• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.135-149
• /
• 2020

Artificial intelligences are changing world. Financial market is also not an exception. Robo-Advisor is actively being developed, making up the weakness of traditional asset allocation methods and replacing the parts that are difficult for the traditional methods. It makes automated investment decisions with artificial intelligence algorithms and is used with various asset allocation models such as mean-variance model, Black-Litterman model and risk parity model. Risk parity model is a typical risk-based asset allocation model which is focused on the volatility of assets. It avoids investment risk structurally. So it has stability in the management of large size fund and it has been widely used in financial field. XGBoost model is a parallel tree-boosting method. It is an optimized gradient boosting model designed to be highly efficient and flexible. It not only makes billions of examples in limited memory environments but is also very fast to learn compared to traditional boosting methods. It is frequently used in various fields of data analysis and has a lot of advantages. So in this study, we propose a new asset allocation model that combines risk parity model and XGBoost machine learning model. This model uses XGBoost to predict the risk of assets and applies the predictive risk to the process of covariance estimation. There are estimated errors between the estimation period and the actual investment period because the optimized asset allocation model estimates the proportion of investments based on historical data. these estimated errors adversely affect the optimized portfolio performance. This study aims to improve the stability and portfolio performance of the model by predicting the volatility of the next investment period and reducing estimated errors of optimized asset allocation model. As a result, it narrows the gap between theory and practice and proposes a more advanced asset allocation model. In this study, we used the Korean stock market price data for a total of 17 years from 2003 to 2019 for the empirical test of the suggested model. The data sets are specifically composed of energy, finance, IT, industrial, material, telecommunication, utility, consumer, health care and staple sectors. We accumulated the value of prediction using moving-window method by 1,000 in-sample and 20 out-of-sample, so we produced a total of 154 rebalancing back-testing results. We analyzed portfolio performance in terms of cumulative rate of return and got a lot of sample data because of long period results. Comparing with traditional risk parity model, this experiment recorded improvements in both cumulative yield and reduction of estimated errors. The total cumulative return is 45.748%, about 5% higher than that of risk parity model and also the estimated errors are reduced in 9 out of 10 industry sectors. The reduction of estimated errors increases stability of the model and makes it easy to apply in practical investment. The results of the experiment showed improvement of portfolio performance by reducing the estimated errors of the optimized asset allocation model. Many financial models and asset allocation models are limited in practical investment because of the most fundamental question of whether the past characteristics of assets will continue into the future in the changing financial market. However, this study not only takes advantage of traditional asset allocation models, but also supplements the limitations of traditional methods and increases stability by predicting the risks of assets with the latest algorithm. There are various studies on parametric estimation methods to reduce the estimated errors in the portfolio optimization. We also suggested a new method to reduce estimated errors in optimized asset allocation model using machine learning. So this study is meaningful in that it proposes an advanced artificial intelligence asset allocation model for the fast-developing financial markets.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.4 no.4
• /
• pp.45-70
• /
• 2009

This article investigates which types of the strategies announced by the listed firms contribute to enhancing the long-term performance of the companies. Since 2002, Korean Exchange adopted the "faire disclosure policy" which mandates that all publicly traded companies must disclose material information to all investors at the same time. Thanks to the policy, Korean investors can, now, easily access the board's decision on management strategies on the same day the decision is made. If the companies trustfully carry out their announced strategies, we can decide which types of strategies actually enhance or deteriorate the long-term performance, simply by comparing the announced strategies and the firm's performance. The sample companies are confined to 60 firms that became listed in the KOSDAQ market through back-door listing from 2003 to 2005. Using only the newly listed companies, we can avoid the interference on the long-term performance of the strategies pursued before the event date. This often holds true, for many companies radically modify their strategies after the listing. Furthermore, the back-door listing companies serve our purpose better than IPO companies do, because the former tend to have a variety of announcement within a given period of time beginning the listing date. Using these sample companies, this article analyzes the effect on one year buy-and-hold returns and abnormal buy-and-hold returns after the listing of the various types of strategies announced during the same period of time. The results show that those evidences of restructuring such as 'reduction of capital' and 'resignation of incumbent board members', actually contribute to the increase in adjusted long-term stock returns. Those strategies which can be view as evidence of new investment such as 'increase in tangible assets', 'acquisition of other companies', do also helps the stockholders better off. On the contrary, 'increase in bank loans', 'changes of CEO' and 'merger' deteriorate the equity value. The last findings let us to presume that the back-door listing companies appear to use the bank loans for value-reducing activities; the change in CEO is not a sign of restructuring, but rather a sign of failure of the restructuring; another merger carried out after back-door listing itself is also value-reducing activity. This article's findings on reduction of capital, merger and bank loans oppose the results of the former empirical studies which analyze only the short-term effect on stock price. Therefore, more long-term performance studies on public disclosures are in order.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.36 no.1
• /
• pp.14-19
• /
• 2007

This study was conducted to analyze the antioxidant activity and xanthine oxidase inhibitory effect of hot-water extracts from Elaeagnus multiflora Thunb. to provide fundamental data for the development of functional materials. The antioxidative activities of hot-water extracts from E. multiflora Thunb. were analyzed by electron donating ability (EDA) using 1,1-diphenyl-2-picryl hydrazyl (DPPH), superoxide dismutase (SOD) -like activity by pyrogallol and nitrite scavenging ability. EDA of extracts from unripe, ripe, and overripe fruits were 77.7%, 36.0%, and 23.7% at 100 ${\mu}g/mL$, respectively, and EDA of extract in unripe fruits was higher than those of others. At 1,000 $\mu$g/mL, the SOD-like activities were 32.8%, 11.2% and 5.0% for unripe, ripe, and overripe fruits, respectively. The SOD-like activity was increased along with the increase of unripe and ripe extract concentrations. The nitrite scavenging ability of unripe fruit extracts in 100, 300, 500 ${\mu}g/mL$ of extraction solution in pH 1.2 and 3.0 was higher than those of others. The nitrate scavenging ability of all extracts was decreased according to the increase of pH. Xanthine oxidase inhibitory activities of unripe, ripe and overripe fruits were 30.0%, 28.2%, and 18.2% at 1,000 ${\mu}g/mL$, respectively.

• Korean Journal of Remote Sensing
• /
• v.22 no.6
• /
• pp.495-505
• /
• 2006

In order to classify aerosol type, Aerosol Optical Thickness (AOT) and Fine mode Fraction (FF), which is the optical thickness ratio of small particles$(<1{\mu}m)$ to total particles, data from MODIS (MODerate Imaging Spectraradiometer) aerosol products were analyzed over North-East Asia during one year period of 2005. A study area was in the ocean region of $20^{\circ}N\sim50^{\circ}N$ and $110^{\circ}E\simt50^{\circ}E$. Three main atmospheric aerosols such as dust, sea-salt, and pollution can be classified by using the relationship between AOT and FF. Dust aerosol has frequently observed over the study area with relatively high aerosol loading (AOT>0.3) of large particles (FF<0.65) and its contribution to total AOT in spring was up to 24.0%. Pollution aerosol, which is originated from anthropogenic sources as well as a natural process like biomass burning, has observed in the regime of high FF (>0.65) with wide AOT variation. Average pollution AOT was $0.31{\pm}0.05$ and its contribution to total AOT was 79.8% in summer. Characteristic of sea-salt aerosol was identified with low AOT (<0.3), almost below 0.1, and slightly higher FF than dust and lower FF than pollution. Seasonal analysis results show that maximum AOT $(0.33{\pm}0.11)$ with FF $(0.66{\pm}0.21)$ in spring and minimum AOT $(0.19{\pm}0.05)$, FF $(0.60{\pm}0.14)$ in fall were observed in the study area. Spatial characteristic was that AOT increasing trend is observed as closing to the eastern part of China due to transport of aerosols from China by the prevailing westerlies.

• Journal of Intelligence and Information Systems
• /
• v.16 no.2
• /
• pp.19-32
• /
• 2010

Volatility plays a central role in both academic and practical applications, especially in pricing financial derivative products and trading volatility strategies. This study presents a novel mechanism based on generalized autoregressive conditional heteroskedasticity (GARCH) models that is able to enhance the performance of intelligent volatility trading systems by predicting Korean stock market volatility more accurately. In particular, we embedded the concept of the volatility asymmetry documented widely in the literature into our model. The newly developed Korean stock market volatility index of KOSPI 200, VKOSPI, is used as a volatility proxy. It is the price of a linear portfolio of the KOSPI 200 index options and measures the effect of the expectations of dealers and option traders on stock market volatility for 30 calendar days. The KOSPI 200 index options market started in 1997 and has become the most actively traded market in the world. Its trading volume is more than 10 million contracts a day and records the highest of all the stock index option markets. Therefore, analyzing the VKOSPI has great importance in understanding volatility inherent in option prices and can afford some trading ideas for futures and option dealers. Use of the VKOSPI as volatility proxy avoids statistical estimation problems associated with other measures of volatility since the VKOSPI is model-free expected volatility of market participants calculated directly from the transacted option prices. This study estimates the symmetric and asymmetric GARCH models for the KOSPI 200 index from January 2003 to December 2006 by the maximum likelihood procedure. Asymmetric GARCH models include GJR-GARCH model of Glosten, Jagannathan and Runke, exponential GARCH model of Nelson and power autoregressive conditional heteroskedasticity (ARCH) of Ding, Granger and Engle. Symmetric GARCH model indicates basic GARCH (1, 1). Tomorrow's forecasted value and change direction of stock market volatility are obtained by recursive GARCH specifications from January 2007 to December 2009 and are compared with the VKOSPI. Empirical results indicate that negative unanticipated returns increase volatility more than positive return shocks of equal magnitude decrease volatility, indicating the existence of volatility asymmetry in the Korean stock market. The point value and change direction of tomorrow VKOSPI are estimated and forecasted by GARCH models. Volatility trading system is developed using the forecasted change direction of the VKOSPI, that is, if tomorrow VKOSPI is expected to rise, a long straddle or strangle position is established. A short straddle or strangle position is taken if VKOSPI is expected to fall tomorrow. Total profit is calculated as the cumulative sum of the VKOSPI percentage change. If forecasted direction is correct, the absolute value of the VKOSPI percentage changes is added to trading profit. It is subtracted from the trading profit if forecasted direction is not correct. For the in-sample period, the power ARCH model best fits in a statistical metric, Mean Squared Prediction Error (MSPE), and the exponential GARCH model shows the highest Mean Correct Prediction (MCP). The power ARCH model best fits also for the out-of-sample period and provides the highest probability for the VKOSPI change direction tomorrow. Generally, the power ARCH model shows the best fit for the VKOSPI. All the GARCH models provide trading profits for volatility trading system and the exponential GARCH model shows the best performance, annual profit of 197.56%, during the in-sample period. The GARCH models present trading profits during the out-of-sample period except for the exponential GARCH model. During the out-of-sample period, the power ARCH model shows the largest annual trading profit of 38%. The volatility clustering and asymmetry found in this research are the reflection of volatility non-linearity. This further suggests that combining the asymmetric GARCH models and artificial neural networks can significantly enhance the performance of the suggested volatility trading system, since artificial neural networks have been shown to effectively model nonlinear relationships.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.1488-1491
• /
• 2006

본 연구에서는 실시간 통합 물관리 시스템의 일환으로 월별 일강수량 예측 시스템에 관한 연구를 실시하였다. 선행시간 2일 예측에 대해서는 기상청 생성 수치모의 RDAPS (Regional Data Assimilation and Prediction System)를 기반으로 강수진단모형인 QPM (Quantitative Precipitatiom Model)을 이용하여 지형효과를 보정하였으며, 선행시간 2일에서 8일까지의 예측에 대해서는 GDAPS (Global Data Assimilation and Prediction System) 모의결과를 QPM을 이용하여 보정하였고, 선행시간 10일 이후의 예측값은 통계적 기법을 이용한 자료를 활용하였다. 통계적 기법으로는 과거 20년간의 관측된 강수경향을 이용하여 시스템을 구축하였다. 강수진단모형 (QPM)은 Misumi et al. (2001), Bell (1978), Collier (1975)등이 제안한 바 있는 Collier-type의 모형으로서 이들 모형은 소규모 지형 효과를 고려한 강수량을 산출하는 진단 모형이다. QPM은 중규모 예측 모형으로부터 계산된 수평 바람, 고도, 기온, 강우 강도, 그리고 상대습도 등의 예측 자료를 이용하고, 중규모 예측 모형에서는 잘 표현되지 않는 소규모 지형 효과를 고려함으로써 중규모 예측 모형에서 생산된 상대적으로 성긴 격자의 강수량 예측 값을 상세 지역의 지형을 고려한 강수량 예측 값으로 재구성하게 된다. QPM은 중규모 모형으로부터 나온 자료를 초기 자료로 이용하고 3 km 간격의 상세 지형을 반영하는 모형으로 소규모 지형 효과를 표현함으로써 상세 지역에서의 강수량 산출과 지형에 따른 강수량의 분포 파악이 용이할 뿐 아니라, 계산 효율성을 개선시킬 수 있다.착능이 높은 것으로 사료되었다.X>${\mu}_{max,A}$는 최대암모니아 섭취률을 이용하여 구한 결과 $0.65d^{-1}$로 나타났다.EX>$60%{\sim}87%$가 수심 10m 이내에 분포하였고, 녹조강과 남조강이 우점하는 하절기에는 5m 이내에 주로 분포하였다. 취수탑 지점의 수심이 연중 $25{\sim}35m$를 유지하는 H호의 경우 간헐식 폭기장치를 가동하는 기간은 물론 그 외 기간에도 취수구의 심도를 표층 10m 이하로 유지 할 경우 전체 조류 유입량을 60% 이상 저감할 수 있을 것으로 조사되었다.심볼 및 색채 디자인 등의 작업이 수반되어야 하며, 이들을 고려한 인터넷용 GIS기본도를 신규 제작한다. 상습침수지구와 관련된 각종 GIS데이타와 각 기관이 보유하고 있는 공공정보 가운데 공간정보와 연계되어야 하는 자료를 인터넷 GIS를 이용하여 효율적으로 관리하기 위해서는 단계별 구축전략이 필요하다. 따라서 본 논문에서는 인터넷 GIS를 이용하여 상습침수구역관련 정보를 검색, 처리 및 분석할 수 있는 상습침수 구역 종합정보화 시스템을 구축토록 하였다.N, 항목에서 보 상류가 높게 나타났으나, 철거되지 않은 검전보나 안양대교보에 비해 그 차이가 크지 않은 것으로 나타났다.의 기상변화가 자발성 기흉 발생에 영향을 미친다고 추론할 수 있었다. 향후 본 연구에서 추론된 기상변화와 기흉 발생과의 인과관계를 확인하고 좀 더 구체화하기 위한 연구가 필요할 것이다.게 이루어질 수 있을 것으로 기대된다.는 초과수익률이 상승하지만, 이후로는 감소하므로, 반전거래전략을 활용하는 경우 주식투자기간은 24개월이하의 중단기가 적합함을 발견하였다. 이상의 행태적 측면과 투자성과측면의 실증결과를 통하여 한국주

• 한국공간정보시스템학회:학술대회논문집
• /
• 2003.11a
• /
• pp.78-83
• /
• 2003

OGC(Open GIS Consortium, Inc.)에서 2000년에 XML의 지리정보 처리를 위한 GML 1.0이 제안된 이후 최근 GML 3.0이 발표되기까지 국제적으로는 다양한 GIS 응용분야에서 GML을 현실 문제에 이용하고자 하는 시도가 이루어지고 있다. 현재 우리나라에서도 국가 GIS(NGIS)에서 GML을 도입하여 국내 표준안으로 추진하고자 다양한 기반연구가 진행되고 있다. 본 연구는 중요한 GIS 응용중의 하나인 지질자원 정보 분야에서 GML을 활용하기 위한 기반연구로서 우리나라의 표준 지질도(또는 수치지질정보)와 기타 지질자원 정보 인프라 구축에 적용될 수 있는 다양한 지구과학자료를 대상으로 하였다. 따라서 본 연구에서는 지질자원 분야에서의 GML 응용을 위한 기반 데이터 모델과 이를 처리하기 위한 아키텍처를 UML 기법으로 설명하고, 이를 바탕으로 시험 구현된 운용환경에서 실제 대상 지역을 선정하여, 연구지역에 대한 지질자원 정보의 GML 적용 사례를 제시하고자 한다. 이를 위한 연구 내용으로는 수치 지질도를 XML-GML의 기본 스키마구조에 따라 엔코딩한 뒤, 주제정보의 표현을 위한 XSLT, SVG 파일 변환 처리 등을 수행하였다. 결론적으로 본 연구는 지질자원 분야의 정보화 인프라 구축을 목적으로 하는 기초 시험연구로 수행되었는 바, 우리나라에서는 2001년 이후 GIS 수치 주제도로서 수치 지질도의 보급이 활성화되면서, 이 정보를 제작/공급하는 기관이나 업무에 사용하는 기관 등에서 GML 기반으로 데이터를 제작하거나 운용이 가능할 것으로 생각된다. 또한, 다른 분야에서 GIS 주제정보를 다루는 경우에도 GML을 주제정보와 연계하여 현실 문제에 적용이 가능한 창조 모델로 이용될 수 있을 것으로 생각된다.}94,\;29.4{\pm}30.3,\;45.1{\pm}44$로 Mel 10군과 Mel 30군이 유의적인 감소를 보였으나(p<0.05) 이들 두 군 간의 차이는 나타나지 않았다. 이상의 결과로, 랫트에서 복강수술 후 melatonin 10mg/kg투여가 복강 내 유착 방지에 효과적이라고 생각된다.-1}{\cdot}yr^{-1}$로서 두 생태계에 축적되었다.여한 3,5,7군에서 PUFA 함량이 증가한 반면, SFA 함량은 감소하여 P/S 비율, n-3P/n-6P 비율은 증가하는 경향이었으며 이는 간장의 인지질, 콜레스테롤 에스테르, 총 지질의 지방산조성에서도 같은 경향을 볼 수 있었다.X>$(C_{18:2})$와 n-3계 linolenic acid$(C_{18:3})$가 대부분을 차지하였다. 야생 돌복숭아 과육 중의 지방산 조성은 포화지방산이 16.74%, 단불포화지방산 17.51% 및 다불포화지방산이 65.73%의 함유 비율을 보였는데, 이 중 다불포화지방산인 n-6계 linoleic acid$(C_{18:2})$와 n-3계 linolenic acid$(C_{18:3})$가 지질 구성 총 지방산의 대부분을 차지하는 함유 비율을 나타내었다.했다. 하강하는 약 4일간의 기상변화가 자발성 기흉 발생에 영향을 미친다고 추론할 수 있었다. 향후 본 연구에서 추론된 기상변화와 기흉 발생과의 인과관계를 확인하고 좀 더 구체화하기 위한 연구가 필요할 것이다.게 이루어질 수 있을 것으로 기대된다.는 초과수익률이 상승하지만, 이후로는 감소하므로, 반전거래전략을 활용하는 경우 주식투자기간은 24개월이하의 중단기가 적합함을 발견하였다. 이상의 행태적 측면과 투자성과측면의 실

• Korea Trade Review
• /
• v.43 no.6
• /
• pp.51-70
• /
• 2018

This study is to define the relationship between capital structure and the market share in the global shipping market, estimating the debt-equity ratio. To analyze the impact of the debt-equity ratio on market share, this study collected data from the 100 largest shipping companies from 2010 to 2017. Results identified that global shipping lines moderate their debt-equity rates to 62%, and all of them strategically utilize debt in order to increase market share in global shipping market. In comparison between the group focused on cargo volume and another group focused on freight rates, it is found that the group focused on cargo volume increase their handling cargo volume through increasing the debt rates. Another group used debt rate for reducing the freight rate and enhancing market power. Furthermore, after classifying the samples into high-growth and low-growth companies, this study compared the group focused on cargo volume and another group focused on freight rates. As a result, the low-growth group showed more significant impacts of the debt rate on market share than the high-growth group. The results of this study provide useful insight for future strategic decision making of shipping lines in the global shipping market.

• The Korean Journal of Financial Management
• /
• v.21 no.2
• /
• pp.27-63
• /
• 2004

Since the 1980s, many multinational corporations have been issuing stocks on foreign stock exchanges, not only to enhance their investor base and liquidity, but also to diversify risks. The phenomenon has also been intensified by the rapid financial globalization and securitization trends. The main purpose of this study is to look into the long-run performance of MNCs' cross-listings of stocks on foreign stock exchanges. We use the event study and cross-sectional regression methods. We obtained some interesting empirical results about the long-run effect of cross-listings. First before the listing data the effect of cross-listing is to increase the underlying stock Vice in the local market. It may be caused by expectation of lower risk and cost of capital. However, after the listing data the stock price has been declining, even if it is not significant. Second, we examine the difference in the long-run cross-listing effect, which may be caused by the listing direction. When listing is made from a less developed market to a more developed market, the effect is better than that in the reverse direction. Furthermore, the effect is worse, when the listing company's home country is the U.S. Third, there is a negative relation between CARs and underlying stock liquidity in the local market, So it implies that a firm, whose underlying stocks are very liquid in the local market should carefully value cross-listing based upon the cost and benefit analysis. Last, but not the least we find that the long-un cross-listing effect is better, when a listing firm's ROE is higher.

• Journal of Korea Spatial Information System Society
• /
• v.6 no.1 s.11
• /
• pp.73-85
• /
• 2004

Recently, as the growth of the wireless Internet, PDA and HPC, the focus of research and development related with GIS(Geographic Information System) has been changed to the Real-Time Mobile GIS to service LBS. To offer LBS efficiently, there must be the Real-Time GIS platform that can deal with dynamic status of moving objects and a location index which can deal with the characteristics of location data. Location data can use the same data type(e.g., point) of GIS, but the management of location data is very different. Therefore, in this paper, we studied the Real-Time Mobile GIS using the HBR-tree to manage mass of location data efficiently. The Real-Time Mobile GIS which is developed in this paper consists of the HBR-tree and the Real-Time GIS Platform HBR-tree. we proposed in this paper, is a combined index type of the R-tree and the spatial hash Although location data are updated frequently, update operations are done within the same hash table in the HBR-tree, so it costs less than other tree-based indexes Since the HBR-tree uses the same search mechanism of the R-tree, it is possible to search location data quickly. The Real-Time GIS platform consists of a Real-Time GIS engine that is extended from a main memory database system. a middleware which can transfer spatial, aspatial data to clients and receive location data from clients, and a mobile client which operates on the mobile devices. Especially, this paper described the performance evaluation conducted with practical tests if the HBR-tree and the Real-Time GIS engine respectively.