• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.51-59
• /
• 2024

This study examines the relationship between the release of the news and the individual stock returns. Investors utilize a variety of information sources to maximize stock returns when establishing investment strategies. News companies publish their articles based on stock recommendation reports of analysts, enhancing the reliability of the information. Defining release of a stock-recommendation news article as an event, we examine its economic impacts and propose a binary classification model that predicts the stock return 10 days after the event. XGBoost and LightGBM models are applied for the study with accuracy of 75%, 71% respectively. In addition, after categorizing the recommended stocks based on the listed market(KOSPI/KOSDAQ) and market capitalization(Big/Small), this study verifies difference in the accuracy of models across four sub-datasets. Finally, by conducting SHAP(Shapley Additive exPlanations) analysis, we identify the key variables in each model, reinforcing the interpretability of models.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.123-138
• /
• 2017

Since the stock market is driven by the expectation of traders, studies have been conducted to predict stock price movements through analysis of various sources of text data. In order to predict stock price movements, research has been conducted not only on the relationship between text data and fluctuations in stock prices, but also on the trading stocks based on news articles and social media responses. Studies that predict the movements of stock prices have also applied classification algorithms with constructing term-document matrix in the same way as other text mining approaches. Because the document contains a lot of words, it is better to select words that contribute more for building a term-document matrix. Based on the frequency of words, words that show too little frequency or importance are removed. It also selects words according to their contribution by measuring the degree to which a word contributes to correctly classifying a document. The basic idea of constructing a term-document matrix was to collect all the documents to be analyzed and to select and use the words that have an influence on the classification. In this study, we analyze the documents for each individual item and select the words that are irrelevant for all categories as neutral words. We extract the words around the selected neutral word and use it to generate the term-document matrix. The neutral word itself starts with the idea that the stock movement is less related to the existence of the neutral words, and that the surrounding words of the neutral word are more likely to affect the stock price movements. And apply it to the algorithm that classifies the stock price fluctuations with the generated term-document matrix. In this study, we firstly removed stop words and selected neutral words for each stock. And we used a method to exclude words that are included in news articles for other stocks among the selected words. Through the online news portal, we collected four months of news articles on the top 10 market cap stocks. We split the news articles into 3 month news data as training data and apply the remaining one month news articles to the model to predict the stock price movements of the next day. We used SVM, Boosting and Random Forest for building models and predicting the movements of stock prices. The stock market opened for four months (2016/02/01 ~ 2016/05/31) for a total of 80 days, using the initial 60 days as a training set and the remaining 20 days as a test set. The proposed word - based algorithm in this study showed better classification performance than the word selection method based on sparsity. This study predicted stock price volatility by collecting and analyzing news articles of the top 10 stocks in market cap. We used the term - document matrix based classification model to estimate the stock price fluctuations and compared the performance of the existing sparse - based word extraction method and the suggested method of removing words from the term - document matrix. The suggested method differs from the word extraction method in that it uses not only the news articles for the corresponding stock but also other news items to determine the words to extract. In other words, it removed not only the words that appeared in all the increase and decrease but also the words that appeared common in the news for other stocks. When the prediction accuracy was compared, the suggested method showed higher accuracy. The limitation of this study is that the stock price prediction was set up to classify the rise and fall, and the experiment was conducted only for the top ten stocks. The 10 stocks used in the experiment do not represent the entire stock market. In addition, it is difficult to show the investment performance because stock price fluctuation and profit rate may be different. Therefore, it is necessary to study the research using more stocks and the yield prediction through trading simulation.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.12
• /
• pp.465-471
• /
• 2021

The study investigates the dynamic correlation of cryptocurrencies and equity in Vietnam and tests the safe-haven property of them from the perspective of the stock market in Vietnam during the pandemic crisis by applying the dynamic conditional correlation (DCC) GARCH model and regression with a dummy variable, respectively. This study employs time series data on the daily dataset from September 2014 to September 2021 with the focus on the two most popular cryptocurrencies - Bitcoin and Litecoin. The results show that the dynamic conditional correlations between cryptocurrencies and equity in Vietnam increased during the pandemic, however, in most periods, positive dynamic correlations often dominate. Besides, the regression results also indicate that Bitcoin and Litecoin act as weak safe-haven investments for stocks in Vietnam during the COVID-19 turmoil. They are more suitable for diversification purposes although the dynamic correlations between them and the stock index in Vietnam vary stronger during the pandemic crisis than before. The findings of this study suggest that in the period of pandemic crisis, cryptocurrencies are not concerned as effective safe-haven assets for stock in Vietnam. Instead, cryptocurrencies are only playing a potential role in diversification benefit in this economy.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.7
• /
• pp.383-391
• /
• 2021

This study examines the connectedness between the number of COVID-19 cases in Thailand and trading value among investors in the Stock Exchange of Thailand. Daily data of COVID-19 cases and trading value were sourced from the Thailand ministry of public health and the Stock Exchange of Thailand, from January 12, 2020 to May 11, 2021. This study applies a multiple linear regression analysis to explain the relationship between variables. Empirical evidence clearly shows that the volatility of trading value was affected by COVID-19's new, confirmed, and deaths cases within the first pandemic period more than during the second pandemic period. Nevertheless, during the third pandemic period there is no evidence that the new, confirmed, and deaths cases significantly influenced trading value. Furthermore, the results show that COVID-19's new and deaths cases have a negative coefficient that indicated the trading value-buy/sell decreased in response to COVID-19's new and deaths cases, whereas the confirmed COVID-19 cases have a positive coefficient that indicated the trading value-buy/sell increased in response to COVID's confirmed cases. In summary, this study suggests that the number of COVID-19 cases have a significant impact on the trading value in the short term more than in the intermediate and long term.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.5
• /
• pp.409-419
• /
• 2022

This paper examines the post-IPO price volatility in the first trading days after the IPO of SOEs that carry out equitization, on a sample of 76 IPOs on the Hanoi Stock Exchange (Vietnam) in the period 2013-2018. Oversubscription rate, firm size, issuance size, internal equity ownership, and listing delay are all factors that influence IPO price volatility in a primitive stock market. The results showed that the average initial market-adjusted return for the first three trading days was -11.95%; -9.58% and -7.29% and the level of price volatility is related to the rate of oversubscription and company size. Issuance price, issuance size, internal equity holdings, and listing delay do not seem to contribute significantly to post-IPO share prices. Individual investors based their valuation on information released during and after the IPO. In general, the number of IPOs that yield positive and negative returns in the first trading days is about the same, indicating that the two phenomena of undervaluation and overvaluation still occur in the process of valuing shares of Vietnamese SOEs for IPOs.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.303-304
• /
• 2021

In the 21st century, as we enter the Fourth Industrial Revolution, research in various fields utilizing big data is being conducted, and innovative and useful technologies are constantly emerging in the world. Among several technologies recently in the big data era, among various fields utilizing some algorithms of artificial intelligence, it shines in the field of finance and is used for pin tech, financial fraud detection and risk management, etc., and recently Even in the booming stock market, it is used for investment prediction and investment factor analysis using artificial intelligence algorithm models. In this paper, we plan to investigate various research cases and investigate trends in how they are used in the stock market through artificial intelligence that utilizes big data.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.06a
• /
• pp.399-408
• /
• 2001

This paper presents a simultaneous optimization approach of case-based reasoning (CBR) using a genetic algorithm(GA) for the prediction of stock price index. Prior research suggested many hybrid models of CBR and the GA for selecting a relevant feature subset or optimizing feature weights. Most studies, however, used the GA for improving only a part of architectural factors for the CBR system. However, the performance of CBR may be enhanced when these factors are simultaneously considered. In this study, the GA simultaneously optimizes multiple factors of the CBR system. Experimental results show that a GA approach to simultaneous optimization of CBR outperforms other conventional approaches for the prediction of stock price index.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.3
• /
• pp.79-85
• /
• 2016

In today's fast-paced capitalistic society, a primary concern is whether to invest capital in any way to increase profits. In recent years, many companies have emphasized ethics and practiced corporate social responsibility activities. These activities are not only required to have at the end of the company. Bringing the ultimate goal of profit maximization is one way to contribute to the development of society and the economy. Investors are aware of corporate social responsibility activities and have begun to reflect this in their investments. We studied the behavior of a newly incorporated company's stock price on the KRX SRI Index using a scale that indicates the level of social responsibility for companies in the domestic stock market. Socially responsible investment involves an excellent company that looks out and looks for additional effects on the stock price of imports and improves the reliability of investors through an event study. The results show that the company we examined has a positive impact on the market. This study confirms the hypothesis that additional stock market reaction will occur when superior companies are newly incorporated in the KRX SRI Index and gain investors' trust. The results demonstrate that becoming a newly incorporated corporation in the KRX SRI Index is positive information to investors.

• International Area Studies Review
• /
• v.13 no.2
• /
• pp.277-297
• /
• 2009

This paper empirically investigates a long-run and short-run equilibrium relationships for exchange rate and stock prices in Korea and Japan from January 1998 to July 2008. Because using monthly data in my study, analyzes unit root test and VEC model including seasonality to overcome bias that happen in seasonal adjustment. The empirical evidence suggests that exists strong evidence supporting the long-run cointegration relationships between exchange rates and stock prices of the Korea and Japan. This implies that it is possible to predict one market from another for both countries, which seems to violate the efficient market hypothesis. In the long-run a negative relationship running from the KRW/JPY real exchange rate to the stock prices of Korea strongly argues for the traditional approach.

• Management & Information Systems Review
• /
• v.29 no.2
• /
• pp.97-118
• /
• 2010

This paper explores the mean and volatility spillover effects among Chinese, Korean, and the U.S. stock markets during the Asian and global financial crises. We found that, during the Asian Financial crisis, there was no mean spillover effect to the Chinese stock markets. However, there were reciprocal mean spillover effects between the U.S. and the Korean market. This implies that Korean market was open, while Chinese market was secluded from the international financial market at that time. The negative volatility spillover effect between the U.S. and China reinforces this finding. During the global financial crisis, there was reciprocal mean spillover effect between the U.S. and China, and between the U.S. and Korea. This may reflect the fact that Chinese market has opened to the international financial market. However, the volatility spillover effect does not exist between China and the U.S., while the U.S. and Korea has reciprocal volatility spillover effect to each other. These findings may imply that China is still in the process of opening her stock market to international investors.