for electronic companies. The accuracy rates of final prediction models for traditional off-line and electronic companies were found to be $84.7\%\;and\;82.4\%$, respectively. When the model for traditional off-line companies was applied for electronic companies, prediction accuracy dropped significantly in the case of bankruptcy classification (from $70.4\%\;to\;45.2\%$) at the level of a blind guess ($41.30\%$). Therefore, the need for different models for traditional off-line and electronic companies is justified.