• International journal of advanced smart convergence
• /
• 제8권2호
• /
• pp.132-139
• /
• 2019

We address the problem about forecasting the direction of stock price movement in the Korea market. Recently, the deep neural network is popularly applied in this area of research. In deep neural network systems, proper parameter initialization reduces training time and improves the performance of the model. Therefore, in our study, we propose a novel parameter initialization technique and apply this technique for the stock price movement prediction model. Specifically, we design a framework which consists of two models: a base model and a main prediction model. The base model constructed with LSTM is trained by using the large data which is generated by a large amount of the stock data to achieve optimal parameters. The main prediction model with the same architecture as the base model uses the optimal parameter initialization. Thus, the main prediction model is trained by only using the data of the given stock. Moreover, the stock price movements can be affected by other related information in the stock market. For this reason, we conducted our research with two types of inputs. The first type is the stock features, and the second type is a combination of the stock features and the Korea Composite Stock Price Index (KOSPI) features. Empirical results conducted on the top five stocks in the KOSPI list in terms of market capitalization indicate that our approaches achieve better predictive accuracy and F1-score comparing to other baseline models.

• 지능정보연구
• /
• 제12권4호
• /
• pp.15-37
• /
• 2006

본 논문은 증권거래소 이상매매 적출업무의 효율성을 제고하기 위해 데이터마이닝 기법을 적용하는 방안에 대해 연구하는 것을 주된 목적으로 한다. 이 과정에서 국내 증권거래소의 이상매매 적출모형과 데이터마이닝을 활용한 해외사례로서 미국 NASD의 ADS를 소개한 뒤, 실증분석에 사용될 자료들을 시세조종 종목과 정상 종목으로 나누어 검토한다. 국내에서 주식시장의 이상매매 적출에 대한 데이터마이닝 기법의 적용에 대한 연구가 없는 상황에서 다양한 입력변수를 만들어 실제로 데이터마이닝 기법들을 적용하여 적출성과를 상호 비교한 결과와 시사점을 기술하였다.

• The Journal of Asian Finance, Economics and Business
• /
• 제9권9호
• /
• pp.351-360
• /
• 2022

This study aims to determine the factors that can influence investors in selecting stocks in the Indonesian capital market to establish an optimal portfolio, and find phenomena that occurred during the COVID-19 pandemic so that buying interest / the number of investors increased in the Indonesian capital market. This study collection technique uses primary data obtained from the survey questionnaire and secondary data which is market data, stock price movement data sourced from the Indonesia Stock Exchange, Indonesian Central Securities Depository, and Bank Indonesia, as well as empirical literature on behavior finance, investment decision, and interest in buying stock. The method used in this research is the survey questionnaire analysis with the SEM (statistical approach). The results of the analysis using SEM show that investor behavior influences the stock-buying interest, investor behavior, and the stock-buying interest influences investor decision-making. However, risk management does not influence investor-decision making. This occurs when the investigator's psychological capacity produces more decision information by decreasing all potential biases, allowing the best stock selection model to be selected. When the investigator's psychological capacity creates more decision information by reducing biases, the optimum stock selection model can be chosen.

• East Asian Economic Review
• /
• 제21권2호
• /
• pp.147-165
• /
• 2017

This study quantifies the dynamic interrelationship between the KOSPI index return and search query data derived from the Naver DataLab. The empirical estimation using a bivariate GARCH model reveals that negative contemporaneous correlations between the stock return and the search frequency prevail during the sample period. Meanwhile, the search frequency has a negative association with the one-week- ahead stock return but not vice versa. In addition to identifying dynamic correlations, the paper also aims to serve as a test bed in which the existence of profitable trading strategies based on big data is explored. Specifically, the strategy interpreting the heightened investor attention as a negative signal for future returns appears to have been superior to the benchmark strategy in terms of the expected utility over wealth. This paper also demonstrates that the big data-based option trading strategy might be able to beat the market under certain conditions. These results highlight the possibility of big data as a potential source-which has been left largely untapped-for establishing profitable trading strategies as well as developing insights on stock market dynamics.

• Journal of the Korean Data and Information Science Society
• /
• 제23권6호
• /
• pp.1075-1084
• /
• 2012

본 논문은 중국의 상해, 심천, 홍콩증권시장간의 정보이전효과를 연구한 것이다. 세 개의 중국 증권시장은 모두 미국의 증권시장수익률에 강하게 영향을 받는데 그 정도는 개방화가 제일 잘된 홍콩증권시장이 가장 크며 상해증권시장, 심천증권시장의 순으로 영향을 받는 것으로 나타나고 있다. 상해증권시장이나 심천증권시장은 서로 간에 수익률이전효과나 변동성전이효과가 존재하지 않지만 이 두 시장은 모두 홍콩증권시장수익률의 영향을 받는 것으로 나타났다. 하지만 미국증권시장의 움직임을 통제하면 이러한 효과는 사라지게 되어 중국의 증권시장간의 정보이전효과는 존재하지 않는 것으로 나타나고 있다. 이러한 결론은 중국의 세 개의 증권시장이 상호독립적인 성격이 강하다는 것을 의미하며, 중국의 증권시장 연구 시 시장 간의 독립성을 반영해야 할 것으로 생각된다.

• Journal of the Korean Data and Information Science Society
• /
• 제18권4호
• /
• pp.945-953
• /
• 2007

In this paper, we propose a smoothing and thus noise-reducing method of data sequences for stock price prediction with hidden Markov models, HMMs. The suggested method just uses simple moving average. A proper average size is obtained from forecasting experiments with stock prices of bank sector of Korean Exchange. Forecasting method with HMM and moving average smoothing is compared with a conventional method.

• 한국콘텐츠학회논문지
• /
• 제12권2호
• /
• pp.472-482
• /
• 2012

주식시장에는 많은 투자자들이 참여하고 있으며 점점 더 많은 사람이 주식투자에 관심을 가지고 있다. 주식시장에서 위험을 회피하고 수익을 얻기 위해서는 다양한 정보를 바탕으로 정확한 의사결정을 해야한다. 즉 수익을 얻을 수 있는 종목 선택, 적절한 매수-매도 가격의 결정, 그리고 적절한 보유기간 등을 결정해야 한다. 본 논문에서는 개인 주식 투자자의 의사결정 지원을 위한 데이터마이닝 도구를 제안한다. 즉, 개인 투자자가 직접 기계학습 방법을 적용하여 주가예측 모델을 생성할 수 있게 하고, 적절한 매수-매도 가격과 보유기간 등을 결정하는 것을 도와주는 도구를 제안한다. 제안하는 도구는 과거 데이터를 이용하여 투자자 자신의 성향에 맞는 투자에서의 의사결정을 할 수 있도록 지원하는 도구로서 주가데이터 관리, 기계학습 적용을 통한 주가예측 모델 생성, 투자 시뮬레이션 등의 기능을 제공한다. 사용자는 스스로 주가에 영향을 미칠 수 있다고 판단하는 기술적 지표를 선정하고 이를 이용하여 주가예측 모델을 만들고 테스트 할 수 있으며, 적절한 예측모델을 적용하여 시뮬레이션을 수행해 봄으로써 실제로 어느 정도 수익을 얻을 수 있는지 평가하고 적절한 매매 정책을 수립할 수 있다. 제안하는 도구를 이용하여 주식 투자자는 기존의 감정적 판단에 의한 투자가 아닌 객관적 데이터에 의해 검증을 거친 주가예측 모델과 매매정책에 따라 주식투자를 할 수 있어 이전 보다 나은 수익을 기대할 수 있다.

• Journal of the Korean Data and Information Science Society
• /
• 제21권6호
• /
• pp.1337-1341
• /
• 2010

The paper investigates linkages between the Korea stock market and each of the major Asia-Pacific stock markets, namely those of the Japan, China, Australia, New-Zealand, We employs the Johansen technique to test for pairwise cointergration between the Korea stock market and each of the major Asia-Pacific stock markets. The major stock indices of the markets are used, from 1 September 2006 to 31 August 2010. The results from the test implies that the Korea market is not cointergrated with any of the major Asia-Pacific markets during the period. Our study implies that there are no long-run linkages between the Korea and any of the major Asia-Pacific stock markets.

• The Journal of Asian Finance, Economics and Business
• /
• 제9권4호
• /
• pp.173-183
• /
• 2022

The objective of this research is to examine the influence of the COVID-19 pandemic on stock markets in a few developing and developed countries. This study uses daily data from January 2020 to May 2021 and obtained from World Health Organization and Thomson Reuters. The secondary data was evaluated through panel econometric methodology that includes different unit root tests, and to analyze the long-run relationship between variables, panel cointegration techniques were applied. The long-run causality among variables was examined through Panel Vector Error Correction Model. The overall findings of this study suggest a long-run association exists between several cases and death with the stock returns of the GCC and other stock markets. Furthermore, the VECM model also identified a long-run causality running from COVID cases and death towards the stock rerun of both sets of stock markets. However, a subsequent Wald test yielded mixed results, indicating no short-run causality between cases and deaths and stock returns in both groups; however, in the case of GCC, several COVID-19 cases are having a causal impact on stock markets, which is notable in light of the fact that the death rate in GCC is significantly lower than in many developed and developing countries.

• 응용통계연구
• /
• 제25권4호
• /
• pp.543-552
• /
• 2012

Parrondo paradox is a counter-intuitive phenomenon where two losing games can be combined to win or two winning games can be combined to lose. When we trade stocks with a history-dependent Parrondo game rule (where we buy and sell stocks based on recent investment outcomes) we found Parrondo paradox in stock trading. Using stock data of the KRX from 2008 to 2010, we analyzed the Parrondo paradoxical cases in the Korean stock market.