South Korea's Stock Research Articles

Practical Application of Deep Reinforcement Learning to Optimal Trade Execution

Although deep reinforcement learning (DRL) has recently emerged as a promising technique for optimal trade execution, two problems still remain unsolved: (1) the lack of a generalized model for a large collection of stocks and execution time horizons; and (2) the inability to accurately train algorithms due to the discrepancy between the simulation environment and real market. In this article, we address the two issues by utilizing a widely used reinforcement learning (RL) algorithm called proximal policy optimization (PPO) with a long short-term memory (LSTM) network and by building our proprietary order execution simulation environment based on historical level 3 market data of the Korea Stock Exchange (KRX). This paper, to the best of our knowledge, is the first to achieve generalization across 50 stocks and across an execution time horizon ranging from 165 to 380 min along with dynamic target volume. The experimental results demonstrate that the proposed algorithm outperforms the popular benchmark, the volume-weighted average price (VWAP), highlighting the potential use of DRL for optimal trade execution in real-world financial markets. Furthermore, our algorithm is the first commercialized DRL-based optimal trade execution algorithm in the South Korea stock market.

ON THE RELATIONSHIP BETWEEN ECONOMIC POLICY UNCERTAINTY, GEOPOLITICAL RISK AND STOCK MARKET RETURNS IN SOUTH KOREA: A QUANTILE CAUSALITY ANALYSIS

In this research, we assess the influence of geopolitical risk (GPR), exchange rate (EXCH) and economic policy uncertainty (EPU) on South Korea stock market. Using monthly dataset covering the period from 1997 to 2021, we utilized the novel non-parametric causality-in-quantiles test initiated by Balcilar et al. (2017) to assess these associations. This study discovered that the effect of macroeconomic shocks in South Korea is diverse across the stock market, implying that the influence of these shocks is not consistent across the stock market in South Korea. Furthermore, this study revealed that the causal influence of EPU, GPR on the stock market is visible in mean and variance. Nonetheless, the causal influence of EXCH on the stock market can only be seen in the mean, with no indication of causation in the variance. We consider that these results are significant to South Korean stock market investors for the purposes of foreign portfolio diversification and establishing investing strategies during times of economic uncertainty.

Efficient one asset replacement scheme for an optimized portfolio

<abstract><p>The traditional mean-variance portfolio optimization models in practice have suffered from complexity and heavy computation loads in the process of selecting the best assets for constructing a portfolio. If not, they are considerably departed from the theoretically optimized values. In this work, we develop the optimized portfolio investment strategy in which only one asset substitution occurs when re-balancing a portfolio. To do this, we briefly look into a quadratically constrained quadratic programming (QCQP), which has been well-studied for the non-negative solution. Based on the quadratic programming, an efficient scheme is presented for solving the large-scale inverse problem. We more precisely update the rank of an inverse matrix, so that the optimal solution can be easily and quickly obtained by our proposed scheme.</p> <p>Various numerical and practical experiments are presented to demonstrate the validity and reliability of our scheme. Our empirical application to the U.S. and South Korea stock markets is tested and highlighted. Moreover, comparisons of a random allocation strategy and our proposed scheme reveal the better performance in the lower risks and higher expected returns obtained by our scheme.</p></abstract>

Stock market comovements: Evidence from the COVID-19 pandemic

The COVID-19 pandemic shock has harmed the US and East Asian stock markets. Focusing on measuring the inherent correlation, this paper employs a GARCH-Copula CoVaR approach to address the debate on the extreme risk spillovers from the US to China, Japan, Hong Kong, and South Korea stock returns. The results show a large spillover effect from the US to East Asian stock markets. Compared to the tranquil period, these spillovers become stronger in the COVID-19 period. The findings show that indirect spillovers on the Chinese stock market are heavier than direct spillovers, and impacts deluge only via Hong Kong. The study contrasts spillover’ features of the US COVID-19 shock and the Chinese 2015 crisis. These findings provide useful support for policymakers and risk managers involved in the East Asian stock markets.

CULTURAL AND NON-CULTURAL HOLIDAY EFFECT IN JAPANESE AND SOUTH KOREA STOCK MARKETS

This paper investigated the existence of cultural and non-cultural holiday effect in Japanese and South Korea stock markets consisting of four selected stock indexes which are Nikkei 225, JASDAQ, KOSDAQ and KOSPI. Descriptive statistics and Ordinary Least Square (OLS) with dummy variables are adopted to examine the average returns and associated with the cultural and non-cultural holiday effect behavior. It is found that post-holiday and cultural post-holiday effects happened in Nikkei 225 while KOSDAQ only showed cultural post-holiday effect. On the other hand, insignificant holiday effect was found in JASDAQ and KOSPI. This holiday and cultural influences can be explained with the arguments from the trading behavior where both countries have their own cultural, own nation holidays and traditional days affecting the trading patterns in the stock markets.

Who Benefitted From the PyeongChang Olympic Announcement? Evidence From the South Korean Stock Market

Understanding the market effects of Olympic host announcements is popular in academic research. Contrary to prior studies, announcing PyeongChang as the 2018 host had a positive effect on South Korea's Stock Market, with conservative estimates suggesting a peak of +3.8% during the 15 trading days post announcement (an increase equivalent to $34.962 billion). The degree to which firms benefitted varied by industry and lifecycle stage. Older and lower-growth financial and information technology firms saw larger abnormal returns compared to other firms. These findings suggest that academics and investors pay greater attention to idiosyncratic price adjustments to systematic market shocks.

Idiosyncratic volatility and interruption mechanisms in South Korean stock markets

PurposeThe purpose of this study is to examine how the volatility interruption (VI) mechanisms affect idiosyncratic volatilities in Korean stock markets.Design/methodology/approachCollecting the South Korea Stock Market (KOSPI) data from June 15, 2015 to March 31, 2019, we collect each residual, , from three different estimated models: capital asset pricing model (CAPM), FF3 and FF5. To estimate the conditional idiosyncratic volatility, the authors employ two conditional time-varying measurements: GARCH and TGARCH.FindingsThe results show that the conditional idiosyncratic volatility increases when stock prices reach the upper and lower static limits, indicating the implementation of adopting static VI mechanism neither stabilize market conditions nor reduce excess volatility along with the existence of price limits.Originality/valueAlthough market regulators and policymakers improve market conditions with the advanced VI mechanism, the empirical results show the adverse effect of the mechanism. Not allowing investors to earn above average returns without accepting above average risks makes Korean stock markets inefficient along with advanced VI mechanisms.

The Effect of the COVID-19 Pandemic on South Korea's Stock Market and Exchange Rate.

This study examines COVID‐19 pandemic effects on the stock market and exchange rate of South Korea. With daily data from January 2, 2019 to August 31, 2020, we show that a new infection spike increases stock price index volatility and decreases foreign investors' holdings of domestic stocks, and indirectly leads to the depreciation of the South Korean won. We indicate that investors may have repurchased the South Korean won seven days after an infection spike, thereby slightly increasing its value. We also find that the Bank of Korea's foreign exchange intervention had a short‐run effect with a limited impact. The intervention did not have a significant effect on exchange rate volatility.

COVID-19 and the Financial Markets’ Volatility and Returns

The study is undertaken to investigate the impact of COVID-19 on the Financial Markets ‘Volatility from the period April 2020 to June 2020. Ten countries namely Pakistan, USA, China, UAE, UK, Spain, France, South Korea, Switzerland, and the Netherlands were selected. Our daily data comes from the WHO situation reports (COVID-19 statistics) and Pakistan, USA, UK, UAE, China, France, Netherlands, Switzerland’s, Spain, and South Korea Stock Exchange Indices database, respectively. We use the KSE-100, S&P 500, FTSE 100, SE 50, AEX, ADX, IBEX, FCHI, KRX, and SSMI 3-month realized volatility index as a proxy for the Pakistan financial markets’ volatility. We test a simple Ordinary Least Squares (OLS) regression investigating the new coronavirus impact on the financial volatility and we use a stepwise procedure. Independent variables included Global COVID-19 Confirm case, Fatality, Country COVID-19 new case, Country Fatality, and dependent variable included country’s market volatility, and market returns. Control variables of the country’s Exchange and Interest rate were also included. The study design is descriptive and analytical using the quantitative method with the application of Eviews. The results suggested that the Global COVID new case seems to have a significant negative impact on the country's market volatility, however, global fatality seems to increase market volatility. Country-specific cases seem to negatively affect that country's volatility however, country-specific fatality doesn’t seem to be significantly impacting volatility. Apart from that, interest and exchange rates seem to increase the volatility. However, the effect of these variables on returns remained insignificant. The findings of this research provide policy implications to investors and policymakers indicating that pandemics can significantly perpetrate business economics.

Asian Stock Markets Analysis: The New Evidence from Time-Varying Coefficient Autoregressive Model

In financial economics studies, the autoregressive model has been a workhorse for a long time. However, the model has a fixed value on every parameter and requires the stationarity assumptions. Time-varying coefficient autoregressive model that we use in this paper offers some desirable benefits over the traditional model such as the parameters are allowed to be varied over-time and can be applies to non-stationary financial data. This paper provides the Monte Carlo simulation studies which show that the model can capture the dynamic movement of parameters very well, even though, there are some sudden changes or jumps. For the daily data from January 1, 2015 to February 12, 2020, our paper provides the empirical studies that Thailand, Taiwan and Tokyo Stock market Index can be explained very well by the time-varying coefficient autoregressive model with lag order one while South Korea's stock index can be explained by the model with lag order three. We show that the model can unveil the non-linear shape of the estimated mean. We employ GJR-GARCH in the condition variance equation and found the evidences that the negative shocks have more impact on market's volatility than the positive shock in the case of South Korea and Tokyo.

Does Nuclear Uncertainty Threaten Financial Markets? The Attention Paid to North Korean Nuclear Threats and Its Impact on South Korea's Financial Markets

We explore how investor attention paid to dangerous nuclear tests influences financial market outcomes. To measure the attention paid to North Korean nuclear threats, we introduce a weekly Google search volume index for keywords on North Korean nuclear events. Using a time‐varying structural vector autoregression model with block exogeneity restrictions, we find that investor attention paid to nuclear threats has heterogeneous effects on South Korea's stock prices across industries and over time: attention on only the first nuclear test was negatively related to the stock price index, which vanished thereafter. Moreover, the investor attention paid to the nuclear risk reduced stock prices, especially in the banking industry, during the entire sample period.

What Drives Stock Returns in South Korea?

We comprehensively investigate what drives stock returns in South Korea stock market which has been one of the most important emerging markets. Unlike the USA market and other developed markets, the well-known cash-flow yield, dividend yield, earnings yield and return reversal factors are not significant pricing factors for stocks in South Korea while momentum factor has a significant and negative pricing premium. We also find that GDP growth is a systematic pricing factor across stocks after controlling for market, value, and size factors. The pricing premium of GDP growth is significantly positive and consistent with Merton’s (1973) ICAPM because economic growth provides positive investment opportunities to investors. For cross-sectional stock return predictability, our Fama-MacBath (1973) regressions show that a stock’s book-to-market ratio, cash-low yield, dividend yield and return reversal are significant predictors at 1% level after controlling for market, value, size, momentum and GDP factors.

Pengaruh krisis keuangan global terhadap indeks harga saham gabungan regional asia dan bisnis di indonesia

Results of analysis of research data proving that the global financial crisis is significantly affecting the Asia Regional Stock Price Index and the Asia Regional Stock Price Index significantly affect business activities in Indonesia, but the global financial crisis did not significantly affect business activities in Indonesia and simultaneous Global Financial Crisis and the Asia Regional Stock Price Index did not significantly affect the Business activities in Indonesia. This means that business activities in Indonesia are more influenced by the Regional Asia Stock Price Index compared to the direct impact of the global financial crisis. Data analysis tool using the Structural Equation Model (SEM) using Lisrel Software 8.8. Observations were made at the end of each month from January 2004 until June 2010. This study used an exogenous latent variable (the Global Financial Crisis) and two endogenous latent variables (namely JCI Asia Regional and Business in Indonesia). The Global Financial Crisis is measured by two indicator variables namely World Inflation and the Stock Market U.S. Index. JCI Asia Regional measured by four indicator variables namely the China Stock Price Index (Shanghai), Japan Stock Price Index (Nikkei), South Korea Stock Price Index (Kospi), and India Stock Price Index (Bombay), whereas Business in Indonesia is measured by two indicator variables namely the Indonesia Stock Price Index (BEI) and Indonesia's inflation.

An Event Study on the Effects of North Korea Risks on South Korea‘s Stock Market

There have always been North Korea Risks in South Korea stock market since its opening. Some studies have concluded that it does not have a substantial impact on South Korea’s economy due to chronic geopolitical risks, while others have argued it has had an impact. However, in light of the Efficient Market Hypothesis (EMH) it can be argued that both opinions view that information about North Korea Risks affects stock markets and that stock prices react to it. This study analyzed the effects of North Korea Risks on South Korea’s stock market using event study methodology empirically, and it tested the semi-strong EMH-a market in which prices always fully reflect available information. The research results are following: First of all, North Korea Risks have an impact on South Korea’s stock market and the data was statistically significant. In particular, stock market already reflected information about the forewarned events like nuclear test. However, market also responded to information about sudden events such as the impact of Kim Jung-il’s death on the South-North economic cooperation stock. Portfolio analysis demonstrated that small capital stocks were affected more than large caps. These results cannot reject the EMH. Also, estimates of market model and that of Fama-French three-factor model did not show a statistically significant difference in different verification. There was no statistically significant difference between growth and value stock in large caps portfolio either. However, there was a statistically significant difference between defense stock and South-North economic cooperation stock, small caps and big caps, and weighted average and simple average. The significance of this study lies in that it conducted the event study by variety estimation model with objective standards for selecting events when measuring the effect of North Korea Risks.

증권시장 흐름과 투자 집단 간의 투자 포지션

우리나라 유가증권시장의 추세 흐름과 투자자들의 투자 포지션의 관계를 중심으로 투자자들의 거래가 어떠한 특징을 갖는지를 실증적으로 분석하였다. 연구 대상 기간은 2004년 1월부터 2011년 12월까지 8년간인 총 96개월의 1,991일간이다. 분석에 사용된 자료는 한국종합주가지수(KOSPI)와 각 거래집단의 총매수량과 매도량, 매수대금과 매도대금 등이다. 매월 말과 매일 종가 두 자료를 이용하여, 각 집단 간의 상관관계를 검정하고 회귀분석을 하였다. 본 연구는 시장을 장기적인 관점에서 국면을 세분화하여 각 투자집단의 투자 포지션을 검정하였다. 외국인들과 기관들은 주로 고가 종목에 대한 거래에 집중되었다는 것을 알 수 있었다. 그리고 국면을 좀 더 세분화하여 검정한 결과 외국인 투자자들은 기관들과는 달리 상승3기에 지수가 상승할 경우 증시에서 빠져나가는 현상을 볼 수 있었다. 하락 말기에 개인들은 매도를 증가시키고 있다는 것을 알 수 있었다. 일반적으로 개인들은 시장의 흐름과 역행하면서, 외국인 투자자들의 상대방이 되어 반대 포지션을 선택하고 있다고 할 수 있을 것 같다. In this paper, characteristics of transactions by investors were examined based on the relationship between South Korea's stock market trends and the amount of net purchasing by investors. The study period is from January of 2004 to December of 2011, a total 1,991 days on 96 months. Data used for correlation and regression analysis include the value of the KOSPI index at the end of each month, the monthly net purchase amount of each of the groups, as well the daily volume, the daily price. In this study, the long-term phase of the market divided by refining. and each of the investment position of invest group was investigated. As a result, foreign investors are a net selling position when market was rising phase of the tertiary. And private investors were a net short positions when the market was decline phase of the tertiary. Regardless of the flow changes, the private investors had opposite position to the flow of the mark, also they had opposite position to the position of the foreign investors.

匯率、油價及成交量之波動率對股票市場報酬之衝擊：南韓股票市場之實證研究

This paper combines the idea of simple variable double GARCH model (Brooks, 2001) and the idea of GJR-GARCH model (Glosten, Jaganathan & Runkle, 1993), proposed a double threshold-IGRACH model of the three variables, we uses this model to discuss the influence of the turnover volume, the oil price and the exchange rate volatility rate on the South Korea stock price return volatility, and takes the threshold by the turnover volume, the oil price and the exchange rate volatility rates' positive and negative value. By the empirical diagnosis results demonstrate that the double threshold-IGRACH (1, 1) model of the three variables to discuss the turnover volume, the oil price, and the exchange rate volatility rate to the South Korea stock market return influence is appropriate, also responded the South Korea stock market has an asymmetrical effect. By the empirical diagnosis result also shows that the eight kind combinations of the positive and negative value for the turnover volume, the oil price and the exchange rate volatility rate, the turnover volume, the oil price and the exchange rate volatility rate information actually affects the stock market return volatility. This result also shows that the turnover volume, the oil price and the exchange rate volatility rate can affect the variation risk of the stock market return volatility.

Return autocorrelations in the stock markets

This article investigates the return autocorrelation in four stock markets around the Asia-Pacific rim: the USA, Japan, Taiwan and South Korea. The results indicate that there are conditional return autocorrelation in Taiwan's and South Korea's stock markets for daily data. Moreover, there are negative relationships between autocorrelation and two factors (trading volume and return volatility) significantly in Taiwan and South Korea, implying that the stock markets in Taiwan and South Korea are not as efficient as those in developed countries (the USA and Japan). For weekly data, however, none of the above four markets has significant return autocorrelation.

Is South Korea's stock market efficient? Evidence from a nonlinear unit root test

In this article we re-examine efficiency of the South Korea's stock market, extending recent work of Narayan and Smyth (2004). For this purpose we apply the nonlinear unit root test procedure recently developed by Kapetanios et al. (2003). The nonlinear unit root test rejects the null hypothesis of unit root, suggesting that the South Korea's stock market is not weak form efficient, contrary to the findings of Narayan and Smyth (2004).

Is South Korea's stock market efficient? A note

In an attempt to examine efficiency of South Korea's stock market (SKM), Narayan and Smyth (2004) used a battery of unit root tests to investigate the random walk hypothesis and on the basis of the reported evidence for unit root, they concluded that the SKM is efficient. The authors have unfortunately confused random walk with unit root hypothesis. The present note stresses the fact that it is insufficient to test for stationarity when examining efficiency, casting serious doubt on Narayan and Smyth's conclusions. Furthermore, we provide comments on the shortfalls of the unit roots tests employed and not accounted for in Narayan and Smyth's study which may lead to spurious results.

Is South Korea's stock market efficient?

This letter applies the Zivot and Andrews (Journal of Business and Economic Statistics, 10, 251–70, 1992) one break and the Lumsdaine and Papell (Review of Economic and Statistics, 79, 212–8, 1997) two break unit root tests to examine the random walk hypothesis for stock prices in South Korea. The results provide strong evidence that stock prices in South Korea are characterized by a unit root, which is consistent with the efficient market hypothesis.