• 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 Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.191-207
• /
• 2021

Up to this day, mobile communications have evolved rapidly over the decades, mainly focusing on speed-up to meet the growing data demands of 2G to 5G. And with the start of the 5G era, efforts are being made to provide such various services to customers, as IoT, V2X, robots, artificial intelligence, augmented virtual reality, and smart cities, which are expected to change the environment of our lives and industries as a whole. In a bid to provide those services, on top of high speed data, reduced latency and reliability are critical for real-time services. Thus, 5G has paved the way for service delivery through maximum speed of 20Gbps, a delay of 1ms, and a connecting device of 106/㎢ In particular, in intelligent traffic control systems and services using various vehicle-based Vehicle to X (V2X), such as traffic control, in addition to high-speed data speed, reduction of delay and reliability for real-time services are very important. 5G communication uses high frequencies of 3.5Ghz and 28Ghz. These high-frequency waves can go with high-speed thanks to their straightness while their short wavelength and small diffraction angle limit their reach to distance and prevent them from penetrating walls, causing restrictions on their use indoors. Therefore, under existing networks it's difficult to overcome these constraints. The underlying centralized SDN also has a limited capability in offering delay-sensitive services because communication with many nodes creates overload in its processing. Basically, SDN, which means a structure that separates signals from the control plane from packets in the data plane, requires control of the delay-related tree structure available in the event of an emergency during autonomous driving. In these scenarios, the network architecture that handles in-vehicle information is a major variable of delay. Since SDNs in general centralized structures are difficult to meet the desired delay level, studies on the optimal size of SDNs for information processing should be conducted. Thus, SDNs need to be separated on a certain scale and construct a new type of network, which can efficiently respond to dynamically changing traffic and provide high-quality, flexible services. Moreover, the structure of these networks is closely related to ultra-low latency, high confidence, and hyper-connectivity and should be based on a new form of split SDN rather than an existing centralized SDN structure, even in the case of the worst condition. And in these SDN structural networks, where automobiles pass through small 5G cells very quickly, the information change cycle, round trip delay (RTD), and the data processing time of SDN are highly correlated with the delay. Of these, RDT is not a significant factor because it has sufficient speed and less than 1 ms of delay, but the information change cycle and data processing time of SDN are factors that greatly affect the delay. Especially, in an emergency of self-driving environment linked to an ITS(Intelligent Traffic System) that requires low latency and high reliability, information should be transmitted and processed very quickly. That is a case in point where delay plays a very sensitive role. In this paper, we study the SDN architecture in emergencies during autonomous driving and conduct analysis through simulation of the correlation with the cell layer in which the vehicle should request relevant information according to the information flow. For simulation: As the Data Rate of 5G is high enough, we can assume the information for neighbor vehicle support to the car without errors. Furthermore, we assumed 5G small cells within 50 ~ 250 m in cell radius, and the maximum speed of the vehicle was considered as a 30km ~ 200 km/hour in order to examine the network architecture to minimize the delay.

• KDI Journal of Economic Policy
• /
• v.12 no.2
• /
• pp.3-49
• /
• 1990

This paper analyzes U.S. demand for imports from Asian NIEs and Japan, utilizing the Almost Ideal Demand System (AIDS) developed by Deaton and Muellbauer, with an emphasis on the effect of changes in the exchange rate. The empirical model assumes a two-stage budgeting process in which the first stage represents the allocation of total U.S. demand among three groups: the Asian NIEs and Japan, six Western developed countries, and the U.S. domestic non-tradables and import competing sector. The second stage represents the allocation of total U.S. imports from the Asian NIEs and Japan among them, by country. According to the AIDS model, the share equation for the Asia NIEs and Japan in U.S. nominal GNP is estimated as a single equation for the first stage. The share equations for those five countries in total U.S. imports are estimated as a system with the general demand restrictions of homogeneity, symmetry and adding-up, together with polynomially distributed lag restrictions. The negativity condition is also satisfied for all cases. The overall results of these complicated estimations, using quarterly data from the first quarter of 1972 to the fourth quarter of 1989, are quite promising in terms of the significance of individual estimators and other statistics. The conclusions drawn from the estimation results and the derived demand elasticities can be summarized as follows: First, the exports of each Asian NIE to the U.S. are competitive with (substitutes for) Japan's exports, while complementary to the exports of fellow NIEs, with the exception of the competitive relation between Hong Kong and Singapore. Second, the exports of each Asian NIE and of Japan to the U.S. are competitive with those of Western developed countries' to the U.S, while they are complementary to the U.S.' non-tradables and import-competing sector. Third, as far as both the first and second stages of budgeting are coneidered, the imports from each Asian NIE and Japan are luxuries in total U.S. consumption. However, when only the second budgeting stage is considered, the imports from Japan and Singapore are luxuries in U.S. imports from the NIEs and Japan, while those of Korea, Taiwan and Hong Kong are necessities. Fourth, the above results may be evidenced more concretely in their implied exchange rate effects. It appears that, in general, a change in the yen-dollar exchange rate will have at least as great an impact, on an NIE's share and volume of exports to the U.S. though in the opposite direction, as a change in the exchange rate of the NIE's own currency $vis-{\grave{a}}-vis$ the dollar. Asian NIEs, therefore, should counteract yen-dollar movements in order to stabilize their exports to the U.S.. More specifically, Korea should depreciate the value of the won relative to the dollar by approximately the same proportion as the depreciation rate of the yen $vis-{\grave{a}}-vis$ the dollar, in order to maintain the volume of Korean exports to the U.S.. In the worst case scenario, Korea should devalue the won by three times the maguitude of the yen's depreciation rate, in order to keep market share in the aforementioned five countries' total exports to the U.S.. Finally, this study provides additional information which may support empirical findings on the competitive relations among the Asian NIEs and Japan. The correlation matrices among the strutures of those five countries' exports to the U.S.. during the 1970s and 1980s were estimated, with the export structure constructed as the shares of each of the 29 industrial sectors' exports as defined by the 3 digit KSIC in total exports to the U.S. from each individual country. In general, the correlation between each of the four Asian NIEs and Japan, and that between Hong Kong and Singapore, are all far below .5, while the ones among the Asian NIEs themselves (except for the one between Hong Kong and Singapore) all greatly exceed .5. If there exists a tendency on the part of the U.S. to import goods in each specific sector from different countries in a relatively constant proportion, the export structures of those countries will probably exhibit a high correlation. To take this hypothesis to the extreme, if the U.S. maintained an absolutely fixed ratio between its imports from any two countries for each of the 29 sectors, the correlation between the export structures of these two countries would be perfect. Therefore, since any two goods purchased in a fixed proportion could be classified as close complements, a high correlation between export structures will imply a complementary relationship between them. Conversely, low correlation would imply a competitive relationship. According to this interpretation, the pattern formed by the correlation coefficients among the five countries' export structures to the U.S. are consistent with the empirical findings of the regression analysis.