• 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.

• Journal of Hospice and Palliative Care
• /
• v.8 no.2
• /
• pp.143-151
• /
• 2005

Purpose: Bereavement Memorial Service has been held every year by the hospice team at St. Vincent's Hospital for the purpose of supporting the bereaved family who feel grief and mourning. The purpose of this study is to find out the attitude of the bereaved attending at bereavement memorial service (BMS) and to find out the areas needing improvements to set up better memorial service. Methods: Hospice team sent invitation card to 180 families of patients who admitted and passed away at hospice ward Nov., 2003${\sim}$Oct., 2004. Among them 22 families attended the BMS meeting, which was held on 26th Nov., 2004. The researcher collected data from 22 families with 'Questionnaire' survey. Except identifying data and 2 dichotomy questions, we used open-ended questionnaire. 1 researcher conducted a telephone interview survey in 18 families who couldn't attend at BMS meeting. Results: The median age was 56 (range $16{\sim}19$) and there were 37 females and 3 males. They were patient's wife (22), mother (4), husband (5), daughter (4), mother-in-law (1), siblings (1), brothers wife (1). Duration after bereavement, $1{\sim}3$ months (17) was the highest frequency. 36 families agreed 'the dead experienced the death with dignity'. The reason of agreement to the death with dignity was 'the patient died in preparation' (16). 'the patient died in well-being condition spiritually' (9), 'the patient died in comfort physically (7). 4. persons thought the dead died with indignity. The bereaved defined 'the death with dignity' as follows: 'acceptance of death & death in spiritual well-being' (9), 'death in physical comfort condition' (7), 'the death in psycho-social well-being' (3), non-respondents (10). Most families (21) were still in difficulty to overcome bereavement grief. The answer regarding the method to overcome the difficulty was 'with spiritual sublimation' (13), 'with devotion of oneself in daily life' (10), 'with devotion to mourning as it is' (3). With regard to their attitude to invitation, 'having joy and thanks from hospice team' (21), 'grief' (4), 'suffering' (4). Toward the existence of hesitation about attendance at BMS meeting, the result as follows. Nonexistence of hesitation respondent (34), existence respondent (6), the reason for hesitation was various; 'the meeting reminds me of the suffering times', 'the meeting makes me to recall, and it will be likely to cry', and so on. The needs and feelings to memorial service meeting were various; 'it was meaningful time', 'it was good to recall about the dead', 'more meeting annually' and so on. In respect of the most difficulty after bereavement, in attendant family, 'depression' (10) was the highest frequency, whereas, in non-attendant family, the most difficult thing was 'financial problem/role difficulty (6). Conclusion: This study shows the rate of attendance was high in bereaved whose bereavement duration $1{\sim}3$ month. Most of bereaved were still suffering from bereavement grief within 1 year. Although most families didn't hesitate and felt positive mood to invitation, the rate of attendance was low. Comparing with two groups between attendant family and non-attendant, the latter felt more difficulty in 'financial problem/role difficulty, on the other hand, the former felt difficulty in 'depression'. Hereafter, the additional study about the factor relating to these attitude and needs of the bereaved relating to memorial service will be necessary.