• International Area Studies Review
• /
• v.22 no.4
• /
• pp.3-18
• /
• 2018

In this study, I examined capital market shock reaction effects of 29 OECD countries with the past 24 years sample period consisting of daily stock market return using T-GARCH model focused on volatility feedback hypothesis. US daily stock market return is used as a unique independent variable in this model in consideration of its characteristics of biggest market share and as an origin country of Global Financial Crisis. As a result, France, Finland, and Mexico in order are shown to be the strongest countries in the aspect of return spillovers from US. Canada, Mexico, and France are shown to be the highest countries in the aspect of explanatory power of model. The degrees of shock reaction are proved to be higher in order in Germany, Chile, Switzerland, and Denmark and those of downside shock reaction are seen higher in order in Greece, Great Britain, Australia, and Japan. Canada and Mexico belonging to NAFTA are shown to be higher in the return spillover from US and in the model explanatory power, but they are shown to be lower in the impact of shock reaction, suggesting that regional distance effect or gravity theory cannot be applied to financial spillovers any longer. In the analysis of subsample period of Global Financial Crisis, north American three countries do not show any consistent results as in the full sample period but shock reaction in the European countries are shown to record stronger, suggesting that shocks from US in the Crisis Times are transferred mainly to European region.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.103-128
• /
• 2021

Recently, investors' interest and the influence of stock-related information dissemination are being considered as significant factors that explain stock returns and volume. Besides, companies that develop, distribute, or utilize innovative new technologies such as artificial intelligence have a problem that it is difficult to accurately predict a company's future stock returns and volatility due to macro-environment and market uncertainty. Market uncertainty is recognized as an obstacle to the activation and spread of artificial intelligence technology, so research is needed to mitigate this. Hence, the purpose of this study is to propose a machine learning model that predicts the volatility of a company's stock price by using the internet search volume of artificial intelligence-related technology keywords as a measure of the interest of investors. To this end, for predicting the stock market, we using the VAR(Vector Auto Regression) and deep neural network LSTM (Long Short-Term Memory). And the stock price prediction performance using keyword search volume is compared according to the technology's social acceptance stage. In addition, we also conduct the analysis of sub-technology of artificial intelligence technology to examine the change in the search volume of detailed technology keywords according to the technology acceptance stage and the effect of interest in specific technology on the stock market forecast. To this end, in this study, the words artificial intelligence, deep learning, machine learning were selected as keywords. Next, we investigated how many keywords each week appeared in online documents for five years from January 1, 2015, to December 31, 2019. The stock price and transaction volume data of KOSDAQ listed companies were also collected and used for analysis. As a result, we found that the keyword search volume for artificial intelligence technology increased as the social acceptance of artificial intelligence technology increased. In particular, starting from AlphaGo Shock, the keyword search volume for artificial intelligence itself and detailed technologies such as machine learning and deep learning appeared to increase. Also, the keyword search volume for artificial intelligence technology increases as the social acceptance stage progresses. It showed high accuracy, and it was confirmed that the acceptance stages showing the best prediction performance were different for each keyword. As a result of stock price prediction based on keyword search volume for each social acceptance stage of artificial intelligence technologies classified in this study, the awareness stage's prediction accuracy was found to be the highest. The prediction accuracy was different according to the keywords used in the stock price prediction model for each social acceptance stage. Therefore, when constructing a stock price prediction model using technology keywords, it is necessary to consider social acceptance of the technology and sub-technology classification. The results of this study provide the following implications. First, to predict the return on investment for companies based on innovative technology, it is most important to capture the recognition stage in which public interest rapidly increases in social acceptance of the technology. Second, the change in keyword search volume and the accuracy of the prediction model varies according to the social acceptance of technology should be considered in developing a Decision Support System for investment such as the big data-based Robo-advisor recently introduced by the financial sector.

• The Korean Journal of Financial Management
• /
• v.17 no.1
• /
• pp.91-110
• /
• 2000

충격이 경제에 가해질 때 이 충격이 경제 내에 일시적으로 존속하는 경우도 있고 이 충격이 영구히 존속하는 경우도 있다. 이 양극단 사이의 과정도 존재할 수 있다. 이것을 표상한 것이 stopbreak 과정이다. 충격의 효과가 영구적 효과와 일시적 효과 사이에서 파동하는 시계열을 모형화한 것이 이 과정인 것이다. 이 과정에서는 일정한 기간에는 영구적인 평균이동이 발생하여 구조변화가 발생한다. 다른 기간에 발생하는 충격은 그 효과가 급속히 소멸한다. 밀접한 관계를 맺고 있는 두 주가의 비율은 한 주가의 변동이 제시하는 것을 분석하고 이것을 이용하여 다른 주가를 예측할 수 있는 정보를 제공한다. 한 주가의 변동이 발생하면 이 두 주가의 비율은 변동한다. 그러나 한 주가의 변동의 정보성이 인정되어 이 정보가 다른 주가에 반영되어 조정되면 두 주가의 비율은 변동이전의 수준으로 회귀할 것이다. 변동이 영구적이면 두 주가비율은 동일한 수준을 유지할 것이다. 반면 다른 주가에 영향을 미치지 못하는 정보이면 두 주가의 비율은 변동된 상태에서 지속될 것이다. 일정기간은 영구적 구조변화가 발생하고 그 이외의 기간에는 구조 변화가 발생하지 않고 있는 것이다. 따라서 stopbreak 과정을 사용하여 정확한 예측을 수행할 수 있다. 주가지수들이 stopbreak 과정에 의하여 생성되고 있음이 발견되었다. 즉 주가지수들은 확률적 영구구조변화가 발생하고 있는 시계열들이다. 종합주가지수/제조업지수 역시 확률적 영구구조변화를 가지는 stopbreak 과정에 의하여 생성되고 있음이 밝혀졌다. 이 과정을 실제에 적용하여 주가의 움직임을 파악하면 예측이 가능하다. 특히 연관성이 깊은 두 주식의 주가비율을 사용할 때 효과적이라 할 수 있다.

• The Journal of the Korea Contents Association
• /
• v.18 no.10
• /
• pp.490-497
• /
• 2018

In this study, we examined whether common idiosyncratic volatility(CIV), a risk factor for idiosyncratic volatility, can be evaluated as a pricing factor. The sample is listed on the Korea Exchange. The analysis period is 288 months from July 1992 to June 2016. The main results of this study are as follows. First, in the empirical verification of the market excess returns of the testing portfolios, the difference in the return on the CIV factor sensitivity difference was statistically significant. In other words, we confirmed that there is a risk premium for CIV factors. Second, CAPM, FF3 factor model, and FF5 factor model do not explain the risk premium for CIV factors, whereas factor models that add CIV factors explain the risk premium for CIV factors. In other words, the CIV factor can be evaluated in terms of pricing factors.

• Korean journal of communication and information
• /
• v.34
• /
• pp.244-274
• /
• 2006

To explore the social construction of the concept of leadership, image of media mogul depicted in the popular business newspaper, the Wall Street Journal, was analyzed. Then, the reconstructed image of the CEO was compared with the firm's stock price change to see their relationship, if any. This paper focused on the case of Steve Case (previous chairman of AOL Time Warner), who was the leader of the world largest media company. The period for the analysis was three years and five months from his inauguration(January 2000) to the resignation(May 2003). In general, CEO of a firm represents the firm itself. Thus, the image of the CEO is highly transcends to the image of the firm as well. Consequently, the image of CEO might have an impact on the firm's performance. Since business newspaper works as one of the most important information intermediaries in the stock market, the image of CEO constructed in the newspaper might be a critical indicator for the investors. The results revealed that media coverage of Steve Case was commensurate with the financial performance, particularly stock price change of the AOL Time Warner.

• The Journal of Society for e-Business Studies
• /
• v.24 no.4
• /
• pp.109-118
• /
• 2019

As a result of the United States (U.S) -China trade conflict, the recent instability of the stock market has led many people to invest in Bitcoin, a commodity that many previous studies have interpreted as a safe asset. However, recent Bitcoin market price fluctuations suggest that the asset's stability stems from speculative purchasing trends. Therefore, classifying the characteristics of Bitcoin assets can be an important reference point in analyzing relevant accounting information. To determine whether Bitcoin is a safe asset, this study analyzed the correlation between Bitcoin and economic indicators to verify whether gold and Bitcoin responded similarly in time series analyses. These show that the regression explanatory power between the price of gold and bitcoin is low, thus no relation between the two assets could be drawn. Additionally, the Granger causality analyses of six individual economic variables and Bitcoin did not establish any notable causality. This can be interpreted that short-term price fluctuations have a significant impact on the nature of Bitcoin as an asset.

• Journal of Digital Convergence
• /
• v.13 no.11
• /
• pp.45-55
• /
• 2015

This study used for KOSPI, KOSDAQ, entertainment culture and digital contents index that is related to cultural contents industry. There was investigated the each stock price index and return trends for a total 597 weeks to July 2015 from March 2004. They looked the content-related stocks about investment worth to comparative analysis the return, volatility, correlation, synchronization phenomena etc. of each stock index. When we saw the growth potential of the cultural contents industry forward, looked forward to the investment possibility of related stocks. Analysis Result cultural content related stocks showed a higher rate after the last 2008 global financial crisis. Recent as high interest in the cultural contents industry, we could see that the investment merit increases slowly. In the future, the cultural content industry is expected to continue to evolve. The increase of investments value in the cultural content related businesses is much expectation.

• The Korean Journal of Financial Studies
• /
• v.10 no.1
• /
• pp.191-214
• /
• 2004

VaR에 의한 금융위험의 측정은 국제결제은행 바젤위원회의 내부모델 허용에 힘입어 금융산업에서 표준방식으로 확고한 입지를 차지하고 있다. 본 연구에서는 한국주식시장포트폴리오를 거래투자자산으로 보유한 경우의 VaR를 극단치이론에 입각하여 측정하고 이의 성과를 RiskMetrics의 성과와 비교하여 검토하였다. GPD의 모수적 추정에 의한 VaR의 사후검정결과는 표본내 사후검정이나 표본외 사후검정에서 어떤 신뢰수준에서도 기대되는 범위와 크게 벗어나지 않은 안정된 결과를 보였다. RiskMetrics의 EWMA방식도 역시 표본내와 표본외 사후검정 어느 경우에나 기대되는 범위에서 크게 벗어나지 않았지만 높은 신뢰수준에서는 그 성과가 GPD VaR에 비하여 상대적으로 불안정하였으며 위험의 과소평가 성향을 확인할 수 있었다. 비모수적 GEV추정에 입각한 VaR의 경우에는 위험을 과대평가하고 지나치게 보수적인 성향을 나타내었다. GPD의 모수적 접근에 의한 VaR 측정은 다양한 신뢰수준에서 정확한 검정결과를 보여주고 있으며, 시간적 흐름에 따르는 VaR의 행태도 지나친 변동성을 보이지 않아 외부규제 및 내부통제를 위한 금융위험의 측정지표로서 실용적인 가치가 있음을 확인할 수 있다.

• The Korean Journal of Financial Management
• /
• v.24 no.3
• /
• pp.91-131
• /
• 2007

In the paper, the effects of sidecar on index arbitrage trading and non-index arbitrage trading in the Korean stock market are examined. The analyses of return, volatility, and liquidity dynamics illustrate that there are no distinct differences for index arbitrage group and non-index arbitrage group surrounding the sidecar events. For further analysis, we construct pseudo-sidecar sample and analyse the effects of the actual sidecar and pseudo-sidecar on arbitrage sample and non-index arbitrage sample. The result of analysis using pseudo-sidecar shows that the differences between index arbitrage group and non-index arbitrage group are larger in pseudo-sidecar sample than in actual sidecar sample. This means that former results can be explained by temporary order clustering in one side before and after the event. Sidecar has little effect on non-index arbitrage group, however, it has relatively large effect on arbitrage group. These results imply that it needs to redesign the sidecar system of the Korean stock market which applies for all program trading including arbitrage and non-index arbitrage trading.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.147-155
• /
• 2022

In this study, we developed a system to dynamically balance a daily stock portfolio and performed trading simulations using gradient boosting and genetic algorithms. We collected various stock market data from stocks listed on the KOSPI and KOSDAQ markets, including investor-specific transaction data. Subsequently, we indexed the data as a preprocessing step, and used feature engineering to modify and generate variables for training. First, we experimentally compared the performance of three popular gradient boosting algorithms in terms of accuracy, precision, recall, and F1-score, including XGBoost, LightGBM, and CatBoost. Based on the results, in a second experiment, we used a LightGBM model trained on the collected data along with genetic algorithms to predict and select stocks with a high daily probability of profit. We also conducted simulations of trading during the period of the testing data to analyze the performance of the proposed approach compared with the KOSPI and KOSDAQ indices in terms of the CAGR (Compound Annual Growth Rate), MDD (Maximum Draw Down), Sharpe ratio, and volatility. The results showed that the proposed strategies outperformed those employed by the Korean stock market in terms of all performance metrics. Moreover, our proposed LightGBM model with a genetic algorithm exhibited competitive performance in predicting stock price movements.