• 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.

• 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 Internet, Broadcasting and Communication
• /
• 제15권3호
• /
• pp.58-65
• /
• 2023

Bankruptcy is a significant risk for start-up companies, but with the help of cutting-edge artificial intelligence technology, we can now predict bankruptcy with detailed explanations. In this paper, we implemented the Category Boosting algorithm following data cleaning and editing using OpenRefine. We further explained our model using the Shapash library, incorporating domain knowledge. By leveraging the 5C's credit domain knowledge, financial analysts in banks or investors can utilize the detailed results provided by our model to enhance their decision-making processes, even without extensive knowledge about AI. This empowers investors to identify potential bankruptcy risks in their business models, enabling them to make necessary improvements or reconsider their ventures before proceeding. As a result, our model serves as a "glass-box" model, allowing end-users to understand which specific financial indicators contribute to the prediction of bankruptcy. This transparency enhances trust and provides valuable insights for decision-makers in mitigating bankruptcy risks.

• 기술혁신학회지
• /
• 제9권2호
• /
• pp.304-324
• /
• 2006

재무분석가들은 기업의 파산에 양향을 미치는 예측변수를 탐색하기 위해서 상당한 연구가 수행되어 왔다. 그러나 기술지향적 중소벤처기업은 일반적으로 역사적 재무자료가 부족하고, 기술경쟁력 수준에 따라 잠재적인 고성장과 고위험이 존재한다. 본 논문에서는 재무자료 대신에 기술력평가 자료를 이용하여 파산을 예측하기 위해서 파산예측 판별모형을 제안하였고, 모형의 정분류율을 통해서 예측력을 검증하기 위해서 교차타당성방법, 최대사후확률방법 등을 사용하였다. 분석결과 중소 벤처기업의 파산예측모형으로 선형판별모형이 로지스틱판별모형보다 적합한 모형이고, 표본자료에 대한 정분류율 추정은 약 69% 이고 정분류율 예측은 약 67% 가 될 것으로 기대된다.

• 한국IT서비스학회지
• /
• 제14권4호
• /
• pp.121-135
• /
• 2015

Ensemble classification is to utilize multiple classifiers instead of using a single classifier. Recently ensemble classifiers have attracted much attention in data mining community. Ensemble learning techniques has been proved to be very useful for improving the prediction accuracy. Bagging, boosting and random subspace are the most popular ensemble methods. In random subspace, each base classifier is trained on a randomly chosen feature subspace of the original feature space. The outputs of different base classifiers are aggregated together usually by a simple majority vote. In this study, we applied the random subspace method to the bankruptcy problem. Moreover, we proposed a method for optimizing the random subspace ensemble. The genetic algorithm was used to optimize classifier subset of random subspace ensemble for bankruptcy prediction. This paper applied the proposed genetic algorithm based random subspace ensemble model to the bankruptcy prediction problem using a real data set and compared it with other models. Experimental results showed the proposed model outperformed the other models.

• 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.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1996년도 추계학술대회발표논문집; 고려대학교, 서울; 26 Oct. 1996
• /
• pp.203-206
• /
• 1996

Prediction of firm bankruptcy have been extensively studied in accounting, as all stockholders in a firm have a vested interest in monitoring its financial performance. The objective of this paper is to develop the hybrid models for bankruptcy prediction. The proposed hybrid models are two phase. Phase one are (a) DA-assisted neural network, (b) Logit-assisted neural network, and (c) Genetic-assisted neural network. And, phase two are (a) DA-assisted Case based reasoning, and (b) Genetic-assisted Case based reasoning. In the variables selection, We are focusing on three alternative methods - linear discriminant analysis, logit analysis and genetic algorithms - that can be used empirically select predictors for hybrid model in bankruptcy prediction. Empirical results using Korean medium-sized firms data show that hybrid models are very promising neural network models and case based reasoning for bankruptcy prediction in terms of predictive accuracy and adaptability.

• 한국컴퓨터정보학회논문지
• /
• 제19권10호
• /
• pp.125-133
• /
• 2014

본 논문에서는 호텔경영을 위한 인공신경망 기반의 부도예측 모형을 개발한다. 부도예측 모형은 호텔에서 관리하는 사업장의 사업성과 이터를 바탕으로 부도 가능성을 평가하여 호텔 전체사업의 부도를 예측하는 특징을 가진다. 부도예측을 위한 전통적인 통계기법은 다변량 판별분석이나 로짓분석 등이 있는데, 본연구는 이들보다 우수한 예측정확성을 갖는 인공신경망 기법을 이용해서 연구를 진행하였다. 이를 위해 우선 우수기업 100개와 도산기업 100개를 선정하여 전체 실험데이터를 구성하고, 뉴로쉘이라는 인공신경망 도구를 이용하여 부도예측모형을 구성하였다. 본 모형 설계와 실험은 서비스드 레지던스 호텔에서 관리하는 각 브랜치의 부도예측과 재무건전성을 판단하기에 효율성이 높아 호텔 경영의 의사결정에 많은 도움이 될 것이다.

• Journal of information and communication convergence engineering
• /
• 제19권4호
• /
• pp.228-233
• /
• 2021

In this study, we analyze the credit information (loan, delinquency information, etc.) of individual business owners to generate voluminous training data to establish a bankruptcy prediction model through a partial synthetic training technique. Furthermore, we evaluate the prediction performance of the newly generated data compared to the actual data. When using conditional tabular generative adversarial networks (CTGAN)-based training data generated by the experimental results (a logistic regression task), the recall is improved by 1.75 times compared to that obtained using the actual data. The probability that both the actual and generated data are sampled over an identical distribution is verified to be much higher than 80%. Providing artificial intelligence training data through data synthesis in the fields of credit rating and default risk prediction of individual businesses, which have not been relatively active in research, promotes further in-depth research efforts focused on utilizing such methods.