Combination of Multiple Classification Techniques for Bankruptcy Prediction using Mixed Integer Programming

Ingoo Han,Hongkyu Jo,Taeho Hong,Hyunchul Ahn 한국지능정보시스템학회 2009 한국지능정보시스템학회 학술대회논문집 Vol.2009 No.11

Although many studies demonstrate that one technique outperforms the others for a given data set, there is often no way to tell a priori which of these techniques will be most effective to solve a specific classification problem. Alternatively, it has been suggested that a better approach to classification problem might be to integrate several different forecasting techniques. This study proposes the linearly combining methodology of different classification techniques. The methodology is developed to find the optimal combining weight and compute the weighted-average of different techniques' outputs. The proposed methodology is represented as the form of mixed integer programming. The objective function of proposed combining methodology is to minimize total misclassification cost, which is the weighted-sum of two types of misclassification. To simplify the problem solving process, cutoff value is fixed and threshold function is removed. The form of mixed integer programming is solved with the branch and bound methods. The result showed that proposed methodology classified more accurately than any of techniques individually did. It is confirmed that proposed methodology predicts significantly better than individual techniques and the other combining methods.

Bankruptcy Prediction and the Characteristics of Financial Data

Ingoo Han,Hongkyu Jo 대한산업공학회 1997 대한산업공학회 춘계학술대회논문집 Vol.1997 No.4

Bankruptcy Predictions for Korea Medium-Sized Firms using Neural Networks and Case Based Reasoning

Han, Ingoo,Park, Cheolsoo,Kim, Chulhong 한국경영과학회 1996 한국경영과학회 학술대회논문집 Vol.- No.2

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.

The Hybrid Systems for Credit Rating

Han, Ingoo,Jo, Hongkyu,Shin, Kyung Shik 한국경영과학회 1997 韓國經營科學會誌 Vol.22 No.3

Although numerous studies demonstrate that one technique outperforms the others for a given data set, it is hard to tell a priori which of these techniques will be the most effective to solve a specific problem. It has been suggested that the better approach to classification problem might be to integrate several different forecasting techniques by combining their results. The issues of interest are how to integrate different modeling techniques to increase the predictive performance. This paper proposes the post-model integration method, which tries to find the best combination of the results provided by individual techniques. To get the optimal or near optimal combination or different prediction techniques, Genetic Algorithms (GAs) are applied, which are particularly suitable for multi-parameter optimization problems with an objective function subject to numerous hard and soft constraints. This study applies three individual classification techniques (Discriminant analysis, Logit model and Neural Networks) as base models for the corporate failure prediction. The results of composite predictions are compared with the individual models. Preliminary results suggest that the use of integrated methods improve the performance of business classification.

경영학자들의 경영 자문을 통한 산학협동: 한국경영학회의 경영 자문사업 사례

한인구(Ingoo Han),정양헌(Yanghon Chung),윤상필(Sangpil Yoon) 한국경영학회 2021 Korea Business Review Vol.25 No.4

본 연구에서는 경영학자들이 참여한 한국경영학회의 경영 자문사업 사례를 분석하였다. 이를 통해 전문 컨설턴트 및 경영자문단과 차별화된 경영학자 경영 자문의 특징을 발견하고, 이러한 경영학자의 경영 자문 활동이 하나의 산학협력 방안으로 작용할 수 있도록 추진 방향을 제시하였다. 벤처기업 및 중소기업의 경우 고가 컨설팅회사의 경영 자문을 받는 것은 현실적으로 어렵다. 이에 한국경영학회는 벤처기업 및 중소기업의 경쟁력 제고를 위해 2017~2018년 동안 경영자문위원회를 신설하여 경영 자문사업을 진행하였다. 한국경영학회는 벤처기업협회 및 IBK기업과 협력하여 기관이 선정한 유망 중소기업에 대해, 자문 희망분야 및 현안에 적합한 경영학자를 할당하였다. 자문 기간은 6개월로 경영학자는 주 1회 기업을 방문하여 자문하는 것을 원칙으로 진행하였고, 자문 종료 후 자율적으로 2차 자문을 요청 및 수행할 수 있도록 하였다. 한국경영학회의 경영 자문 사례에서 나타난 경영학자 경영 자문의 특징은 다음과 같다. 기업의 현장 이슈에 관련된 강의 수요가 존재한다는 것과 장기적 관점에서 기업경영 방향에 대한 교육수요에 대응하였다는 점이다. 이 외에도 경영학자는 이론적으로 타당한 경영시스템, 사례에 기초한 성공적 경영방식 등의 지식을 통해 보편적이고 현장맞춤형 해결책을 제시하였다. 자문 기간 및 진행 과정 또한 6개월 이상으로 단기간의 해결책이 아닌 장기간 경영 자문을 수행하여, 경영시스템을 근본적으로 개선한 경영전략 방향성을 자문하였다. 이러한 경영학자의 경영 자문은 성과의 불확실성과 적은 보수에 따른 경영 자문 의욕의 저하가 나타날 수 있다. 또한, 즉각적이고 구체적인 해결방안을 바라는 기업에 대해 낮은 빈도로 장기간 지속하는 경영학자의 자문은 부적합 할 수도 있다. 그러나 경영 자문 활동 이외에도 자문 사례를 통한 연구성과 및 조교와 인턴십을 활용한 인재-일자리 확보 등을 통해 점차 바람직한 산학협력의 일환으로 자리 잡을 수 있을 것이다. 이러한 경영학자의 경영 자문이 안정적으로 자리 잡기 위해서는 벤처기업 및 중소기업과 관련된 유관기관의 긴밀한 협력 및 지원이 필요하고, 이에 관한 실증적 연구가 이루어져야 할 것이다. In this study, the case of management consulting project of the Korean Academic Society of Business Administration was analyzed in which business scholars participated. Through this, the characteristics of management consulting by business scholars were discovered and directions for future promotion were suggested. The Korean Academic Society of Business Administration conducted management consulting projects from 2017 to 2018. Business scholars were assigned to advise on promising SMEs selected by the Korea Venture Business Association and Industrial Bank of Korea. The characteristics shown in the above case are as follows. There is a demand for lectures related to corporate field issues. Business scholars responded to this demand for education. Moreover, business scholars consulted on theoretical management systems and successful management methods based on cases. They worked on solving fundamental problems by conducting management consulting for over 6 months. In addition to management consulting in the future, it is expected to increase research performance through advisory cases and secure human resources and jobs using students. Through this, these activities can be established as desirable industry-university cooperation. In order for these activities to be stably established, cooperation and support from organizations are required, and empirical research on this should be conducted.

Using Data Mining Tools to promote the use of Value Added Service in Mobile Telecommunication Market

Young Chul Han,Kyong Joo Oh,Hyunchul Ahn,Ingoo Han 대한산업공학회 2007 대한산업공학회 추계학술대회논문집 Vol.2007 No.11

The Prediction of Interest Rate Using Artificial Neural Network Models

Taeho Hong,Ingoo Han 대한산업공학회 1996 대한산업공학회 춘계학술대회논문집 Vol.1996 No.4

Effects of source influence and peer referrals on information diffusion in Twitter

Kwon, Joseph,Han, Ingoo,Kim, Byoungsoo Emerald Group Publishing Limited 2017 Industrial Management & Data Systems Vol. No.

<P>Originality/value-Given the growing popularity of social media, particularly SNSs with online social networks as information channels, the authors first consider online social transmission as a user-driven diffusion process. Based on social factors in the diffusion process, the authors derive source and peer effects on the social transmission process.</P>

Combining Cluster Analysis and Neural Networks for the Classification Problem

Kim, Kyungsup,Han, Ingoo 한국경영과학회 1996 한국경영과학회 학술대회논문집 Vol.- No.2

The extensive researches have compared the performance of neural networks (NN) with those of various statistical techniques for the classification problem. The empirical results of these comparative studies have indicated that the neural networks often outperform the traditional statistical techniques. Moreover. there are some efforts that try to combine various classification methods, especially multivariate discriminant analysis with neural networks. While these efforts improve the performance. there exists a problem violating robust assumptions of multivariate discriminant analysis that are multivariate normality of the independent variables and equality of variance-covariance matrices in each of the groups. On the contrary, cluster analysis alleviates this assumption like neural networks. We propose a new approach to classification problems by combining the cluster analysis with neural networks. The resulting predictions of the composite model are more accurate than each individual technique.

Utilization of Forecasting Accounting Earnings Using Artificial Neural Networks and Case-based Reasoning : Case Study on Manufacturing and Banking Industry 제조업과 은행업을 중심으로

최용석,한인구,신택수 한국경영과학회 2003 한국경영과학회지 Vol.28 No.3

The financial statements purpose to provide useful information to decision-making process of business managers. The value-relevant information. however, embedded in the financial statement has been often overlooked in Korea. In fact the financial statements in Korea are been utilized for nothing but account reports to Security Supervision Boards (SSB). The objective of this study is to develop earnings forecasting models through financial statement analysis using artificial intelligence (AI). AI methods are employed in forecasting earnings : artificial neural networks (ANN) for manufacturing industry and case-based reasoning (CBR) for banking industry. The experimental results using such AI methods are as follows. Using ANN for manufacturing industry records 63.2% of hit ratio for out-of-sample, which outperforms the logistic regression by around 4%. The experiment through CBR for banking industry shows 65.0% of hit ratio that beats the statistical method by 13.2% in holdout sample. Finally, the prediction results for manufacturing industry are validated through monitoring g the shift in cumulative returns of portfolios based on the earning prediction. The portfolio wit the firms whose earnings are predicted to increase is designated as best portfolio and the portfolio wit the earnings-decreasing firms as worst portfolio. The difference between tow portfolios is about 3% of cumulative abnormal return on average. Consequently, this result showed that the financial statements In Korea contain the value-relevant information that is not reflected in stock prices.