• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.

• The Journal of the Korea Contents Association
• /
• v.22 no.10
• /
• pp.271-278
• /
• 2022

MyData service integrates and manages user's personal data such as finance, credit, etc, and is expected to provide useful information to the user as personal data in various fields are gradually integrated. Discovering factors that affect the intention to use of MyData service is a very important topic for understanding that service. To this end, in this study, the attributes of the MyData service were derived, and the derived service attributes were grouped together by using factor analysis. As a result, we found four factors such as "convenience", "usefulness", "security", and "control". After that, we established our research model to analyze the causal relationship between these four factors and the intention to use of MyData service. According to the analysis results, among the factors of the MyData service attribute, "convenience", "usefulness", and "control" had a significant effect, and "security" did not have a significant effect. In particular, it was confirmed that "control" had the greatest influence on the intention to use. This study suggests that MyData service provider need to make users recognize they are controlling their data and develop services that provide various benefits to users.

• The Korean Journal of Applied Statistics
• /
• v.36 no.6
• /
• pp.619-629
• /
• 2023

Fertilizers are crucial for increasing crop yield, but using too much of them without taking into account the nutrients that the crops need can increase costs for farm management and have a negative impact on the environment. Through smart agriculture, fertilizers can be applied as needed at the right time to reflect the growth characteristics of crops, reducing the burden of fertilizer losses and providing economical nutrient management. In this study, we use the total dry weight of field-cultivated red pepper and green onion grown in various growing environments to fit a nonlinear model-based crop growth model using different growth curves (logistic, Gompertz, Richards, and double logistic curve), and we propose a fertilizer distributed algorithm based on crop growth rate.

• Informatization Policy
• /
• v.31 no.2
• /
• pp.65-81
• /
• 2024

The scale of e-procurement through online shopping malls of public institutions including government comprehensive shopping malls is increasing day by day. This study aims to examine how public officials evaluate products, delivery, and post service of online shopping malls for public institutions and to explore ways of improving their satisfaction. The results from a survey conducted among public officials of public institutions who have experience using online shopping malls of public institutions showed generally high satisfaction levels, although there was dissatisfaction with product diversity. Perception of delivery quality was generally positive, but there was room for improvement in delivery service. Furthermore, employing structural equation modeling, the study examined the influences on satisfaction and intention to reuse. Perceived product quality, delivery quality, and delivery service quality were confirmed to influence satisfaction considerably. Therefore, more efforts should be directed towards managing the information and quality of products to prevent returns, exchanges, and repairs and, in case of issues, handling them promptly and transparently.

• Korean journal of applied entomology
• /
• v.60 no.1
• /
• pp.49-61
• /
• 2021

Integrated mite management provided a basic direction to early the fruit tree IPM. The early IPM concept was based on incorporation of the biological control for mite pests with the existing chemical control compatibly. Since then, the hypotheses and mechanisms of the interaction between species diversity and pest population dynamics have provided a broader understanding of mite-centered pest management in fruit tree ecosystems. Based on the principle of the ecosystem, biological control and pest management through habitat modification or manipulation are developing to the concept of agro-ecological engineering. In particular, the natural enemy diversity is dynamically changed according to the different cultivation environment in the management of mite pests, and the species composition of phytophagous mites is also changed by the environment for orchard management. This paper reviews the biological control of mites, which was the basis of apple IPM, and also re-examines the topics of species diversity and pest management, predacious mite diversity in relation to mite control and the change of species composition of mite pests in the sight of ecological engineering. Finally, we suggest a strategy for biological control of spider mites in apple orchards in Korea.

• The Journal of the Korea Contents Association
• /
• v.10 no.12
• /
• pp.342-351
• /
• 2010

This study aims to investigate the major causes of conflict between clients and vendors in the outsourced IS development. A research model is established based on the prior research of IS outsourcing, system development and conflict. An empirical study was executed using 214 survey questionnaire of project teams composed of client and vendor with PASW 18.0. Research results using multiple regressions show that contract specificity, requirements certainty, objective alignment and client knowledge have negative effects on conflict. This research results will provide various implications for outsourcing project success.

• Korean Journal of Construction Engineering and Management
• /
• v.12 no.2
• /
• pp.81-88
• /
• 2011

Providers haven't recently had a flexible construction cost estimation system to meet various needs of consumers about public housing. So the subject of this study is to estimate construction cost reasonably in early project stage of public housing and then develop reliable means which is able to support construction cost management and establish a adequate funding investment plan as a provider. In this study, Regression analysis was performed by the case on 20 public apartment complex which were designed from the first half of 2007 to the first half of 2008. A total construction cost of construction, civil engineering, machinery, elevator, land scape, electricity and communication work was used as one sample for increasing explanation and representativeness of the case. In addition, The total construction cost which is devided into design, contract and completion cost was variously analysed for increasing relevance of model and actual utilization. The result of estimation model based on a total construction cost set up completion and design cost showed that error rate is within 2%, which is a excellent result. The estimation model of the construction cost developed by this study is expected to estimate approximate construction cost which is adjacent real construction cost in early stage of the project by using some data.

• Korean Journal of Construction Engineering and Management
• /
• v.15 no.4
• /
• pp.150-158
• /
• 2014

A bunch of asphalt roads have been damaged frequently in relation to the rapid climate change. To solve and prevent this type of problems, many nationalities in the world have performed various researches. In this regard, the objective of this study is to develop prediction model as to the number of potholes occurred in seoul. At the same time, we have utilized empirical and statistical approaches in order for us to identify factors which is affecting the actual occurrence. The predictive model was determinded by using BHS (Basic Harmony Search) algorithm. Prediction was based on the weather and traffic data as well as data occurrence data of porthole. To assess the influences which are PAR(Pitch Adjusting Rate) and HMCR(Harmony Memory Considering Rate), we determined suitability by changing the values. In the process of the determining a predictive model, the predictive model composed Training data (2011, 2012 and 2013yrs data). To determine the suitability of the model, we have utilized Testing Set (2009 and 2010 yrs data). The suitability of the basic prediction model has been from RMSE(Root Mean Squared Error), MAE(Mean Absolute Error) and Coefficient of determination.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.161-161
• /
• 2015

최근 정보화 기술의 발달로 다양하고 방대한 정보들이 집적되고 있으며, 다양한 분야에서 집적된 자료의 활용성에 대한 관심이 보이고 있다. 특히, 수자원분야에서는 ADCP와 같은 최신 계측기법으로 확보되고 있는 방대한 양의 하천의 유속 및 하상 등의 자료를 수집, 저장, 처리, 검색하고자 하는 요구가 증가하고 있다. ADCP를 이용하여 유속을 계측할 경우, 재래식 계측 방법인 봉부자를 이용한 방법, 프로펠러유속계를 이용하는 방법에 비해 빠르고 정밀한 자료를 수집할 수 있는 장점이 있지만 계측자료의 양이 방대해짐에 따라 자료의 저장, 관리와 처리가 힘든 단점이 있어 ADCP를 이용한 자료의 저장 및 관리 처리를 자동화하는 소프트웨어에 대한 수요가 증가하고 있다.이러한 상황에 맞춰 수자원 발전을 위한 미국 대학 협력단체인 CUAHSI(Consortium of University for the Advancement of Hydrologic Science)에서는 수자원정보화시스템(Hydrologic Information System; HIS)의 구축하기 위해 표준화된 수자원 관측자료 데이터베이스 구조인 ODM(Observation Data Model)을 개발한 바 있다. 최근에는 하천 단면과 같은 하천 측정자료를 송수신할 경우 사용할 수 있는 표준 자료 프로토콜인 RiverML을 개발하여 Beta 버전을 제공하고 있다. 따라서 본 연구에서는 하천 자료 및 모형의 공유를 목적으로 HydroShare의 일환인 수자원 관측자료 중 하천자료의 전송용 언어인 RiverML과 하천의 시공간적 수리동역학적 자료 구조인 Arc River를 기반으로 ADCP의 계측자료를 RiverML로 변환하는 기술과 변환된 결과를 토대로 2차원 및 3차원으로 표출하는 GIS기반 소프트웨어를 개발하였다.

• Journal of Korea Technology Innovation Society
• /
• v.21 no.3
• /
• pp.992-1020
• /
• 2018

The purpose of this study is to investigate the ways to enhance the creativity of R & D teams of government-funded research institutes through systematic empirical studies. For this purpose, a research model was established based on existing research on group creativity and verified through empirical studies. Specifically, This study first attempts to investigate the influence that team diversity, team cohesion, team autonomy and team efficacy have on team creativity. Second, it intends to verify the mediating effects of team efficacy between team characteristics and team creativity. An empirical study was conducted on 102 R & D teams of government-funded research institutes. In the team creativity measurement, the evaluation by the leaders and the self evaluation of the members were performed in parallel. This is to increase the accuracy of the evaluation and to compare the differences of the viewpoints of the two subjects. The result of the analysis demonstrated that team cohesion among the others had a positive influence on team creativity, and that team efficacy possessed certain positive qualities in mediating the relationship between team diversity, team autonomy, and team creativity. Based on these findings, this study discussed its academic implications as well as its practical limitations, and made suggestions on future research tasks that remain.