• Journal of the Korea Society for Simulation
• /
• v.30 no.1
• /
• pp.75-85
• /
• 2021

In this paper, we present a deep neural network-based prediction model that processes and analyzes the corporate credit and personal credit information of individual business owners as a new method to predict the default rate of individual business more accurately. In modeling research in various fields, feature selection techniques have been actively studied as a method for improving performance, especially in predictive models including many features. In this paper, after statistical verification of macroeconomic indicators (macro variables) and credit information (micro variables), which are input variables used in the default rate prediction model, additionally, through the credit information feature selection method, the final feature set that improves prediction performance was identified. The proposed credit information feature selection method as an iterative & hybrid method that combines the filter-based and wrapper-based method builds submodels, constructs subsets by extracting important variables of the maximum performance submodels, and determines the final feature set through prediction performance analysis of the subset and the subset combined set.

• Journal of the Korea Concrete Institute
• /
• v.20 no.2
• /
• pp.147-156
• /
• 2008

In an uniaxial compressive test of a concrete standard specimen (150$\times$300 mm) the crack initiation and extension with the stress increase are the major reason of the failure, which is similar to the breakage of the particle bonding in the simulation by using particle bonded model, especially particle flow code in 3 dimensions (PFC3D) developed by Itasca Consulting Group Inc. That is the main motive to study the possibility of an uniaxial compressive strength test simulation. It is important to investigate the relationship between the micro-parameters and the macro-properties because the 3-dimensional particle bonded model uses the spherical particles to analyze the physical phenomena. Contact bonded model used herein has eight micro-parameters and there are five macro-properties; Young's modulus, Poisson's ratio, uniaxial compressive strength and the crack initiation stress and the ratio concerning the crack propagation with the stress. To simulate the compressive test we made quantitative relationships between the micro-parameters and the macro-properties by using the fractional factorial design and various sensitivity analyses including regression analysis, which result in the good agreement with the previous studies. Also, the stress-stain curve and the crack distribution over the specimen given by PFC3D showed the mechanical behavior of the concrete standard specimen under the uniaxial compression. It is concluded that the particle bonded model can be a good tool for the analyzing the mechanical behavior of concrete under the uniaxial compressive load.

• The KIPS Transactions:PartD
• /
• v.10D no.5
• /
• pp.845-858
• /
• 2003

The various software engineering techniques have been come out in order to cope with the software crisis since 1980's. These days the software Engineering has focused on the process of software development which is the guide for a qualify and productive improvement of software. But, most of the methodologies assume that a new system will be constructed and reused in the future. these do not support how we reuse legacy system's resources and construct a new system efficiently. In this paper, we present an efficient Reengineering Process for legacy system evolutions, RUP+re, which extends and customizes RUP. RUP+re consists of Reverse Engineering Workflow, Transformation Workflow and Evolution Workflow based on Small-h model. We describe RUP+re's workflows with their own detail steps and verify the process through the case study practivally. So, we provide efficient guidelines to the software Reengineering process construction which evolutes the resources of a legacy system.

• KDI Journal of Economic Policy
• /
• v.28 no.1
• /
• pp.193-218
• /
• 2006

This paper examines the macroeconomic structural differences of the free floating exchange rate regime and the managed float exchange rate regime focusing on the Korean economy, and compares it to the two benchmark economies, Japan and Australia. Korea's shift to the free floating exchange rate regime from the managed float exchange rate regime came after the 1997 economic crisis. Korea's exchange rate policy provides a unique opportunity to study the different behaviors or roles, if any, of managed float and free floating exchange rate regimes. Based on a simple monetary model, we find that the exchange rates of Korea are more sensitive to the economic fundamentals under the free floating regime than under the managed float regime. Impulse response analysis shows that exchange rate pass-through into domestic variables, especially inflation rate, has a bigger short-term impact under the floating regime than under the managed regime. This finding is consistent with the view that the managed (or fixed) regime provides the domestic price stability necessary for the economic growth for the developing countries.

• The Korean Journal of Financial Management
• /
• v.16 no.2
• /
• pp.179-213
• /
• 1999

본 연구에서는 국내 주식시장에서 주식수익률의 횡단면 차이에 유의적인 설명력을 가지는 것으로 나타난 기본적 변수가 시장지수 베타에서는 측정되지 않은 또 다른 가격화된 위험에 대해 유용한 대용변수인지를 규명하였다. 기본적 변수들 중에서 기업규모와 장부/시장가치 비율은 주식수익률의 횡단면 차이를 설명함에 있어 독립적인 효과를 갖는 가장 유의적인 변수였다. 주식수익률의 횡단면 차이에 매우 유의적인 설명력을 가지는 깃으로 나타난 거시경제요인의 요인민감도는 기업규모, 장부/시장가치 비율을 포함시 더 이상 유의적인 설명력을 가지지 못하였다. 소규모, 높은 장부/시장가치 기업은 매우 지속적인 수익성 악화를 겪고 있는 곤경기업이며, 역시 배당감소위험, 레버리지위험 및 미래 현금흐름의 불확실성으로 측정된 기업특성적 위험이 보다 큰 곤경기업이었다. 따라서 이러한 실증결과는 소규모, 높은 장부/시장가치 주식이 대규모, 낮은 장부/시장가치 주식에 비해 높은 수익률을 보이는 원인이 보다 높은 위험에 따른 보상의 결과이며, 규모변수와 장부/시장 가치 비율은 이들 위험에 대한 유용한 대용치라는 '위험에 기초한 가설'을 지지하는 증거로 주장될 수 있다. 기업규모와 장부/시장가치 비율이 시장베타로는 측정되지 않는 주식가격결정에 있어 가격화 된 또 다른 위험을 대리한다면 수익률에 나타난 SIZE, B/M효과는 합리적 가격결정하 APT나 ICAPM과 같은 확장된 CAPM과 모순되지 않는 하나의 증거로 볼 수 있으며, 비록 이들 변수들이 관찰 불가능한 진정한 시장베타에 대한 보다 나은 대용치라고 할지라도 이들 두 변수와 관련된 요인을 포함한 다요인 가격결정모델이 시장지수만을 포함한 단일요인모델에 비해 보다 유용한 모형임을 기대할 수 있다.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.25 no.10
• /
• pp.1337-1345
• /
• 2001

Numerical investigation is made to study the effects of thermosolutal convection on the formation of macrosegregation in a Pb-Sn alloy solidification process in a two dimensional confined rectangluar mold. The basic equations are sovled using the Contrinum Model theory with the SIMPE algorithm during the solidification process. In addition, to track the liquid-solid interface with time variations, the moving boundary condition was adopted and moving irregular interface shapes were treated with the time-dependent, boundary-fitted coordinate system. As the temperature reduces from the liquidus to the solidus, the liquid concentration of Sn, the lighter constituent, increases. Then the buoyancy-driven flow due to temperature and liquid composition gradients occurs in the mushy region and forms the complicated macrosegregation maps. belated to this phenomena, effects on the macrosegregation formation depending on the cooling condition and gravity values are examined.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.514-516
• /
• 2005

CBD(Component Based Development)는 장기간에 걸쳐 발전된 소프트웨어 개발의 한 형태이며, 이미 표준화되거나 공인되지 않았지만 실제로 모든 기업들은 컴포넌트를 나름대로 제작하거나 이미 잘 개발되어진 컴포넌트를 재사용하여 자체 프로젝트에 재활용하므로써 최소의 개발비로 표준화를 추구하는 한편 최대의 기능과 신속한 개발로 소프트웨어의 품질과 생산성 향상을 도모하고 있다. 본 논문에서는 레거시 시스템을 활용하여 컴포넌트로 되어 있지 않은 프로그램을 컴포넌트화 함은 물론 기존 애플리케이션에 존재하는 컴포넌트를 래핑하여 재사용 가능한 서비스를 생성, 재공하기 위한 CBD 기반의 회계처리 응용 시스템을 설계 및 구현한다. 제안된 회계처리 응용 시스템 APAS(Accounting Process Application System) 모델은 시스템 구축 개발 기간의 단축과 관리 및 유지보수를 쉽게 하여 업무의 효율성을 높이고, 레거시 시스템을 재활용하여 신규 개발시 우려되는 위험도를 낮추어 소프트웨어 생산성 제고 효과도 얻을 수 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.47-56
• /
• 2020

The stock index is used not only as an economic indicator for a country, but also as an indicator for investment judgment, which is why research into predicting the stock index is ongoing. The task of predicting the stock price index involves technical, basic, and psychological factors, and it is also necessary to consider complex factors for prediction accuracy. Therefore, it is necessary to study the model for predicting the stock price index by selecting and reflecting technical and auxiliary factors that affect the fluctuation of the stock price according to the stock price. Most of the existing studies related to this are forecasting studies that use news information or macroeconomic indicators that create market fluctuations, or reflect only a few combinations of indicators. In this paper, this we propose to present an effective combination of the news information sentiment analysis and various macroeconomic indicators in order to predict the US Dow Jones Index. After Crawling more than 93,000 business news from the New York Times for two years, the sentiment results analyzed using the latest natural language processing techniques BERT and NLTK, along with five macroeconomic indicators, gold prices, oil prices, and five foreign exchange rates affecting the US economy Combination was applied to the prediction algorithm LSTM, which is known to be the most suitable for combining numeric and text information. As a result of experimenting with various combinations, the combination of DJI, NLTK, BERT, OIL, GOLD, and EURUSD in the DJI index prediction yielded the smallest MSE value.

• The KIPS Transactions:PartD
• /
• v.12D no.7 s.103
• /
• pp.947-956
• /
• 2005

Software(S/W) reengineering is one of the effective technologies to produce a business worth and en and the S/W ROI continuously. In spite of, S/W reengineering has been recognized a cost-consumptive works with inefficient productivity. In fact we have used to transform to confusion system with destructive system architecture by extending and updating legacy system in a temporary expedients. Moreover it is impossible to provide the time-market products for coping with rapid changeable system environment and meeting to complicated customer's requirements. Therefore, we need a systematic reengineering methodology to fulfill the changeable environment, as appearance of new IT techniques, various alteration of business information model, and increment of business logic. Legacy systems can be utilized as the core property in business organization through reengineering methodology. In this paper, we target to establish the reengineering process, proposed MaRMI-RE consisting of initial Planning phase, reverse engineering and component transformation phase. To describe the MaRMI-RE, we presented the concrete tasks and techniques and artifacts per individual phase in process, and the case study is showed briefly.

• The KIPS Transactions:PartD
• /
• v.16D no.4
• /
• pp.583-594
• /
• 2009

Most of the SOA solutions applicable to businesses and organizations are taking a top-down methodology. It starts with an analysis of an organization's requirements, followed by definition of business models and identification of candidate services and ends with finding or developing required services. Challenges in adopting SOA while abandoning legacy systems involve time and cost required during the process. Many businesses and organizations want to gradually migrate into SOA while making the most of the existing system. In this paper, we propose A Method for Migration of Legacy System into Web Service(M-LSWS); it allows legacy system to be migrated into web service accessible by SOA and be used as data repositories. M-LSWS defines procedures for migration into reusable web services through analysis of business processes and identification of candidate services based on design specification and code of legacy system. M-LSWS aims to migrate of legacy system into web service appropriate for SOA. The proposed method consists of four steps: analysis of legacy system, elicitation of reusable service and its specification, service wrapping and service registration. Each step has its own process and guideline. The eligibility of the proposed method will be tested by applying the method to book management system.