• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.3
• /
• pp.123-128
• /
• 2019

This paper proposes the stock price prediction based on the artificial intelligence, where the model with recurrent convolution neural network (RCNN) layers is adopted. In the motivation of this prediction, long short-term memory model (LSTM)-based neural network can make the output of the time series prediction. On the other hand, the convolution neural network provides the data filtering, averaging, and augmentation. By combining the advantages mentioned above, the proposed technique predicts the estimated stock price of next day. In addition, in order to emphasize the recent time series, a custom weighted loss function is adopted. Moreover, stock data related to the stock price index are adopted to consider the market trends. In the experiments, the proposed stock price prediction reduces the test error by 3.19%, which is over other techniques by about 19%.

• KIISE Transactions on Computing Practices
• /
• v.23 no.11
• /
• pp.625-631
• /
• 2017

The stock price prediction for stock markets remains an unsolved problem. Although there have been various overtures and studies to predict the price of stocks scientifically, it is impossible to predict the future precisely. However, stock price predictions have been a subject of interest in a variety of related fields such as economics, mathematics, physics, and computer science. In this paper, we will study fluctuation patterns of stock prices and predict future trends using the Deep learning. Therefore, this study presents the three deep learning models using Tensorflow, an open source framework in which each learning model accepts different input features. We expand the previous study that used simple price data. We measured the performance of three predictive models increasing the number of priced-based input features. Through this experiment, we measured the performance change of the predictive model depending on the price-based input features. Finally, we compared and analyzed the experiment result to evaluate the impact of the price-based input features in stock price prediction.

• Management & Information Systems Review
• /
• v.28 no.3
• /
• pp.25-44
• /
• 2009

The purpose of this paper is to examine the determinants which cause a price differential between common and preferred stock. Prior studies have shown that variables like liquidity, size, the number of outstanding shares issued can explain the price differential between common and preferred stock price. Based on year 2006 through year 2008 data, we analyzed the determinants using regression model. Dummy variables representing large/small company and KSE/KOSDAQ respectively are added and analyzed as independent variables. The firm size, trade volume turnover, and the number of preferred shares to total outstanding shares were proved to make influence on the price differential under the 5% significance level. Especially, we have found the number of preferred shares to total outstanding shares provide the most strong relationship with the price differential. This means that a high ratio of preferred stock to total outstanding shares leads to relatively high value of common stock and causes a big price differential.

• The Korean Journal of Financial Management
• /
• v.14 no.3
• /
• pp.1-21
• /
• 1997

본 연구는 가치창조 경영의 중심지표인 EVA가 우리나라에서도 올바른 주주가치 평가지표로서 활용될 수 있을지를 살펴보고 있다. 실증분석 결과를 보면 연구기간(1986년${\sim}$1995년)중 대부분의 기업은 주당 EVA가 음(陰)이였고, 주당 EVA는 주당영업 이익, 주당순이익, 자기자본이익률등 기존 성과 척도들에 비해 주가와 상관관계가 가장 높았다. 연도별 EVA를 기준으로 매년 포트폴리오를 재구성하는 방법으로 10년간의 초과 수익률을 계산한 결과 EVA가 양(陽)인 포트폴리오는 음(陰)경우보다 초과수익률이 거의 140%정도 높았다. 또한 당해연도 뿐 아니라 전년도 주당 EVA가 주가변동의 주요결정 요인인것도 발견되었다. 이러한 연구결과는 EVA의 극대화가 주가의 극대화 곧 기업가치 및 주주가치 극대화를 의미하므로 성과지표로서 EVA를 성과측정 및 보상등 기업의 모든 의사결정에 활용할 수 있다는 것을 시사해 준다. 또한 EVA를 포트폴리오 관리를 위한 새로운 투자지표로 활용한다면 증권시장에서 수익률을 재고할 수 있다는 것을 입증해줌으로써 증권시장의 활성화에 크게 기여할 수 있을 것이다.

• The Korean Journal of Financial Management
• /
• v.18 no.1
• /
• pp.129-156
• /
• 2001

본 연구는 1997년 11월 1일부터 1998년 9월 20일까지의 5분 단위로 측정된 거래 자료를 이용하여, KOSPI 200 선물시장, KOSPI 200 옵션시장 및 KOSPI 200 주가지수간의 선도/지연관계를 실증 분석하였다. 분석방법은 다양한 시계열 분석방법들을 이용하였으며 주요 결과는 다음과 같다. 첫째, 선물시장은 현물시장을 25분간 선도하였으며, 현물시장도 선물시장을 10분 정도 선도하였다. 둘째, 옵션시장도 현물시장을 약 20분간 선도하며, 약하지만 현물시장도 옵션시장을 5분에서 10분 가량 선도하였다. 셋째, 선물시장은 옵션시장을 20여분간 강하게 선도하였고, 옵션시장도 선물시장을 5분 정도 선도하였다. 넷째, 거래량이 적고 변동성이 높은 경우 선도/지연관계의 차이가 존재하는 것으로 나타났다. 다섯째, 옵션의 외가격과 등가격에 따른 시장간의 선도/지연관계의 분석결과 주가지수, 선물, 옵션의 선도/지연관계는 등가격과 외가격옵션에서 거의 비슷하게 나타났지만 등가격에서 현물에 대한 선물과 옵션시장의 선도효과가 강하게 나타났다.

• The Korean Journal of Financial Management
• /
• v.20 no.1
• /
• pp.191-212
• /
• 2003

Recently, there is a growing body of literature that suggests that information inefficiency is one of the causes of the asymmetric volatility. If this explanation for the asymmetric volatility is appropriate, then innovations, such as the introduction of futures, may be expected to impact the asymmetric volatility of stock market. As transaction costs and margin requirements in the futures market are lower than those in the spot market, new information is transmitted to futures prices more quickly and affects spot prices through arbitrage trading with spots. Also, the merit of the futures market may attract noise traders away from the spot market to the futures market. This study examines the impact of futures on the asymmetry of stock market volatility. If the asymmetric volatility is significant lower post-futures and exist in the futures market, it has validity that the asymmetric volatility is caused by information inefficiency in the spot market. The data examined are daily logarithmic returns on KOSPI 200 stock price index from January 4, 1993 to December 26, 2000. To examine the existence of the asymmetric volatility in the futures market, logarithmic returns on KOSPI 200 futures are used from May 4, 1996 to December 26, 2000. We used a conditional mode of TGARCH(threshold GARCH) of Glosten, Jagannathan and Runkel(1993). Pre-futures the spot market exhibits significant asymmetric responses of volatility to news and post-futures asymmetries are significantly lower, irrespective of bear market and bull market. The results suggest that the introduction of stock index futures has an effect on the asymmetric volatility of the spot market and are inconsistent with leverage being the sole explanation of asymmetry. However, it is found that the volatility of futures is not so asymmetric as expected.

• Management & Information Systems Review
• /
• v.32 no.4
• /
• pp.189-207
• /
• 2013

Using high-frequency data for 2 years, this study investigates intraday lead-lag relationship between stock index and stock index futures markets in Korea and China. We found that there are some differences in price discovery and volatility transmission between Korea and China after the stock index futures markets was introduced. Following Stoll-Whaley(1990) and Chan(1992), the multiple regression is estimated to examine the lead-lag patterns between the two markets by Newey-West's(1987) heteroskedasticity and autocorrelation consistent covariance matrix(HAC matrix). Empirical results of KOSPI 200 shows that the futures market leads the cash market and weak evidence that the cash market leads the futures market. New market information disseminates in the futures market before the stock market with index arbitrageurs then stepping in quickly to bring the cost-of-carry relation back into alignment. The regression tests for the conditional volatility which is estimated using EGARCH model do not show that there is a clear pattern of the futures market leading the stock market in terms of the volatility even though controlling nonsynchronous trading effects. This implies that information in price innovations that originate in the futures market is transmitted to the volatility of the cash market. Empirical results of CSI 300 shows that the cash market is found to play a more dominant role in the price discovery process after the Chinese index started a sharp decline immediately after the stock index futures were introduced. The new stock index futures markets does not function well in its price discovery performance at its infancy stage, apparently due to high barriers to entry into this emerging futures markets. Based on EGAECH model, the results uncover strong bi-directional dependence in the intraday volatility of both markets.

• The Korean Journal of Financial Management
• /
• v.14 no.1
• /
• pp.219-247
• /
• 1997

우리나라에서는 그 동안 유상증자(有償增資)시 주주배정(株主配定)(right offer)방식에 의하고 기업공개시의 발행가격도 일률적으로 산정(算定)되어 증권인수(證券引受)에 따른 인수기관(引受機關)(underwriter)의 역할이 제한되어 왔으나 앞으로는 증권발행방식이 다양화되어 발행가격의 결정을 포함한 인수기관의 역할이 강조될 것이다. 대부분 총액인수(總額引受)(firm commitment underwriting)방식을 택하는 미국자본시장에서 인수기관을 선정하고 발행조건들을 결정하는 방법에는 투자은행과의 협의(協議)(negotiation)에 의하는 방식과 비공개경쟁입찰(非公開競爭入札)(sealed bidding)에 의하는 방식이 있는데 많은 기업들은 상대적으로 비용이 많이 드는 협의발행을 선택한다. 본 연구에서는 이에 대한 가설들을 뉴욕증권거래소나 아메리칸증권거래소에서 거래되는 공익기업의 신주발행자료를 통해 실증 검정했다. 인수 스프레드(underwriting spread)는 발행금액에 관계없이 협의발행(協議發行)이 경쟁발행(競爭發行)보다 평균적으로 1.16% 높았으며 발행비용(發行費用)도 협의발행이 유의적인 수준에서 0.341% 정도 높았다. 비대칭정보하에서 신호균형(信號均衡)(signaling equilibrium)으로 설명할 수 없지만 협의발행에 의한 통합균형(統合均衡)(pooling equilibrium)의 가능성은 배제하지 못했다. 주식발행 발표일(發表日)(announcement date)을 전후해 인수방식에 따른 주가변동의 차이를 분석한 결과 대리인가설(代理人假說)은 부분적으로 지지했다. 발행일(發行日)(offering date)을 전후한 주가변동에 의하면 인수기관의 사전매각노력(事前賣却努力)이 협의발행하에서 더 높았으나 발행일 직후의 주가회복은 보이지 않아 인수방식에 따른 가격안정화(價格安定化) 노력의 차이는 없었다. 발행기업들간의 주가차별화의 정도를 분석한 결과 협의발행에서 인회활동(認淮活動) (certification effects)을 더 잘 할 수 있다는 사실을 지지하지 못했다.

• Journal of Korea Technology Innovation Society
• /
• v.14 no.3
• /
• pp.466-487
• /
• 2011

This study analyzed the effect of small and medium businesses' R&D intensity and patents on their price-earnings (P/E) ratios. Regression analysis was conducted on a sample of manufacturers listed on the Korean Securities Dealers Automated Quotations (KOSDAQ) for the past decade (2000~2009). The result is summarized as follows. First, a negative correlation was identified between companies' R&D intensity and their P/E ratios, but no significant relationship was found between their numbers of domestic patent applications and registrations and P/E ratios. Second, the analysis of the effect of the companies' R&D intensity on their P/E ratios resulted in a negative correlation of -1%. Third, the analysis of the effect of the companies' number of domestic patent applications and registrations on their P/E ratios showed that they did not have any significant relationship. Fourth, high-tech firms' R&D intensity had a negative correlation of -1% with their P/E ratios, but had a positive correlation of 1% with their numbers of domestic patent applications. Furthermore, the R&D intensity of middle-to-high and middle-to-low tech enterprises had a negative correlation of -1% with their P/E ratios, whereas their numbers of domestic patent applications and registrations had no significant relationship with their P/E ratios. The above results suggest that to produce successful outcomes from their R&D investment and patents, individual firms need strategies for technological innovation that relate to their technological level.

• The Korean Journal of Financial Management
• /
• v.21 no.2
• /
• pp.153-181
• /
• 2004

This study is to explore whether the relationship among financial markets changed according to financial development. For this study, data analysis was conducted through analytic methods incorporated structural breaks such as Zivot and Andrews'(1992) unit root test Gregory and Hansen's(1996a,b) cointegration test, etc. In study results, it was found that dynamic relationship between stock price and interest rate was changed from negative to positive after the structural break(Oct 1999). It may be resulted from the fact that asset substitutability between stock and bond was increased since stock investment became popularized The negative relationship between stock price and exchange rate was reinforced after the structural break(the foreign currency crisis). Also, the negative relationship between interest rate and exchange rate was strengthened after the structural break(Oct. 1999).