• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• Tuberculosis and Respiratory Diseases
• /
• v.45 no.6
• /
• pp.1265-1276
• /
• 1998

Background : Nitric oxide(NO) is an endogenously produced free radical that plays an important role in regulating vascular tone, inhibition of platelet aggregation and white blood cell adhesion to endothelial cells, and host defense against infection. The highly reactive nature of NO with oxygen radicals suggests that it may either promote or reduce oxidant-induced cell injury in several biological pathways. Oxidant injury and interactions between pulmonary vascular endothelium and leukocytes are important in the pathogenesis of acute lung injury, including acute respiratory distress syndrome(ARDS). In ARDS, therapeutic administration of NO is a clinical condition providing exogenous NO in oxidant-induced endothelial injury. The role of exogenous NO from NO donor or the suppression of endogenous NO production was evaluated in oxidant-induced endothelial injury. Method : The oxidant injury in cultured rat lung microvascular endothelial cells(RLMVC) was induced by hydrogen peroxide generated from glucose oxidase(GO). Cell injury was evaluated by $^{51}$chromium($^{51}Cr$) release technique. NO donor, such as S-nitroso-N-acetylpenicillamine(SNAP) or sodium nitroprusside(SNP), was added to the endothelial cells as a source of exogenous NO. Endogenous production of NO was suppressed with N-monomethyl-L-arginine(L-NMMA) which is an NO synthase inhibitor. L-NMMA was also used in increased endogenous NO production induced by combined stimulation with interferon-$\gamma$(INF-$\gamma$), tumor necrosis factor-$\alpha$(TNF-$\alpha$), and lipopolysaccharide(LPS). NO generation from NO donor or from the endothelial cells was evaluated by measuring nitrite concentration. Result : $^{51}Cr$ release was $8.7{\pm}0.5%$ in GO 5 mU/ml, $14.4{\pm}2.9%$ in GO 10 mU/ml, $32.3{\pm}2.9%$ in GO 15 mU/ml, $55.5{\pm}0.3%$ in GO 20 mU/ml and $67.8{\pm}0.9%$ in GO 30 mU/ml ; it was significantly increased in GO 15 mU/ml or higher concentrations when compared with $9.6{\pm}0.7%$ in control(p < 0.05; n=6). L-NMMA(0.5 mM) did not affect the $^{51}Cr$ release by GO. Nitrite concentration was increased to $3.9{\pm}0.3\;{\mu}M$ in culture media of RLMVC treated with INF-$\gamma$ (500 U/ml), TNF-$\alpha$(150 U/ml) and LPS($1\;{\mu}g/ml$) for 24 hours ; it was significantly suppressed by the addition of L-NMMA. The presence of L-NMMA did not affect $^{51}Cr$ release induced by GO in RLMVC pretreated with INF-$\gamma$, TNF-$\alpha$ and LPS. The increase of $^{51}Cr$ release with GO(20 mU/ml) was prevented completely by adding 100 ${\mu}M$ SNAP. But the add of SNP, potassium ferrocyanate or potassium ferricyanate did not protect the oxidant injury. Nitrite accumulation was $23{\pm}1.0\;{\mu}M$ from 100 ${\mu}M$ SNAP at 4 hours in phenol red free Hanks' balanced salt solution. But nitrite was not detectable from SNP upto 1 mM The presence of SNAP did not affect the time dependent generation of hydrogen peroxide by GO in phenol red free Hanks' balanced salt solution. Conclusion : Hydrogen peroxide generated by GO causes oxidant injury in RLMVC. Exogenous NO from NO donor prevents oxidant injury, and the protective effect may be related to the ability to release NO. These results suggest that the exogenous NO may be protective on oxidant injury to the endothelium.