http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
한인구(In Goo Han),권영식(Young Sig Kwon),이건창(Kun Chang Lee) 한국경영학회 1995 經營學硏究 Vol.24 No.4
Credit rating represent an assessment of the relative level of risk associated with the timely payments required by the debt obligations. Credit rating is essential for the capital market to works efficiently. The results of credit rating by a professional agency are major criteria to banks` decision of loans and their terms. There are three domestic credit rating agencies. They use judgmental methodology rather than scientific and quantitative tools. In the period of economic liberalization, more attention is paid to the development of scientific credit rating system. The traditional techniques for creidit rating are statistical models such as MDA, probit, and logit. Artificial intelligence techniques such as inductive learning and neural network have been applied for credit rating since late 1980`s. In this research, we developed NICE-AI, which is the first credit rating system based on the neural network models. NICE-AI is available in the commercial information service, NICE-TIPS by National Information & Credit Evaluation In.
權寧植 동국대학교 경영대학원 1981 經營論叢-東國大學校 經營大學院 Vol.6 No.-
The purpose of this study is to develop a long range financial planning model and to demonstrate its applicability for Corporations. The model is aimed at reflecting the changes of the internal and external financial events of firms including new developments in strategies and environments The model consists of 10 sectors, 71 Equations. The actual application of the model in Korean firm has revealed that the forecasting error depends highly on the estimate of Sales and Earning Before Interests-Taxes. Therefore, the model has confirmed its applicability, predictability and the explanatory power of financial systems, provided that one can the accurate estimate of those two financial factors.
권영식,오태일 동국대학교 경영대학원 1983 經營論叢-東國大學校 經營大學院 Vol.8 No.-
Within the framework of capital market theories, the systematic risk, which can not be eliminated by diversification, is the sole relevant risk to which risk premium relates. The estimation of systematic risk(beta) is generally made by using past data. But previous studies have shown that beta is not stable over time. The purpose of this study is to find the determinants of beta. The results of empirical study are asfollows. First, the relation of beta and sales of the firm was tested by regression analysis. The result has shown that systematic risk of a stock reflects cash flow of the firm. Second, the change of beta was tested by ANOVA, and it was found that economic events play an important role under stability of beta. Third, from the characteristics of the firm such as industry risk, deta/equity ratio, are proven to be determinants of beta.
A Review of Artificial Intelligence Models in Business Classification
한인구,권영식,조홍규 한국지능정보시스템학회 1995 지능정보연구 Vol.1 No.1
Business researchers have traditionally used statistical techniques for classification. In late 1980's, inductive learning started to be used for business classification. Recently, neural network began to be applied for business classification. This study reviews the business classification studies, identifies a neural network approach as the most powerful classification tool, and discusses the problems and issues in neural network applications.