< Previous   List   Next >  
A study on the prediction of korean NPL market return
Full-text Download
Hyeon Su Lee (Department of Investment Information Engineering, Yonsei University)
Seung Hwan Jeong (Department of Industrial Engineering, Yonsei University)
Kyong Joo Oh (Department of Industrial Engineering, Yonsei University)
Vol. 25, No. 2, Page: 123 ~ 139
Artificial Neural Network, Decision Tree, Genetic Algorithm, Logistic Regression, NPL
The Korean NPL market was formed by the government and foreign capital shortly after the 1997 IMF crisis. However, this market is short-lived, as the bad debt has started to increase after the global financial crisis in 2009 due to the real economic recession. NPL has become a major investment in the market in recent years when the domestic capital market's investment capital began to enter the NPL market in earnest. Although the domestic NPL market has received considerable attention due to the overheating of the NPL market in recent years, research on the NPL market has been abrupt since the history of capital market investment in the domestic NPL market is short. In addition, decision-making through more scientific and systematic analysis is required due to the decline in profitability and the price fluctuation due to the fluctuation of the real estate business.
In this study, we propose a prediction model that can determine the achievement of the benchmark yield by using the NPL market related data in accordance with the market demand. In order to build the model, we used Korean NPL data from December 2013 to December 2017 for about 4 years. The total number of things data was 2291. As independent variables, only the variables related to the dependent variable were selected for the 11 variables that indicate the characteristics of the real estate. In order to select the variables, one to one t-test and logistic regression stepwise and decision tree were performed.
Seven independent variables (purchase year, SPC (Special Purpose Company), municipality, appraisal value, purchase cost, OPB (Outstanding Principle Balance), HP (Holding Period)).
The dependent variable is a bivariate variable that indicates whether the benchmark rate is reached.
This is because the accuracy of the model predicting the binomial variables is higher than the model predicting the continuous variables, and the accuracy of these models is directly related to the effectiveness of the model. In addition, in the case of a special purpose company, whether or not to purchase the property is the main concern. Therefore, whether or not to achieve a certain level of return is enough to make a decision. For the dependent variable, we constructed and compared the predictive model by calculating the dependent variable by adjusting the numerical value to ascertain whether 12%, which is the standard rate of return used in the industry, is a meaningful reference value. As a result, it was found that the hit ratio average of the predictive model constructed using the dependent variable calculated by the 12% standard rate of return was the best at 64.60%.
In order to propose an optimal prediction model based on the determined dependent variables and 7 independent variables, we construct a prediction model by applying the five methodologies of discriminant analysis, logistic regression analysis, decision tree, artificial neural network, and genetic algorithm linear model we tried to compare them. To do this, 10 sets of training data and testing data were extracted using 10 fold validation method. After building the model using this data, the hit ratio of each set was averaged and the performance was compared. As a result, the hit ratio average of prediction models constructed by using discriminant analysis, logistic regression model, decision tree, artificial neural network, and genetic algorithm linear model were 64.40%, 65.12%, 63.54%, 67.40%, and 60.51%, respectively. It was confirmed that the model using the artificial neural network is the best.
Through this study, it is proved that it is effective to utilize 7 independent variables and artificial neural network prediction model in the future NPL market. The proposed model predicts that the 12% return of new things will be achieved beforehand, which will help the special purpose companies make investment decisions. Furthermore, we anticipate that the NPL market will be liquidated as the transaction proceeds at an appropriate price.
Show/Hide Detailed Information in Korean
한국 NPL시장 수익률 예측에 관한 연구
이현수 (연세대학교)
정승환 (연세대학교)
오경주 (연세대학교)
로지스틱 회귀분석, 유전자 알고리즘, 의사결정나무, 인공신경망, NPL
국내 NPL (Non performing loan) 시장은 1998년에 형성되었지만, 본격적으로 활성화 된 시기는 2009년으로역사가 짧은 시장이다. 이로 인해 NPL 시장에 대한 연구도 아직까지는 활발히 진행되지 않고 있는 상황이다.
본 연구는 NPL 시장의 각 물건 별 기준 수익률 달성 유무를 예측할 수 있는 모델을 제안한다. 모델 구축에 사용되는 종속변수는 물건 별 최종 수익률이 기준 수익률 수치 도달 여부를 나타내는 이항변수를 사용하였고, 독립변수로는 물건의 특성을 나타내는 11개의 변수를 대상으로 one to one t-test와 logistic regression stepwise, decision tree를 수행하여 의미있는 7개의 독립변수를 선별하였다. 그리고 통상적으로 사용되는 기준 수익률 수치(12%)가 의미있는 기준 수치인지 확인하기 위해 수치 값을 조절해가며 종속변수를 산출하여 예측모델을 구축해보았다. 그 결과 12%의 기준 수익률 수치로 산출한 종속변수를 이용하여 구축한 예측모델의 평균 Hit ratio 가 64.60%로 가장 우수하다는 결과를 얻었다. 다음으로 선별된 7개의 독립변수들과 12%를 기준으로한 수익률달성유무 종속변수를 이용하여 판별분석, 로지스틱 회귀분석, 의사결정나무, 인공신경망, 유전자알고리즘 선형모델의 5가지 방법론을 적용해 예측모델을 구축해보았다. 5가지 방법론으로 도출한 예측 모델 간 Hit ratio를 비교한 결과 인공신경망을 이용하여 구축한 예측모델의 Hit ratio가 67.4%로 가장 우수한 결과를 도출해내었다.
본 연구를 통해 추후 NPL시장 신규 물건 매매에 있어서 7가지의 독립변수들과 인공신경망 예측 모델을 활용하는 것이 효과적임을 증명하였다. 물건의 12% 수익률 달성 여부를 사전에 예측해봄으로써 유동화회사가 투자의사결정을 하는 데에 도움을 줄 것으로 예상하며, 나아가 NPL 시장의 거래가 적정한 가격 선에서 진행됨으로인해 유동성이 더욱 높아질 것이라 기대한다.
Cite this article
JIIS Style
Lee, H. S., S. H. Jeong, and K. J. Oh, "A study on the prediction of korean NPL market return", Journal of Intelligence and Information Systems, Vol. 25, No. 2 (2019), 123~139.

IEEE Style
Hyeon Su Lee, Seung Hwan Jeong, and Kyong Joo Oh, "A study on the prediction of korean NPL market return", Journal of Intelligence and Information Systems, vol. 25, no. 2, pp. 123~139, 2019.

ACM Style
Lee, H. S., Jeong, S. H., and Oh, K. J., 2019. A study on the prediction of korean NPL market return. Journal of Intelligence and Information Systems. 25, 2, 123--139.
Export Formats : BiBTeX, EndNote
Advanced Search
Date Range

author = {Lee, Hyeon Su and Jeong, Seung Hwan and Oh, Kyong Joo},
title = {A study on the prediction of korean NPL market return},
journal = {Journal of Intelligence and Information Systems},
issue_date = {June 2019},
volume = {25},
number = {2},
month = Jun,
year = {2019},
issn = {2288-4866},
pages = {123--139},
url = {},
doi = {},
publisher = {Korea Intelligent Information System Society},
address = {Seoul, Republic of Korea},
keywords = { Artificial Neural Network, Decision Tree, Genetic Algorithm, Logistic Regression and NPL
%0 Journal Article
%1 776
%A Hyeon Su Lee
%A Seung Hwan Jeong
%A Kyong Joo Oh
%T A study on the prediction of korean NPL market return
%J Journal of Intelligence and Information Systems
%@ 2288-4866
%V 25
%N 2
%P 123-139
%D 2019
%I Korea Intelligent Information System Society