• 한국정보시스템학회:학술대회논문집
• /
• 한국정보시스템학회 2002년도 추계학술대회
• /
• pp.289-312
• /
• 2002

This study suggests the Link weight analysis approach to choose input variables and an integrated model to make more accurate bankruptcy prediction model. the Link weight analysis approach is a method to choose input variables to analyze each input node's link weight which is the absolute value of link weight between an input nodes and a hidden layer. There are the weak-linked neurons elimination method, the strong-linked neurons selection method in the link weight analysis approach. The Integrated Model is a combined type adapting Bagging method that uses the average value of the four models, the optimal weak-linked-neurons elimination method, optimal strong-linked neurons selection method, decision-making tree model, and MDA. As a result, the methods suggested in this study - the optimal strong-linked neurons selection method, the optimal weak-linked neurons elimination method, and the integrated model - show much higher accuracy than MDA and decision making tree model. Especially the integrated model shows much higher accuracy than MDA and decision making tree model and shows slightly higher accuracy than the optimal weak-linked neurons elimination method and the optimal strong-linked neurons selection method.

• 유통과학연구
• /
• 제16권11호
• /
• pp.21-27
• /
• 2018

Purpose - This study investigates the financial ratio of savings banks and the effect of the ratio having influence upon bankruptcy by quantitative empirical analysis of forecast model to give material of better management and objective evidence of management strategy and way of advancement and risk control. Research design, data, and methodology - The author added two growth indexes, three fluidity indexes, five profitability indexes, and four activity indexes CAMEL rating to not only the balance sheets but also the income statement of thirty savings banks that suspended business from 2011 to 2015 and collected fourteen financial ratio indexes. IBMSPSS VER. 21.0 was used. Results - Variables having influence upon bankruptcy forecast models included total asset increase ratio and operating income increase ratio of growth index and sales to account receivable ratio, and tangible equity ratio and liquidity ratio of liquidity ratio. The study selected total asset operating ratio, and earning and expenditure ratio from profitability index, and receivable turnover ratio of activity index. Conclusions - Financial supervising system should be improved and financial consumers should be protected to develop saving bank and to control risk, and information on financial companies should be strengthened.

• 한국정보시스템학회지:정보시스템연구
• /
• 제18권3호
• /
• pp.375-399
• /
• 2009

In this study, we propose a integrated model of logistic regression, artificial neural networks, support vector machines(SVM), with case-based reasoning(CBR). To predict respondents in the direct marketing is the binary classification problem as like bankruptcy prediction, IDS, churn management and so on. To solve the binary problems, we employed logistic regression, artificial neural networks, SVM. and CBR. CBR is a problem-solving technique and shows significant promise for improving the effectiveness of complex and unstructured decision making, and we can obtain excellent results through CBR in this study. Experimental results show that the classification accuracy of integration model using CBR is superior to logistic regression, artificial neural networks and SVM. When we apply the customer response model to predict respondents in the direct marketing, we have to consider from the view point of profit/cost about the misclassification.

• 경영정보학연구
• /
• 제24권4호
• /
• pp.23-40
• /
• 2022

Support Vector Machine(SVM)은 기업부실 예측문제 등 다양한 분야에서 성공적으로 활용되어 왔으나 범주 불균형 문제가 존재하는 경우 다수 범주의 경계영역은 확장되는 반면, 소수 범주의 경계영역은 축소되고 분류 경계선이 소수 범주로 편향되어 분류 성과에 부정적인 영향을 미치는 것으로 보고되고 있다. 본 연구는 범주 불균형 문제에 대한 대칭 마진 SVM(EMSVM)의 한계점을 개선하기 위하여 비대칭 마진 SVM(UMSVM)과 임계점 이동 기법을 결합한 최적화 비대칭 마진 SVM인 OPT-UMSVM을 제안한다. OPT-UMSVM은 소수 범주 방향으로 치우진 분류 경계선을 다수 범주로 재이동함으로써 소수 범주의 민감도를 개선하고 최적화된 분류 성과를 산출함으로써 SVM의 일반화 능력을 향상시키는 장점을 가진다. OPT-UMSVM의 성과 개선 효과를 검증하기 위하여 불균형 비율이 상이한 5개의 표본군을 구성하여 10-fold 교차타당성 검증을 수행한 결과는 다음과 같다. 첫째, 범주 불균형이 미미한 표본에서 UMSVM은 EMSVM의 성과 개선 효과가 미약한 반면, 범주 불균형이 심화된 표본에서 UMSVM은 EMSVM의 성과개선에 크게 공헌하고 있다. 둘째, OPT-UMSVM은 EMSVM 및 기존의 UMSVM과 비교하여 범주 균형 및 범주 불균형 표본 모두에서 보다 우수한 성과를 가지고 있으며, 특히 범주 불균형이 심화된 표본에서 유의적인 성과 차이를 보였다.

• Asia pacific journal of information systems
• /
• 제21권2호
• /
• pp.43-58
• /
• 2011

Support vector machines (SVMs), a machine learning technique, has been applied to not only binary classification problems such as bankruptcy prediction but also multi-class problems such as corporate credit ratings. However, in general, the performance of SVMs can be easily worse than the best alternative model to SVMs according to the selection of predictors, even though SVMs has the distinguishing feature of successfully classifying and predicting in a lot of dichotomous or multi-class problems. For overcoming the weakness of SVMs, this study has proposed an approach for selecting features for multi-class SVMs that utilize the impurity measures of classification trees. For the selection of the input features, we employed the C4.5 and CART algorithms, including the stepwise method of discriminant analysis, which is a well-known method for selecting features. We have built a multi-class SVMs model for credit rating using the above method and presented experimental results with data regarding S&P 500 companies.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.213-216
• /
• 2015

Despite the significant increase of Korean contractors in the international construction market, many SMCCs (Small & Medium Construction Companies) have suffered in the global financial crisis, and some of them have been kicked out of the international market after experiencing huge losses on projects. SMCCs face obstacles in the international market, such as an insufficient ability to gather information and inappropriate management of associated risks, which lead to difficulties in establishing effective business strategies. In other words, making immature decisions without an effective business strategy may cause not only the failure of one project but also the bankruptcy of the SMCC. To overcome this, the research presented herein aims to propose a decision support system for SMCCs, which would screen projects and make a go/no-go decision at the early stages of international projects. The proposed system comprises a double axis: (1) a profit prediction model, which evaluates 10 project properties using an objective methodology based on a historical project performance database and roughly suggests expected profit rate, and (2) a feasibility assessment model, which evaluates 17 project environment factors in a subjective and quantitative methodology based on experience and supervision. Finally, a web-based system is established to enhance the practical usability, which is expected to be a good reference for inexperienced SMCCs to make proper decisions and establish effective business strategies.

• 지능정보연구
• /
• 제29권3호
• /
• pp.361-381
• /
• 2023

기업 부도 예측에 관한 연구는 재무정보를 중심으로 연구되어 왔다. 기업의 재무정보는 분기별로 갱신되기 때문에 실시간으로 기업의 폐업 가능성을 예측하는 데 있어 적시성이 부족하게 되는 문제가 발생한다. 이를 개선하고자 하는 평가 기업에서는 대상 기업의 건전성을 판단하기 위한 재무정보 외의 정보를 활용한 기업의 건전성을 판단하는 방법이 필요하다. 이를 위해 정보 기술의 발달로 기업에 대한 비재무정보 수집이 용이해지면서 기업 부도 예측에 재무정보 외의 추가적인 변수와 여러 가지 방법론을 적용하는 연구가 진행되어 왔으며, 이 중에서도 어떤 변수들이 기업의 부도를 예측하는데 영향을 주는지를 밝히는 것이 중요한 연구 과제가 되었다. 본 연구에서는 전자결제서비스를 이용하는 사업자의 폐업을 예측할 때 비재무정보를 구성하는 전자결제 정보들이 얼마나 영향을 미치는지를 살펴보았으며, 재무정보와 비재무정보 결합에 따른 폐업 예측 정확도 차이를 살펴보았다. 구체적으로, 재무정보 모형과 비재무정보 모형, 그리고 이를 결합한 모형으로 구성된 세 가지 연구 모형을 설계하였으며 Multi Layer Perceptron(MLP) 알고리즘을 포함한 여섯 가지 알고리즘으로 폐업 예측 정확도를 확인하였다. 재무정보와 비재무정보를 결합한 모형이 가장 높은 예측 정확도를 보였으며, 그 다음으로는 비재무정보 모형, 재무정보 모형의 순서로 예측 정확도가 확인되었다. 알고리즘별 폐업 예측 정확도는 여섯 가지의 알고리즘 중 XGBoost가 가장 높은 예측 정확도를 보였다. 사업자의 폐업 예측에 활용된 전체 87개의 변수를 대상으로 상대적 중요도를 살펴본 결과 폐업 예측에 중요하게 영향을 미친 변수는 상위 20개 중 70% 이상이 비재무정보인 것으로 확인되었다. 이를 통해 비재무정보의 전자결제 정보가 사업자의 폐업을 예측하는 중요한 변수임을 확인하였으며, 비재무 정보가 재무정보의 대안적 정보로서 활용할 수 있는 가능성 역시 살펴볼 수 있었다. 본 연구를 기반으로 사업자의 폐업을 예측할 수 있는 정보로서 비재무정보의 수집과 활용에 대한 중요성을 인식하고 기업의 의사결정에 활용할 수 있는 방안에 대해서도 다루었다.

• Journal of Information Technology Applications and Management
• /
• 제11권1호
• /
• pp.117-135
• /
• 2004

Since human decision making behavior is likely to follow nonlinear strategy, it is conjectured that the human decision making behavior can be modeled better by nonlinear models than by linear models. All that linear models can do is to approximate rather than model the decision behavior. This study attempts to test this conjecture by analyzing human decision making behavior and combining the results of the analysis with predictive performance of both linear models and nonlinear models. In this way, this study can examine the relationship between the predictive performance of models and the existence of valid nonlinear strategy in decision making behavior. This study finds that the existence of nonlinear strategy in decision making behavior is highly correlated with the validity of the decision (or the human experts). The second finding concerns the significant correlations between the model performance and the existence of valid nonlinear strategy which is detected by Lens Model. The third finding is that as stronger the valid nonlinear strategy becomes, the better nonlinear models predict significantly than linear models. The results of this study bring an important concept, validity of nonlinear strategy, to modeling human experts. The inclusion of the concept indicates that the prior analysis of human judgement may lead to the selection of proper modeling algorithm. In addition, lens Model Analysis is proved to be useful in examining the valid nonlinearity in human decision behavior.

• 한국경영과학회지
• /
• 제26권4호
• /
• pp.55-70
• /
• 2001

Artificial neural network(ANN) models have been widely used for the classification problems in business such as bankruptcy prediction, credit evaluation, etc. Although the application of ANN to classification of consumers＇ choice behavior is a promising research area, there have been only a few researches. In general, most of the researches have reported that the classification performance of the ANN models were better than conventional statistical model Because the survey data on consumer behavior may include much noise and missing data, ANN model will be more robust than conventional statistical models welch need various assumptions. The purpose of this paper is to study the potential of the ANN model for forecasting consumers＇ choice behavior based on survey data. The data was collected by questionnaires to the shoppers of department stores and discount stores. Then the correct classification rates of the ANN models for the training and test sample with that of multiple discriminant analysis(MDA) and logistic regression(Logit) model. The performance of the ANN models were betted than the performance of the MDA and Logit model with respect to correct classification rate. By using input variables identified as significant in the stepwise MDA, the performance of the ANN models were improved.

• 한국IT서비스학회지
• /
• 제18권2호
• /
• pp.37-54
• /
• 2019

The purpose of this study is to present an evaluation model to measure the clarification level of stakeholder requirements of public sector software projects in the Republic of Korea. We tried to grasp the quality of proposal request through evaluation model. It also examines the impact of the level of stakeholder requirements on the level of system requirements. To do this, we analyzed existing research models and related standards related to business requirements and stakeholder requirements, and constructed evaluation models for the system operation concept documents in the ISO/IEC/IEEE 29148. The system operation concept document is a document prepared by organizing the requirements of stakeholders in the organization and sharing the intention of the organization. The evaluation model proposed in this study focuses on evaluating whether the contents related to the system operation concept are faithfully written in the request for proposal. The evaluation items consisted of three items: 'organization status', 'desired changes', and 'operational constraints'. The sample extracted 217 RFPs in the national procurement system. As a result of the analysis, the evaluation model proved to be valid and the internal consistency was maintained. The level of system operation concept was very low, and it was also found to affect the quality of system requirements. It is more important to clearly write stakeholders' requirements than the functional requirements. we propose a news classification methods for sentiment analysis that is effective for bankruptcy prediction model.