• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.83-102
• /
• 2021

The government recently announced various policies for developing big-data and artificial intelligence fields to provide a great opportunity to the public with respect to disclosure of high-quality data within public institutions. KSURE(Korea Trade Insurance Corporation) is a major public institution for financial policy in Korea, and thus the company is strongly committed to backing export companies with various systems. Nevertheless, there are still fewer cases of realized business model based on big-data analyses. In this situation, this paper aims to develop a new business model which can be applied to an ex-ante prediction for the likelihood of the insurance accident of credit guarantee. We utilize internal data from KSURE which supports export companies in Korea and apply machine learning models. Then, we conduct performance comparison among the predictive models including Logistic Regression, Random Forest, XGBoost, LightGBM, and DNN(Deep Neural Network). For decades, many researchers have tried to find better models which can help to predict bankruptcy since the ex-ante prediction is crucial for corporate managers, investors, creditors, and other stakeholders. The development of the prediction for financial distress or bankruptcy was originated from Smith(1930), Fitzpatrick(1932), or Merwin(1942). One of the most famous models is the Altman's Z-score model(Altman, 1968) which was based on the multiple discriminant analysis. This model is widely used in both research and practice by this time. The author suggests the score model that utilizes five key financial ratios to predict the probability of bankruptcy in the next two years. Ohlson(1980) introduces logit model to complement some limitations of previous models. Furthermore, Elmer and Borowski(1988) develop and examine a rule-based, automated system which conducts the financial analysis of savings and loans. Since the 1980s, researchers in Korea have started to examine analyses on the prediction of financial distress or bankruptcy. Kim(1987) analyzes financial ratios and develops the prediction model. Also, Han et al.(1995, 1996, 1997, 2003, 2005, 2006) construct the prediction model using various techniques including artificial neural network. Yang(1996) introduces multiple discriminant analysis and logit model. Besides, Kim and Kim(2001) utilize artificial neural network techniques for ex-ante prediction of insolvent enterprises. After that, many scholars have been trying to predict financial distress or bankruptcy more precisely based on diverse models such as Random Forest or SVM. One major distinction of our research from the previous research is that we focus on examining the predicted probability of default for each sample case, not only on investigating the classification accuracy of each model for the entire sample. Most predictive models in this paper show that the level of the accuracy of classification is about 70% based on the entire sample. To be specific, LightGBM model shows the highest accuracy of 71.1% and Logit model indicates the lowest accuracy of 69%. However, we confirm that there are open to multiple interpretations. In the context of the business, we have to put more emphasis on efforts to minimize type 2 error which causes more harmful operating losses for the guaranty company. Thus, we also compare the classification accuracy by splitting predicted probability of the default into ten equal intervals. When we examine the classification accuracy for each interval, Logit model has the highest accuracy of 100% for 0~10% of the predicted probability of the default, however, Logit model has a relatively lower accuracy of 61.5% for 90~100% of the predicted probability of the default. On the other hand, Random Forest, XGBoost, LightGBM, and DNN indicate more desirable results since they indicate a higher level of accuracy for both 0~10% and 90~100% of the predicted probability of the default but have a lower level of accuracy around 50% of the predicted probability of the default. When it comes to the distribution of samples for each predicted probability of the default, both LightGBM and XGBoost models have a relatively large number of samples for both 0~10% and 90~100% of the predicted probability of the default. Although Random Forest model has an advantage with regard to the perspective of classification accuracy with small number of cases, LightGBM or XGBoost could become a more desirable model since they classify large number of cases into the two extreme intervals of the predicted probability of the default, even allowing for their relatively low classification accuracy. Considering the importance of type 2 error and total prediction accuracy, XGBoost and DNN show superior performance. Next, Random Forest and LightGBM show good results, but logistic regression shows the worst performance. However, each predictive model has a comparative advantage in terms of various evaluation standards. For instance, Random Forest model shows almost 100% accuracy for samples which are expected to have a high level of the probability of default. Collectively, we can construct more comprehensive ensemble models which contain multiple classification machine learning models and conduct majority voting for maximizing its overall performance.

• Korean Journal of Veterinary Research
• /
• v.9 no.1
• /
• pp.23-62
• /
• 1969

Throughout the studies the following experimental results were obtained and are summarized: 1. Multiplication of agents in primary cell cultures of both GF classical and CR-64 acute strain of Marek's disease infected chicken kidneys was accompanied by the formation of distinct transformed cell foci. This characteristic nature of cell transformation was passaged regularly by addition of dispersed cell from infected cultures to normal chicken kidney cell cultures, and also transferred was the nature of cell transformation to normal chick-embryo liver and neuroglial cell cultures. No cytopathic changes were noticed in inoculated chick-embryo fibroblast cultures. 2. The same cytopathic effects were noticed in normal kidney cell monolayers after the inoculation of whole blood and huffy coat cells derived from both forms of Marek's disease infected chickens. In these cases, however, the number of transformed cell foci appearing was far less than that of uninoculated monolayers prepared directly from the kidneys of Marek's disease infected chickens. 3. The change in cell culture IS regarded as a specific cell transformation focus induced by an oncogenic virus rather than it plaque in slowly progressing cytopathic effect by non-oncogenic viruses, and it is quite similar to RSV focus in chick-embryo fibroblasts in many respects. 4. The infective agent (cell transformable) were extremely cell-associated and could not be separated in an infective state from cells under the experimental conditions. 5. The focus assay of these agents was valid as shown by the high degree of linear correlation (r=0.97 and 0.99) between the relative infected cell concentration (in inoculum) and the transformed cell foci counted. 6. No differences were observed between the GF classical strain and the CR-64 acute strain of Marek's disease as far as cell culture behavior. 7. Characterization of the isolates by physical and chemical treatments, development of internuclear inclusions in Infected cells, and nucleic acid typing by differential stainings and cytochemical treatments indicated that the natures of these cell transformation agents closely resemble to those described fer the group B herpes viruses. 8. Susceptible chicks inoculated with infected kidney tissue culture cells developed specific lesions of Marek's disease, and in a case of prolonged observation after inoculation (5 weeks) the birds developed clinical symptoms and gross lesions of Marek's disease. Kidney cell cultures prepared from those inoculated birds and sacrificed showed a superior recovery of cell transformation property by formation of distinct foci. 9. Electron microscopic study of infected kidney culture cells (GF agent) by negative staining technique revealed virus particles furnishing the properties of herpes viruses. The particle was measured about $100m{\mu}$ and, so far, no herpes virus envelop has been seen from these preparations. 10. No relationship of both isolates to avian leukosis/sarcoma group viruses and PPLO was observed.