• 유통과학연구
• /
• 제14권1호
• /
• pp.93-102
• /
• 2016

Purpose - The purpose of paper is studying the static and dynamic side for long-term memory storage properties, and increase the explanatory power regarding the long-term memory process by looking at the long-term storage attributes, Korea Composite Stock Price Index. The reason for the use of GPH statistic is to derive the modified statistic Korea's stock market, and to research a process of long-term memory. Research design, data, and methodology - Level shifts were subjected to be an empirical analysis by applying the GPH method. It has been modified by taking into account the daily log return of the Korea Composite Stock Price Index a. The Data, used for the stock market to analyze whether deciding the action by the long-term memory process, yield daily stock price index of the Korea Composite Stock Price Index and the rate of return a log. The studies were proceeded with long-term memory and long-term semiparametric method in deriving the long-term memory estimators. Chapter 2 examines the leading research, and Chapter 3 describes the long-term memory processes and estimation methods. GPH statistics induced modifications of statistics and discussed Whittle statistic. Chapter 4 used Korea Composite Stock Price Index to estimate the long-term memory process parameters. Chapter 6 presents the conclusions and implications. Results - If the price of the time series is generated by the abnormal process, it may be located in long-term memory by a time series. However, test results by price fixed GPH method is not followed by long-term memory process or fractional differential process. In the case of the time-series level shift, the present test method for a long-term memory processes has a considerable amount of bias, and there exists a structural change in the stock distribution market. This structural change has implications in level shift. Stratum level shift assays are not considered as shifted strata. They exist distinctly in the stock secondary market as bias, and are presented in the test statistic of non-long-term memory process. It also generates an error as a long-term memory that could lead to false results. Conclusions - Changes in long-term memory characteristics associated with level shift present the following two suggestions. One, if any impact outside is flowed for a long period of time, we can know that the long-term memory processes have characteristic of the average return gradually. When the investor makes an investment, the same reasoning applies to him in the light of the characteristics of the long-term memory. It is suggested that when investors make decisions on investment, it is necessary to consider the characters of the long-term storage in reference with causing investors to increase the uncertainty and potential. The other one is the thing which must be considered variously according to time-series. The research for price-earnings ratio and investment risk should be composed of the long-term memory characters, and it would have more predictability.

• 유통과학연구
• /
• 제13권5호
• /
• pp.71-82
• /
• 2015

Purpose - The purpose of this study is to investigate risk price implied from the pricing kernel of Korean stock distribution market. Recently, it is considered that the quantitative easing programs of major developed countries are contributing to a reduction in global uncertainty caused by the 2007~2009 financial crisis. If true, the risk premium as compensation for global systemic risk or economic uncertainty should show a decrease. We examine whether the risk price in the Korean stock distribution market has declined in recent years, and attempt to provide practical implications for investors to manage their portfolios more efficiently, as well as academic implications. Research design, data and methodology - To estimate the risk price, we adopt a non-parametric method; the minimum norm pricing kernel method under the LOP (Law of One Price) constraint. For the estimation, we use 17 industry sorted portfolios provided by the KRX (Korea Exchange). Additionally, the monthly returns of the 17 industry sorted portfolios, from July 2000 to June 2014, are utilized as data samples. We set 120 months (10 years) as the estimation window, and estimate the risk prices from July 2010 to June 2014 by month. Moreover, we analyze correlation between any of the two industry portfolios within the 17 industry portfolios to suggest further economic implications of the risk price we estimate. Results - According to our results, the risk price in the Korean stock distribution market shows a decline over the period of July 2010 to June 2014 with statistical significance. During the period of the declining risk price, the average correlation level between any of the two industry portfolios also shows a decrease, whereas the standard deviation of the average correlation shows an increase. The results imply that the amount of systematic risk in the Korea stock distribution market has decreased, whereas the amount of industry-specific risk has increased. It is one of the well known empirical results that correlation and uncertainty are positively correlated, therefore, the declining correlation may be the result of decreased global economic uncertainty. Meanwhile, less asset correlation enables investors to build portfolios with less systematic risk, therefore the investors require lower risk premiums for the efficient portfolio, resulting in the declining risk price. Conclusions - Our results may provide evidence of reduction in global systemic risk or economic uncertainty in the Korean stock distribution market. However, to defend the argument, further analysis should be done. For instance, the change of global uncertainty could be measured with funding costs in the global money market; subsequently, the relation between global uncertainty and the price of risk might be directly observable. In addition, as time goes by, observations of the risk price could be extended, enabling us to confirm the relation between the global uncertainty and the effect of quantitative easing. These topics are beyond our scope here, therefore we reserve them for future research.

• 한국정보시스템학회지:정보시스템연구
• /
• 제27권3호
• /
• pp.123-140
• /
• 2018

Purpose The purpose of this study is to explore the optimal trading frequency which is useful for stock price prediction by using deep learning for charting image data. We also want to identify the appropriate time for accurate forecasting of stock price when performing pattern analysis. Design/methodology/approach In order to find the optimal trading frequency patterns and forecast timings, this study is performed as follows. First, stock price data is collected using OpenAPI provided by Daishin Securities, and candle chart images are created by data frequency and forecasting time. Second, the patterns are generated by the charting images and the learning is performed using the CNN. Finally, we find the optimal trading frequency patterns and forecasting timings. Findings According to the experiment results, this study confirmed that when the 10 minute frequency data is judged to be a decline pattern at previous 1 tick, the accuracy of predicting the market frequency pattern at which the market decreasing is 76%, which is determined by the optimal frequency pattern. In addition, we confirmed that forecasting of the sales frequency pattern at previous 1 tick shows higher accuracy than previous 2 tick and 3 tick.

• Journal of Information Technology Applications and Management
• /
• 제26권6호
• /
• pp.1-12
• /
• 2019

On the Internet age, the news is generated and distributed not only by traditional news media, but also by a variety of online news media, news platforms, content websites/content farms, and social media. Since it is an easy task to create and distribute news, some of these news reports may contain fake or false facts. In the end, the cyberspace is full of fake or false messages. People may wonder if these fake news actually influence our decision making. In this paper, we discussed a real case of fake news. In this case, a Taiwanese company used some fake news, advertorial news, and news placement to manipulate or influence its stock price and trade volume. We collected all news for the case company during a period of four years and five months (from January 2013 to May 2017). We analyzed the relationship between published news and stock price. Based on the analysis results, we conclude that we should not ignore the influence of news placement and fake business news on the stock price.

• 사물인터넷융복합논문지
• /
• 제8권1호
• /
• pp.1-10
• /
• 2022

본 연구는 IoT 관련 산업이 재무건전성을 확보하고, 코로나-19 종식 이후에 세계시장을 선점할 수 있는 기반을 마련하는데 목적이 있다. 이러한 연구를 통하여 IoT 관련 기업의 계량적 경영실태를 점검하였다. 또한, 주가변동과 관리종목 지정에 따른 재무비율의 관련성을 규명함으로써 기업의 부실에 선제적으로 대비하고자 하였다. 연구는 2019년부터 2020년까지 유가증권 시장에서 코스피와 코스닥에 상장되어 있는 502개의 기업으로 선정하였다. 통계분석 방법은 다중회귀분석, 차이분석, 로지스틱 회귀분석 등을 실시하였다. 연구 결과는 다음과 같다. 첫째, 코로나-19 이전과 이후에 따라 IoT 기업의 회계정보가 주가에 반영되는 영향력은 다르게 존재한다는 것을 알 수 있었다. 둘째, 코로나 이전과 이후에 따른 IoT 기업의 기말주가에서 차이가 있는 것으로 나타났다. 셋째, 코로나-19 이후에 주가변동에 따른 재무비율은 다르게 존재한다는 것을 알 수 있었다. 넷째, 코로나-19 이후에 관리종목 지정에 따른 재무비율은 다르게 존재한다는 것을 알 수 있었다. 이러한 연구결과를 통하여 IoT 기업의 재무건전성을 확보하고, 코로나-19 종식 이후에 세계시장으로 도약할 수 있는 기반을 마련하기 위한 몇 가지 제언을 하였다. 이러한 연구의 결과를 통하여 IoT 기업의 성장을 유도하고, 변화하는 금융시장에서 재무건전성을 담보할 수 있는 미래시대의 데카콘 기업으로 성장하는데 기여하길 기대한다.

• Asia pacific journal of information systems
• /
• 제30권4호
• /
• pp.719-740
• /
• 2020

The stock market changes continuously as new information emerges, affecting the judgments of investors. Online news articles are valued as a traditional window to inform investors about various information that affects the stock market. This paper proposed new ways to utilize online news articles with technical indicators. The suggested hybrid model consists of three models. First, a self-attention-based convolutional neural network (CNN) model, considered to be better in interpreting the semantics of long texts, uses news content as inputs. Second, a self-attention-based, bi-long short-term memory (bi-LSTM) neural network model for short texts utilizes news titles as inputs. Third, a bi-LSTM model, considered to be better in analyzing context information and time-series models, uses 19 technical indicators as inputs. We used news articles from the previous day and technical indicators from the past seven days to predict the share price of the next day. An experiment was performed with Korean stock market data and news articles from 33 top companies over three years. Through this experiment, our proposed model showed better performance than previous approaches, which have mainly focused on news titles. This paper demonstrated that news titles and content should be treated in different ways for superior stock price prediction.

• 한국건설관리학회논문집
• /
• 제11권5호
• /
• pp.41-52
• /
• 2010

리츠는 주식시장에 상장되어 있으면서 부동산 개발을 위한 자금조달의 성격과 부동산에 투자하는 특징도 있으므로, 주식 시장과 건설 및 부동산시장과 관계가 있을 것으로 예상할 수 있다. 본 연구에서는 리츠와 주식시장, 건설 및 부동산 경기와 관계된 지표들을 시계열 분석하여, 리츠와의 영향관계를 분석하였다. 시계열 분석은 백터자기회귀모형과 백터오차수정모형을 사용하였으며, 다음의 세 부분으로 분류하여 분석하였다. 첫째, 리츠와 건설 코스피 지수와의 관계를 분석한 결과, 건설 코스피 지수가 리츠에 영향을 주는 것으로 분석되었다. 둘째, 리츠와 건설경기 동행지수인 건축착공면적, 부동산 경기 지수인 오피스 임대지수와 주택매매가격지수와의 관계를 분석하였다. 각 지표들은 서로 인과관계는 없는 것으로 분석되었지만, 리츠와 주택매매가격지수는 서로에게 영향을 주는 것으로 분석되었다. 셋째, 리츠와 건설경기 선행지수인 건축허가면적의 관계를 분석하였다. 두 지표는 서로 인과관계가 없는 것으로 분석되었지만, 건축허가면적이 리츠에 영향을 미치는 것으로 분석되었다. 본 연구를 통해 리츠는 주식시장과 주택경기, 건설경기 선행지표인 건축허가 면적에 영향을 받지만, 건설경기 동행지표인 건축착공면적과 오피스 임대지수에는 상대적으로 영향을 작게 받는 것으로 분석되었다.

• Journal of the Korean Data Analysis Society
• /
• 제20권6호
• /
• pp.2759-2769
• /
• 2018

The behavioral finance view on the existence of asset pricing anomalies is based on two factors: investors' sentiment and limits to arbitrage. This paper tries to examine the effect of investors' sentiment on the stock price in the Korean stock market. In order to measure investors' sentiment, we constructed the sentiment index using principal component of five sentiment variables. By using sentiment index as an additional independent variable to three risk factors, impacts of the sentiment index on individual stocks and 25 portfolios sorted by BM-size are examined. Main results found are as follows: 1) not only all three risk factors show positive impacts on the return of individual stock, but also the sentiment index has a positive impact. SI alone explains 15% of individual return variation. 2) among four independent variables, the most important factor turned out to be the market risk factor and investors' sentiment has better explanatory power on stock price than the size effect. 3) after controlling the market risk factor, the coefficient of the sentiment index for the smallest size and highest book/market value portfolios is significantly positive. 4) all the coefficients of the sentiment index for 25 portfolios sorted by BM-size have significant positive value after controlling size or (and) value.

• 산업융합연구
• /
• 제21권1호
• /
• pp.87-93
• /
• 2023

주식 투자에서 매수와 매도의 타이밍을 결정하는 것은 주식 투자의 수익률 올리기 위해 가장 중요한 요인 중에 하나이다. 주식은 싸게 사서 비싸게 팔면 이익이 되지만, 비싸게 사서 싸게 팔면 손해가 된다. 주식의 가격을 결정하는 매수와 매도의 물량에 의해 가격이 결정이 되고, 매수와 매도는 기업실적, 경제지표와도 관련이 있다. CNN에서 제공하는 공포와 탐욕지수는 7가지 요소를 사용하고, 각 요소에 가중치를 부여하여 탐욕과 두려움으로 정의한 가중치 평균을 0~100 사이의 척도로 계산하여 매일 발표하고 있다. 지수가 0에 가까우면 주식시장 심리가 두려운것이고, 100에 가까우면 탐욕스러운 것이다. 따라서 미국 S&P 500 지수를 CNN 공포와 탐욕지수에 따른 매수와 매도를 할 경우 최대 수익률이 발생하는 매매 기준을 분석하여 최적의 매수와 매도 타이밍을 제시하여 주식투자에 수익률을 높일 수 있는 방안을 제시하고자 한다.

• 재무관리연구
• /
• 제22권1호
• /
• pp.37-69
• /
• 2005

본 연구에서는 자기주식 취득 뿐 아니라 자기주식 처분도 주주의 부에 영향을 미치는가와 취득목적 및 처분목적에 따라 주주의 부에 미치는 영향이 서로 다르게 나타나는가를 검증하였다. 실증분석 결과, 주가 안정 목적이나 이익소각 목적의 자기주식 취득 공시는 양(+)의 초과수익률을 주지만, 임직원에게 인센터브를 제공하기 위한 자기주식 취득 공시는 음(-)의 초과수익률이 나타남을 발견하였다. 또 임직원 인센티브용 자기주식 처분이나 만기로 인한 신탁계약 해지는 주가에 부정적인 영향을 주지만, 운영자금 조달이나 재무구조 개선을 위한 자기주식 직접처분은 주주의 부를 유의적으로 증가시키는 것으로 나타났다. 횡단면 분석에서도 자기주식 취득 및 처분은 그 목적에 따라 초과수익률에 영향을 주는 요인이 다름을 확인하였다. 본 연구의 결과는 자기주식 처분도 중요한 재무전략의 하나로 인식되어야 하며, 나아가 자기주식의 취득이나 처분에 관한 연구는 그 목적을 감안하고 접근해야 함을 시사한다.