• Korean Business Review
• /
• v.12
• /
• pp.119-138
• /
• 1999

In this study, we empirically investigate the relations between trading volumes and our proxies for information flows and differences of opnion. Econometric methods to analyze the relations in the equity and KOSPI 200 futures markets include Generalized Method of Moment(GMM) and Generalized Autoregressive Conditional Heteroscedasticity(GARCH) models. Major findings from our empirical analyses are summarized as follows; (i) Trading volume in both the equity and KOSPI 200 futures markets varies positively with proxies for information flows. We find that trading volumes in both markets are closely related to firm-specific information rather than market-wide information. (ii) Trading volumes in the equity and KOSPI 200 futures market have positive relations with our proxies for differences of opinion. (iii) Day-of-the-week effect is clear in both markets. Trading volumes in both the equity and KOSPI 200 futures markets tend to be relatively low early and late in the week. (IV) Futures contract life-cycle effect is clear. In other words, futures trading volume increses in the period around contract expiration. (V) In addition, ARCH effect on trading volumes is reported significant enough to take into account. The disturbance of trading volumes in both markets seem to be conditional heteroscedastic.

• Journal of Digital Convergence
• /
• v.15 no.2
• /
• pp.135-144
• /
• 2017

This study is to identify the growth rate and volatility of logistics related firms in the stock market. To do this, we used monthly data for 197 years from June 2000 to October 2016 by selecting KOSPI and Transport & Storage(T&S), KOSDAQ, Transportation(TRANS) index. The purpose of this study is to compare the T&S and TRANS stock index returns with the KOSPI and KOSDAQ index. And we are to judge whether the development potential of the logistics industry and the value of the investment of related companies in the future is high. For this purpose, we will analyze the basic statistics, correlation and growth rate of each index, and compare T&S and TRANS with market returns. Analysis result, for the past 197 months logistics related T&S and TRANS have been higher than market returns. The correlation was highly related to TRANS and T & S in KOSPI, but it was not related to KOSDAQ. TRANS represents high risk and high return, while KOSDAQ represents high risk and low return market. TRANS is considered to be an efficient investment. We expect the future development of logistics related industries and T & S and TRANS to show a high rate of increase compared to the market returns.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.6
• /
• pp.287-295
• /
• 2007

This paper proposes a novel data editing techniques with genetic algorithm (GA) in case-based reasoning (CBR) for the prediction of Korea Stock Price Index (KOSPI). CBR has been widely used in various areas because of its convenience and strength in compelax problem solving. Nonetheless, compared to other machine teaming techniques, CBR has been criticized because of its low prediction accuracy. Generally, in order to obtain successful results from CBR, effective retrieval of useful prior cases for the given problem is essential. However. designing a good matching and retrieval mechanism for CBR system is still a controversial research issue. In this paper, the GA optimizes simultaneously feature weights and a selection task for relevant instances for achieving good matching and retrieval in a CBR system. This study applies the proposed model to stock market analysis. Experimental results show that the GA approach is a promising method for data editing in CBR.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.1
• /
• pp.123-130
• /
• 2021

With the recent developments in computer technology, there has been an increasing interest in the field of machine learning. This also has led to a significant increase in real business cases of machine learning theory in various sectors. In finance, it has been a major challenge to predict the future value of financial products. Since the 1980s, the finance industry has relied on technical and fundamental analysis for this prediction. For future value prediction models using machine learning, model design is of paramount importance to respond to market variables. Therefore, this paper quantitatively predicts the stock price movements of individual stocks listed on the KOSPI market using machine learning techniques; specifically, the reinforcement learning model. The DQN and A2C algorithms proposed by Google Deep Mind in 2013 are used for the reinforcement learning and they are applied to the stock trading strategies. In addition, through experiments, an input value to increase the cumulative profit is selected and its superiority is verified by comparison with comparative algorithms.

• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.461-475
• /
• 2021

Hidden Markov model (HMM) is a statistical model in which the system consists of two elements, hidden states and observable results. HMM has been actively used in various fields, especially for time series data in the financial sector, since it has a variety of mathematical structures. Based on the HMM theory, this research is intended to apply the domestic KOSPI200 stock index as well as the prediction of global stock indexes such as NIKKEI225, HSI, S&P500 and FTSE100. In addition, we would like to compare and examine the differences in results between the HMM and support vector regression (SVR), which is frequently used to predict the stock price, due to recent developments in the artificial intelligence sector.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.4
• /
• pp.63-71
• /
• 2016

This paper is about applying efficient data mining method which improves the score calculation and proper building performance of credit ranking score system. The main idea of this data mining technique is accomplishing such objectives by applying Correlation based Feature Selection which could also be used to verify the properness of existing rank scores quickly. This study selected 2047 manufacturing companies on KOSPI market during the period of 2009 to 2013, which have their own credit rank scores given by NICE information service agency. Regarding the relevant financial variables, total 80 variables were collected from KIS-Value and DART (Data Analysis, Retrieval and Transfer System). If correlation based feature selection could select more important variables, then required information and cost would be reduced significantly. Through analysis, this study show that the proposed correlation based feature selection method improves selection and classification process of credit rank system so that the accuracy and credibility would be increased while the cost for building system would be decreased.

• Asia-Pacific Journal of Business
• /
• v.14 no.2
• /
• pp.33-49
• /
• 2023

Purpose - The purpose of this study is to examine the option selection and optimal trading of informed traders in KOSPI 200 options market based on the PIN (probability of informed trading) model of Easley et al.(2002). Design/methodology/approach - This study uses TAQ (trade and quote) data provided by Korean Exchanges (KRX) which contains all the bids and trades recorded during the continuous auction trading hours for the KOSPI 200 options between May 2019 and September 2020. Findings - First, there was no difference in the PIN between call and put options in the 2019 data, but the PIN of put options was slightly higher in 2020. Second, regardless of the type of option, the PIN was higher for in-the-money (ITM) options, and the PIN of out-of-the-money (OTM) options was the same as or slightly higher than that of at-the-money (ATM) options. Third, we found that the PIN decreases as trading liquidity increases, and fourth, the PIN increased sharply as the expiration date approached, especially for OTM options, while ITM and ATM options showed relatively weak effects. Fifth, for foreign and institutional investors, the periodicity of orders was observed in milliseconds, especially for foreign investors, where the periodicity of orders was clear and frequent in OTM options. The results suggest that the purpose of option trading varies depending on the moneyness from the perspective of the informed trader.

• The Korean Journal of Financial Management
• /
• v.22 no.1
• /
• pp.71-91
• /
• 2005

The object or this paper is to analyze the rollover effect on KOSPI 200 index option prices. Especially we analyze the implied volatilities of the options that became the near maturity options as the old one expired. For this analysis, a panel data of KOSPI 200 Index Option Prices from year 1999 to year 2001 were used, and following results were obtained. First, after controlling for the underlying index returns, strike prices and other pricing factors, the call option prices tend to decrease while the put option prices tend to increase during the week of expiry. Second, if one concentrates on the daily price changes, call option prices tend to go up on Thursday (as the old options expire), and then experience a price decrease on the following day, while the reverse is true for the put options. These results imply that the option prices are affected by some of the market micro-structure effects such as whether the option is the near maturity option. We conjecture that the reason for this is related to the undervaluation of KOSPI 200 futures. The results from this paper have implications on the timing of option trades. If one wants to buy put options, and/or sell call options, he has better off by executing his intended trades before the old options expire. On the other hand, if one wants to buy call options, and/or sell put options, hi has better off by executing his intended trades after the expiry.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.6
• /
• pp.1061-1073
• /
• 2009

Stock price index option investing is a scientific investment method and various index and investment strategies have been developed. The purpose of this study is to apply the variety of option investment strategies that have been introduced in the market and validate them using past option trading data. Option data was based on an actual stock exchange market tick data ranging from September 2001 to January 2007. Visual Basic is used to propose an option back-testing model. Validation process was carried out by transferring the tick data into ten-minute intervals and empirically analyzed. Furthermore, most option-related strategies have been applied to the model, and the usefulness of each strategies can be easily evaluated. As option investment has high leverage followed by high risks and profit, the optimal option investment strategy should be used according to the market condition at the time to make stable profit with minimum risk.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1997.10a
• /
• pp.105-108
• /
• 1997

Previous studies in stock market predictions using artificial intelligence techniques such as artificial neural networks and case-based reasoning, have focused mainly on spot market prediction. Korea launched trading in index futures market (KOSPI 200) on May 3, 1996, then more people became attracted to this market. Thus, this research intends to predict the daily up/down fluctuant direction of the price for KOSPI 200 index futures to meet this recent surge of interest. The forecasting methodologies employed in this research are the integration of genetic algorithm and artificial neural network (GAANN) and the integration of genetic algorithm and case-based reasoning (GACBR). Genetic algorithm was mainly used to select relevant input variables. This study adopts the categorical data preprocessing based on expert's knowledge as well as traditional data preprocessing. The experimental results of each forecasting method with each data preprocessing method are compared and statistically tested. Artificial neural network and case-based reasoning methods with best performance are integrated. Out-of-the Model Integration and In-Model Integration are presented as the integration methodology. The research outcomes are as follows; First, genetic algorithms are useful and effective method to select input variables for Al techniques. Second, the results of the experiment with categorical data preprocessing significantly outperform that with traditional data preprocessing in forecasting up/down fluctuant direction of index futures price. Third, the integration of genetic algorithm and case-based reasoning (GACBR) outperforms the integration of genetic algorithm and artificial neural network (GAANN). Forth, the integration of genetic algorithm, case-based reasoning and artificial neural network (GAANN-GACBR, GACBRNN and GANNCBR) provide worse results than GACBR.