• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.157-178
• /
• 2009

Corporate credit rating is a very important factor in the market for corporate debt. Information concerning corporate operations is often disseminated to market participants through the changes in credit ratings that are published by professional rating agencies, such as Standard and Poor's (S&P) and Moody's Investor Service. Since these agencies generally require a large fee for the service, and the periodically provided ratings sometimes do not reflect the default risk of the company at the time, it may be advantageous for bond-market participants to be able to classify credit ratings before the agencies actually publish them. As a result, it is very important for companies (especially, financial companies) to develop a proper model of credit rating. From a technical perspective, the credit rating constitutes a typical, multiclass, classification problem because rating agencies generally have ten or more categories of ratings. For example, S&P's ratings range from AAA for the highest-quality bonds to D for the lowest-quality bonds. The professional rating agencies emphasize the importance of analysts' subjective judgments in the determination of credit ratings. However, in practice, a mathematical model that uses the financial variables of companies plays an important role in determining credit ratings, since it is convenient to apply and cost efficient. These financial variables include the ratios that represent a company's leverage status, liquidity status, and profitability status. Several statistical and artificial intelligence (AI) techniques have been applied as tools for predicting credit ratings. Among them, artificial neural networks are most prevalent in the area of finance because of their broad applicability to many business problems and their preeminent ability to adapt. However, artificial neural networks also have many defects, including the difficulty in determining the values of the control parameters and the number of processing elements in the layer as well as the risk of over-fitting. Of late, because of their robustness and high accuracy, support vector machines (SVMs) have become popular as a solution for problems with generating accurate prediction. An SVM's solution may be globally optimal because SVMs seek to minimize structural risk. On the other hand, artificial neural network models may tend to find locally optimal solutions because they seek to minimize empirical risk. In addition, no parameters need to be tuned in SVMs, barring the upper bound for non-separable cases in linear SVMs. Since SVMs were originally devised for binary classification, however they are not intrinsically geared for multiclass classifications as in credit ratings. Thus, researchers have tried to extend the original SVM to multiclass classification. Hitherto, a variety of techniques to extend standard SVMs to multiclass SVMs (MSVMs) has been proposed in the literature Only a few types of MSVM are, however, tested using prior studies that apply MSVMs to credit ratings studies. In this study, we examined six different techniques of MSVMs: (1) One-Against-One, (2) One-Against-AIL (3) DAGSVM, (4) ECOC, (5) Method of Weston and Watkins, and (6) Method of Crammer and Singer. In addition, we examined the prediction accuracy of some modified version of conventional MSVM techniques. To find the most appropriate technique of MSVMs for corporate bond rating, we applied all the techniques of MSVMs to a real-world case of credit rating in Korea. The best application is in corporate bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. For our study the research data were collected from National Information and Credit Evaluation, Inc., a major bond-rating company in Korea. The data set is comprised of the bond-ratings for the year 2002 and various financial variables for 1,295 companies from the manufacturing industry in Korea. We compared the results of these techniques with one another, and with those of traditional methods for credit ratings, such as multiple discriminant analysis (MDA), multinomial logistic regression (MLOGIT), and artificial neural networks (ANNs). As a result, we found that DAGSVM with an ordered list was the best approach for the prediction of bond rating. In addition, we found that the modified version of ECOC approach can yield higher prediction accuracy for the cases showing clear patterns.

• Journal of Korean Society on Water Environment
• /
• v.30 no.6
• /
• pp.638-646
• /
• 2014

Soil erosion from agricultural fields leads to various environmental problems weakening the capabilities of flood control and ecosystem in water bodies. Regarding these problems, Ministry of Environment of South-Korea prepared various structural and non-structural best management practices (BMPs) to control soil erosion. However, a lot of efforts are required to monitor and develop BMPs. Thus, modeling techniques have been developed and utilized for these issues. This study estimated the effectiveness of BMPs which are a vegetation mat with infiltration roll and Roll type vegetation channel using Soil and Water Assessment Tool (SWAT) model through the adjustment of the conservation practice factors, P factors, for Universal Soil Loss Equation which were calculated by monitoring data collected at the segment plots. Each BMP was applied to the areas with slopes ranged from 7% to 13% in the Haeanmyeon watershed. As a result of simulation, the vegetation mat with infiltration roll and Roll type vegetation channel showed 55% and 59% efficiency of soil erosion reduction, respectively. Also, Vegetation mat with infiltration roll and Roll type vegetation channel showed each 11.2% and 11.8% efficiency in reduction of sediment discharge. These roll type vegetation channel showed greater efficiency of soil erosion reduction and sediment discharge. Based on these results, if roll type vegetation channel is widely used in agricultural fields, reduction of soil erosion and sediment discharge of greater efficiency would be expected.

• Journal of the Korean Society for Library and Information Science
• /
• v.4
• /
• pp.43-71
• /
• 1975

Operations research has developed rapidly since its origins in World War II. Practitioners of O. R. have contributed to almost every aspect of government and business. More recently, a number of operations researchers have turned their attention to library and information systems, and the author believes that significant research has resulted. It is the purpose of this essay to introduce the library audience to some of these accomplishments, to present some of the author's hypotheses on the subject of library management to which he belives O. R. has great potential, and to suggest some future research directions. Some problem areas in librianship where O. R. may play a part have been discussed and are summarized below. (1) Library location. It is usually necessary to make balance between accessibility and cost In location problems. Many mathematical methods are available for identifying the optimal locations once the balance between these two criteria has been decided. The major difficulties lie in relating cost to size and in taking future change into account when discriminating possible solutions. (2) Planning new facilities. Standard approaches to using mathematical models for simple investment decisions are well established. If the problem is one of choosing the most economical way of achieving a certain objective, one may compare th althenatives by using one of the discounted cash flow techniques. In other situations it may be necessary to use of cost-benefit approach. (3) Allocating library resources. In order to allocate the resources to best advantage the librarian needs to know how the effectiveness of the services he offers depends on the way he puts his resources. The O. R. approach to the problems is to construct a model representing effectiveness as a mathematical function of levels of different inputs(e.g., numbers of people in different jobs, acquisitions of different types, physical resources). (4) Long term planning. Resource allocation problems are generally concerned with up to one and a half years ahead. The longer term certainly offers both greater freedom of action and greater uncertainty. Thus it is difficult to generalize about long term planning problems. In other fields, however, O. R. has made a significant contribution to long range planning and it is likely to have one to make in librarianship as well. (5) Public relations. It is generally accepted that actual and potential users are too ignorant both of the range of library services provided and of how to make use of them. How should services be brought to the attention of potential users? The answer seems to lie in obtaining empirical evidence by controlled experiments in which a group of libraries participated. (6) Acquisition policy. In comparing alternative policies for acquisition of materials one needs to know the implications of each service which depends on the stock. Second is the relative importance to be ascribed to each service for each class of user. By reducing the level of the first, formal models will allow the librarian to concentrate his attention upon the value judgements which will be necessary for the second. (7) Loan policy. The approach to choosing between loan policies is much the same as the previous approach. (8) Manpower planning. For large library systems one should consider constructing models which will permit the skills necessary in the future with predictions of the skills that will be available, so as to allow informed decisions. (9) Management information system for libraries. A great deal of data can be available in libraries as a by-product of all recording activities. It is particularly tempting when procedures are computerized to make summary statistics available as a management information system. The values of information to particular decisions that may have to be taken future is best assessed in terms of a model of the relevant problem. (10) Management gaming. One of the most common uses of a management game is as a means of developing staff's to take decisions. The value of such exercises depends upon the validity of the computerized model. If the model were sufficiently simple to take the form of a mathematical equation, decision-makers would probably able to learn adequately from a graph. More complex situations require simulation models. (11) Diagnostics tools. Libraries are sufficiently complex systems that it would be useful to have available simple means of telling whether performance could be regarded as satisfactory which, if it could not, would also provide pointers to what was wrong. (12) Data banks. It would appear to be worth considering establishing a bank for certain types of data. It certain items on questionnaires were to take a standard form, a greater pool of data would de available for various analysis. (13) Effectiveness measures. The meaning of a library performance measure is not readily interpreted. Each measure must itself be assessed in relation to the corresponding measures for earlier periods of time and a standard measure that may be a corresponding measure in another library, the 'norm', the 'best practice', or user expectations.

• Knowledge Management Research
• /
• v.23 no.1
• /
• pp.89-109
• /
• 2022

Due to COVID-19 and soaring participation of individual investors, large-scale transactions exceeding system capacity limits have been reported frequently in the capital market. The capital market IT systems, which the impact of system failure is very critical, have encountered unexpectedly tremendous transactions in 2020, resulting in a sharp increase in system failures. Despite the fact that many companies maintained large-scale system capacity planning policies, recent transaction influx suggests that a new approach to capacity planning is required. Therefore, this study developed capital market IT system capacity planning models using machine learning techniques and analyzed those performances. In addition, the performance of the best proposed model was improved by using sentiment index that can promptly reflect the behavior of investors. The model uses empirical data including the COVID-19 period, and has high performance and stability that can be used in practice. In practical significance, this study maximizes the cost-efficiency of a company, but also presents optimal parameters in consideration of the practical constraints involved in changing the system. Additionally, by proving that the sentiment index can be used as a major variable in system capacity planning, it shows that the sentiment index can be actively used for various other forecasting demands.

• Journal of Distribution Science
• /
• v.4 no.1
• /
• pp.5-26
• /
• 2006

As the capital of knowledge becomes more important than traditional capital like land or labor in the 21st century, the most competitive resource for corporations is knowledge. Furthermore, corporations may evaluate and improve latent knowledge of 'intellectual capital(IC)' within organizations, which will enhance their performance in the future. However, most Korea Distribution Companies have evaluated only tangible assets, ignoring latent capital. Since enterpreneurs have recognized that they cannot explain the difference between maret value and book value, the major advanced states lead to more sophisticated techniques to evaluate IC value. Although it is extremely important and urgent to evaluate IC value, the indexes of evaluating IC have never been examined and have been adopted by many corporations. Therfore, this study intends to develop a index for IC valuation. This study hopes to give some insights into the practical use of intellectual capital for the Korea Distribution Companies and help them develop a strategic perspective to enhance their competitiveness.

• Korean Journal of Heritage: History & Science
• /
• v.44 no.1
• /
• pp.106-121
• /
• 2011

The number of World Natural Heritage Sites is smaller than that of World Cultural Heritage Sites. As of 2010, the total number of natural sites was 180, which is less than 1/3 of all cultural sites. The reason why the number of natural sites is smaller can be attributed to the evaluating criteria of OUV(outstanding universal value). Only 9 fossil related sites were designated as World Heritage Sites among 180 Natural Sites. This study compares their OUVs including the academic value and characteristics of the 9 World Heritage Sites to provide data and reference for KCDC(Korean Cretaceous Dinosaur Coast) to apply as a World Natural Heritage Site. This study was carried out to obtain information and data on the Wadi Al-Hitan of Egypt which was designated as a World Natural Heritage Site. The study includes field investigation for whale fossils, interviews of site paleontologists and staff, and inspections of facilities. Three factors can likely be attributed to its successful management and operating system. First, there is a system for comprehensive research and a monitoring plan. Secondly, experts have been recruited and hired and professional training for staff members has been done properly. Finally, the Wadi Al-Hitan has developed local resources with specialized techniques for conservation and construction design, which matched well with whale fossils and the environment at the site. The Wadi Al-Hitan put a master plan into practice and achieved goals for action plans. To designate a future World Natural Heritage Site in Korea, it is important to be recognized by international experts including IUCN specialists as the best in one's field with OUV. Full-time regular-status employees for a research position are necessary from the preparation stage for the UNESCO World Heritage Site. Local government and related organizations must do their best to control monitoring plans and to improve academic value after the UNESCO World Heritage Site designation. As we experienced during the designation process of Jeju Volcanic Island and Lava Tubes as the first Korean World Natural Heritage Site, participation by various scholars and specialists need to be in harmony with active endeavors from local governments and NGOs.

• Korean Security Journal
• /
• no.47
• /
• pp.7-36
• /
• 2016

The security providers industry, often referred to as an industry with unconfined growth ceiling, has entered a remarkable mass-growth phase since the 1980. In the modern era, private-sector security increasingly cover functions relating to general security awareness (including counter-terrorism) in partnership with State bodies, and the scale of operations continue to accelerate, relative to the expanding roles. In the era of pluralisation of policing, there has been widening efforts pursued to develop a range of regulatory strategies internationally in order to manage such growth and development. To date, in South Korea, a diverse set of industry review studies have been conducted. However, the analyses have been conventionally confined to North America, Britain, Germany and Japan, while developments in other world regions remain unassessed. This article is intended to inform the drivers and determinants of regulatory reforms in Australia, and examine the effectiveness of the main pillars of licensing innovations. Over the past decades, the Australian regime has undergone a wave of reforms in response to emerging issues, and in recognition of the industry as a 'public good' due to underpopulation density and the resulting security challenges. The focus of review in this study was on providing a detailed review of the regulatory approach taken by Australia that has expanded police-private security co-operation since the 1980s. The emphasis was on examining the core pillars of risk management strategies and oversight practices progressed to date and evaluating areas of possible improvement in regulation relative to South Korea. Overall, this study has identified three key features of Australian regime: (1) close checks on questionable close associates (including fingerprinting), (2) power of inspection and seizure without search warrant, (3) the 'three strikes' scheme. The rise of the private security presence in day-to-day policing operations means that industry warrant some intervening government-sponsored initiative. The overall lessons learnt from the Australian case was taken into account in determining the following checks and balances that would provide the ideal setting for the best-practice arrangement: (1) regulatory measure should be evaluated against a set of well-defined indicators, such as the merits of different enforcement tools for each given risk, (2) information about regulatory impacts should be analysed by a specialist research institute, (3) regulators should be innovative in applying a range of strategies available to them by employing a mixture of compliance promotional strategies, and adjust the mix as required.