• Journal of the Korean Data and Information Science Society
• /
• v.27 no.5
• /
• pp.1293-1305
• /
• 2016

In this paper, we develop debt collection predictive models for the person in arrears by utilizing the direct loan data of the Korea Student Aid Foundation. We suggest credit risk scorecards for overdue student direct loan using the developed 3 models. Model 1 is designed for 1 month overdue, Model 2 is designed for 2 months overdue, and Model 3 is designed for overdue over 2 months. Model 1 shows that the major influencing factors for the delinquency are overdue account, due data for payment, balance, household income. Model 2 shows that the major influencing factors for delinquency loan are days in arrears, balance, due date for payment, arrears. Model 3 shows that the major influencing factors for delinquency are the number of overdue in recent 3 months, due data for payment, overdue account, arrears. The debt collection predictive models and credit risk scorecards in this study will be the basis for segmented management service and the call & collection strategies for preventing delinquency.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.6
• /
• pp.1207-1216
• /
• 2015

This study aims to compare the model power in developing corporate credit rating models and to suggest a good way to build models based on the characteristic of data. Among many measurement methods, AR is used to measure the model power under various conditions. SAS/MACRO is in use for similar repetitions to reduce time to build models under several combination of conditions. A corporate credit rating model is composed of two sub-models; a credit scoring model and a default prediction model. We verify that the latter performs better than the former under various conditions. From the result of size comparisons, models of large size corporate are more powerful and more meaningful in financial viewpoint than those of small size corporate. As a corporate size gets smaller, the gap between sub-models becomes huge and the effect of outliers becomes serious.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.4
• /
• pp.845-854
• /
• 2016

Sentiment analysis or opinion mining is a technique of text mining employed to identify subjective information or opinions of an individual from documents in blogs, reviews, articles, or social networks. In the literature, only a problem of binary classification of ratings based on review texts in an online review. However, because there can be positive or negative reviews as well as neutral reviews, a multi-class classification will be more appropriate than the binary classification. To this end, we consider the multi-class classification of ratings based on review texts. In the preprocessing stage, we extract words related with ratings using chi-square statistic. Then the extracted words are used as input variables to multi-class classifiers such as support vector machines and proportional odds model to compare their predictive performances.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.173-178
• /
• 2023

As Korean literature spreads around the world, its position in the overseas publishing market has become important. As demand in the overseas publishing market continues to grow, it is essential to predict future book sales and analyze the characteristics of books that have been highly favored by overseas readers in the past. In this study, we proposed ensemble learning based prediction model and analyzed characteristics of the cumulative sales of more than 5,000 copies classified as good sellers published overseas over the past 5 years. We applied the five ensemble learning models, i.e., XGBoost, Gradient Boosting, Adaboost, LightGBM, and Random Forest, and compared them with other machine learning algorithms, i.e., Support Vector Machine, Logistic Regression, and Deep Learning. Our experimental results showed that the ensemble algorithm outperforms other approaches in troubleshooting imbalanced data. In particular, the LightGBM model obtained an AUC value of 99.86% which is the best prediction performance. Among the features used for prediction, the most important feature is the author's number of overseas publications, and the second important feature is publication in countries with the largest publication market size. The number of evaluation participants is also an important feature. In addition, text mining was performed on the four book reviews that sold the most among good-selling books. Many reviews were interested in stories, characters, and writers and it seems that support for translation is needed as many of the keywords of "translation" appear in low-rated reviews.

• Journal of Digital Convergence
• /
• v.13 no.2
• /
• pp.105-113
• /
• 2015

If the watchdog role of good corporate governance, corporate executives and reduce agency costs and information asymmetries. Corporate governance score higher because enterprise internal control systems and financial reporting system is well equipped with the company management is enabled and corporate performance is higher because the high financial credit rating. Under these assumptions and hypotheses set up this study corporate governance (CGI) has been studied demonstrated how the financial impact on the credit rating (CFR). Findings,

relevant corporate governance (CGI) and financial credit rating was found to significantly affect the positive (+), Regression coefficient code is expected code of positive (+), the value

indicated by the value of all positive. The results of corporate governance (CGI) has showed excellent results, such as the more predictable will increase the credit score financial rating. The results of this study will have more CGI-credit financial rating the greater good. This study might be expected to provide a useful guide that corporate social responsibility, the company with a good governance and oversight systems enable to to get a higher credit rating in practice and research.

• Journal of Digital Convergence
• /
• v.18 no.1
• /
• pp.301-307
• /
• 2020

In recent years, a recommendation system is introduced in many different fields with the beginning of the 5G era and making a considerably prominent appearance mainly in books, movies, and music. In such a recommendation system, however, the preference degrees of users are subjective and uncertain, which means that it is difficult to provide accurate recommendation service. There should be huge amounts of learning data and more accurate estimation technologies in order to improve the performance of a recommendation system. Trying to solve this problem, this study proposed a movie recommendation system based on Fuzzy-AHP and Word2vec. The proposed system used Fuzzy-AHP to make objective predictions about user preference and Word2vec to classify scraped data. The performance of the system was assessed by measuring the accuracy of Word2vec outcomes based on grid search and comparing movie ratings predicted by the system with those by the audience. The results show that the optimal accuracy of cross validation was 91.4%, which means excellent performance. The differences in move ratings between the system and the audience were compared with the Fuzzy-AHP system, and it was superior at approximately 10%.

• Journal of KIISE
• /
• v.44 no.5
• /
• pp.486-495
• /
• 2017

Collaborative Filtering is limited because of the cost that is required to perform the recommendation (such as the time complexity and space complexity). The RFWBP (Rating Frequency Weight-based Baseline Predictor) that approximates the precision of the existing methods is one of the efficiency methods to reduce the cost. But, the following issues need to be considered regarding the RFWBP: 1) It does not reduce the error because the RFWBP does not learn for the recommendation, and 2) it recommends all of the items because there is no condition for an appropriate recommendation list when only the RFWBP is used for the achievement of efficiency. In this paper, the BBP (Bias-Based Predictor) is proposed to solve these problems. The BBP reduces the error range, and it determines some of the cases to make an appropriate recommendation list, thereby forging a recommendation list for each case.

• The Korean Journal of Financial Studies
• /
• v.4 no.1
• /
• pp.123-149
• /
• 1998

우리 나라 경제는 1993년 이후로 호황을 유지하다가 1996년 말부터는 경제불황이 닥쳐, 현재는 구제금융이라는 최악의 경제혼란기에 처해 있다. 하루에도 기업의 도산은 부지기수로 발생되고 있으며, 도산으로 인하여 국민들은 직장을 싫고 물가인상 등으로 가계마저 흔들리고 있는 실정이다. 이러한 이유로 본 연구에서는 재무비율에 의한 기업도산예측모델을 설정하려고 한다. 연구의 자료는 1996년 3월 은행연합회에서 개발한 '기업신용평가표'에 나타난 재무비율을 이용하였다. 연구의 결과를 보면 '기업신용평가표'의 변수는 기존연구에 비교하여 보면 도산예측력이 낮은 편인데, 그 이유는 기존연구는 대부분 통계적으로 검증된 5-6개의 변수를 대상으로 도산예측력을 나타내고 있는데 반하여, 본 연구에서는 기업신용평가표에서 선정된 모든 변수를 대상으로 분석했기 때문이다. 그러나 대체적으로 분석하여 볼 때 기업신용평가표의 재무비율 선정은 양호한 편으로 생각된다. 그러나 본 연구의 주목적은 신용평점에 의한 도산예측력분석이므로 본 연구의 선정모형에서 나타난 자기자본비율, 현금흐름/총부채(고정장기적합율), 매출액경상이익율, 총자본순이익율, 영업자산회전율 등은 기업신용평가내지 도산예측분석에 유용한 것으로 나타났다.

• Journal of dental hygiene science
• /
• v.14 no.3
• /
• pp.332-341
• /
• 2014

This study was aimed to define the predicting factor account for the Korean Dental Hygienist Licensing Examination (KDHLE) by analyzing the academic grade score and the KDHLE score. The subjects included 185 graduates (2007, 2009, 2011~2014 graduates). The ratio of successful applicants of the subjects was 99.2%. The academic grade scores were calculated to grade point average, the KDHLE was scoring marks out of 300 (200 of written examination score and 100 of performance evaluation score) for correlation and regression analysis. The graduation grades and comprehensive examination scores correlated significantly with the KDHLE written examination scores (correlation coefficient=0.612), and KDHLE total score (correlation coefficient=0.258). First~third grade score and comprehensive examination scores correlated significantly with KDHLE total scores (p<0.05). Especially, there are the highest correlated between second comprehensive examination scores and KDHLE total scores (correlation coefficient=0.455), the last score in time sequence is the important factors account for the KDHLE total score. But there is no correlation between academic grade score and KDHLE performance evaluation scores, therefore it is necessary to study for determine the reason. The results of multiple linear regression analysis, second grade score and the average score of comprehensive examination were the main predicting factors account for the KDHLE total score, the explanatory power was 31.6%. Our results show that KDHLE total and written examination scores are predicted by the academic grade score reliably, but not the KDHLE performance evaluation scores. Further studies are needed to determine relationship between dental hygiene education and KDHLE.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2007.05a
• /
• pp.190-197
• /
• 2007

외환위기 이후 우리나라 금융기관은 상대적으로 위험성이 높은 기업대출보다, 높은 수익성을 가지는 가계 대출에 관심을 기울이게 되었다. 가계대출이 증가함에 따라 개인신용평가의 중요성이 부각되고, 이에 많은 신용평가시스템이 개발되어 왔다. 하지만 기존의 신용평가시스템은 대출 신청 당시의 데이터 및 과거의 데이터를 가지고 개인의 신용을 평가하기 때문에, 미래 상황에 대한 예측은 고려하지 못한다. 시스템 다이나믹스는 시간의 흐름에 따른 각 요인의 변화를 살펴봄으로써 미래 상황에 대한 예측이 가능한 분석 방법이다. 이에 본 연구에서는 시스템 다이나믹스 방법론을 활용하여 개인 신용 상태에 대한 미래의 동태적인 변화를 예측하여, 그 결과를 반영한 신용평가모델을 개발하고자 한다. 이를 위하여, 먼저 신용평점 영향을 주는 변수들을 선정하고, 이 변수들 간의 인과관계를 밝혀낸 후, 인과관계를 토대로 분석 모델을 구축한 뒤, 컴퓨터 시뮬레이션을 실행함으로써, 대출 희망자의 미래의 신용상태 변화 모양을 예측해 본다. 이러한 시뮬레이션 결과를 신용평가에 반영하게 되면, 금융기관의 신용 대출의 위험을 줄이는 데 기여할 것으로 기대된다.