• Journal of Information Technology Applications and Management
• /
• v.14 no.2
• /
• pp.151-168
• /
• 2007

The corporate credit rating represents an assessment of the relative level of risk associated with the timely payments required by the debt obligation. In this study, the corporate credit rating model employs artificial intelligence methods including Neural Network (NN) and Case-Based Reasoning (CBR). At first we suggest three classification models, as partitioned neural networks, all of which convert multi-group classification problems into two group classification ones: Ordinal Pairwise Partitioning (OPP) model, binary classification model and simple classification model. The experimental results show that the partitioned NN outperformed the conventional NN. In addition, we put to use CBR that is widely used recently as a problem-solving and learning tool both in academic and business areas. With an advantage of the easiness in model design compared to a NN model, the CBR model proves itself to have good classification capability through the highest hit ratio in the corporate credit rating.

• The Journal of Industrial Distribution & Business
• /
• v.7 no.2
• /
• pp.13-20
• /
• 2016

Purpose - The purpose of this research is to discover whether the presence of the product average rating introduces biases or change the way people perceive information. We posit that review's overall rating has a predisposition effect on consumers' perception towards detailed review information. Research design, data, and methodology - To test these hypotheses, we conducted an empirical study on a real-world setting of online shopping platform. We choose the Amazon website to test our results. The data we use were collected by the Stanford Network Analysis Project1 (McAuley et al., 2013). Results - With a dataset containing reviews of seven product categories from amazon.com., our findings could possess more generalizability as they are produced on the typical and influential online market. Second, as our research provides alternative views of consumers' shopping behavior, it is better to test our hypotheses by data from the same source. Conclusions - Our study reveals the impact of the collective rating presence on consumers' diagnosticity perception and sheds light upon some of the conflictive results in prior studies. Our research generates implications to both theories and business practices, and suggests future directions for the research question.

• Korean Journal of Human Ecology
• /
• v.10 no.1
• /
• pp.83-91
• /
• 2001

Currently, obtaining information about the housing studies through the internet web sites is one of the outstanding mediums. Those are of the housings, architecture, interior design, furniture products, hotels and its journals, etc., and out of all those informations are the highly expected value of use. But. it may causes the public users to experience a negative effect, because many of those informations provided on the internet web sites related to the housing studies/informations are not providing an equal quality of information. And measuring the quality is also not easy. This study focuses on the establishment of evaluation criterion for the housing information-related internet web sites. In such a vein, it proposes a clear model to evaluate the information qualities with the 43 questionnaires / examining items. To test the questionnaires/rating items, the analysis has been implemented which has shown the reciprocal effect between the 2 major factors. One major factor with 4 variables on the information searches are (1) the accuracy/reliability of contents and techniques, (2) the design of a picture and communication, (3) the readability and security, and (4) the security of private information, and the other factor with 3variables on the additional services are (1) the diversities of contents and ease of orderings, (2) the abilities of search and e-mail, and (3) the events and after services. This study/rating model will provide the users with a fundamental material in evaluating the quality of housing information on the internet web sites.

• Asia pacific journal of information systems
• /
• v.21 no.2
• /
• 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.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.9 no.1
• /
• pp.43-52
• /
• 2013

Pervasive computing and social network are good resources in recommendation method. Collaborative filtering is one of the most popular recommendation methods, but it has some limitations such as rating sparsity. Moreover, it does not consider social network in pervasive computing environment. We propose an effective proactive friend recommendation method using social network and contexts in pervasive computing environment. In collaborative filtering method, users need to rate sufficient number of items. However, many users don't rate items sufficiently, because the rating information must be manually input into system. We solve the rating sparsity problem in the collaboration filtering method by using contexts. Our method considers both a static and a dynamic friendship using contexts and social network. It makes more effective recommendation. This paper describes a new friend recommendation method and then presents a music friend scenario. Our work will help e-commerce recommendation system using collaborative filtering and friend recommendation applications in social network services.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2003.05a
• /
• pp.474-483
• /
• 2003

A number of studies for corporate bond rating classification problems have demonstrated that artificial intelligence approaches such as Case-based reasoning (CBR) can be alternative methodologies to statistical techniques. CBR is a problem solving technique in that the case specific knowledge of past experience is utilized to find a most similar solution to the new problems. To build a successful CBR system to deal with human information processing, the representation of knowledge of each attribute is an important key factor We propose a hybrid approach of using fuzzy sets that describe the approximate phenomena of the real world because it handles inexact knowledge represented by common linguistic terms in a similar way as human reasoning compared to the other existing techniques. Integration of fuzzy sets with CBR is important to develop effective methods for dealing with vague and incomplete knowledge to statistical represent using membership value of fuzzy sets in CBR.

• The Journal of Asian Finance, Economics and Business
• /
• v.3 no.3
• /
• pp.5-15
• /
• 2016

This study examines whether Korean rating agencies such as Korea Investors Service (KIS), National Information & Credit Evaluation (NICE), and Korea Ratings Corporation (KR), incorporate corporate governance into their corporate bond ratings in Korea. We find that the Korean rating agencies assign higher ratings to the bonds issued by Chaebol (Korean business group) affiliated firms. Our results also indicate that those rating agencies give higher ratings to the bonds with greater foreign investor share ownership. Moreover, if the rating agencies value corporate governance, higher rated firms should issue bonds at lower yield to maturity. We discover that Chaebol affiliation is counted favorably by the rating agencies. We find that investors are willing to pay lower risk premium for bonds with higher institutional ownership, but higher risk premium to bonds with greater equity ownership in the form of depository receipts. Therefore, even if the rating agencies and investors in Korea consider corporate governance (Chaebol affiliation and ownership structure) an important determinant in bond ratings and the yields to maturity, they have opposite views on institutional ownership and share ownership in the form of depository receipts.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.6
• /
• pp.81-89
• /
• 2020

Online reviews we encounter commonly on SNS, although a complex range of assessment information affecting the consumer's preferences are included, it is general that such information is just provided by simple numbers or star ratings. Based on those review types, it is not easy to get specific information that consumers want and use it to make a decision for purchase. Therefore, in this study, we propose a prediction methodology that can provide ratings broken down by evaluation items by performing sentiment analysis on restaurant reviews written in Korean. To this end, we select 'food', 'price', 'service', and 'atmosphere' as the main evaluation items of restaurants, and build a new sentiment dictionary for each evaluation item. It also classifies review sentences by rating item, predicts granular ratings through sentiment analysis, and provides additional information that consumers can use to make decisions. Finally, using MAE and RMSE as evaluation indicators it shows that the rating prediction accuracy of the proposed methodology has been improved than previous studies and presents the use case of proposed methodology.

• Journal of Information Processing Systems
• /
• v.15 no.2
• /
• pp.331-343
• /
• 2019

Dynamic thermal rating of the overhead transmission lines is affected by many uncertain factors. The ambient temperature, wind speed and wind direction are the main sources of uncertainty. Measurement uncertainty is an important parameter to evaluate the reliability of measurement results. This paper presents the uncertainty analysis based on Monte Carlo. On the basis of establishing the mathematical model and setting the probability density function of the input parameter value, the probability density function of the output value is determined by probability distribution random sampling. Through the calculation and analysis of the transient thermal balance equation and the steady- state thermal balance equation, the steady-state current carrying capacity, the transient current carrying capacity, the standard uncertainty and the probability distribution of the minimum and maximum values of the conductor under 95% confidence interval are obtained. The simulation results indicate that Monte Carlo method can decrease the computational complexity, speed up the calculation, and increase the validity and reliability of the uncertainty evaluation.

• Journal of Information Technology Services
• /
• v.17 no.4
• /
• pp.53-74
• /
• 2018

This study theoretically examines the essence of the competencies, qualifications and grades newly required in the era of the 4th industrial revolution, points out that the engineer rating system does not reflect the new talent and practical capability, and conducts theoretical and empirical analyzes on improvement of the rating system. The current rating system need to be improved because it is not possible for graduates and experience workers to upgrade. Also, it is reasonable that the current highest grade of engineer, the Professional Engineer, which is a sort of qualification, is not a grade but a function of calculating the grade. Based on this theoretical background, empirical analysis of the question investigation and focus group interview shows that the rating system should be improved to four grades or return to the previous system in 2013. And if it is reduced to four grade, it should go in the way that the professional engineer and the qualified engineer combined. In the industry, the future skills of engineers are as follows : qualification, ability to use emerging technology, problem solving, understanding and utilization of major, and data management, etc. These can be summarized as qualification, education (degree) and career. In particular, the engineering industry considers qualifications, degrees, and career experience, and career experience as the most important elements of the rating system. In this regard, it is necessary to introduce a method that accurately reflects the career experience in the improvement of the engineer rating system.