• Journal of Korea Society of Digital Industry and Information Management
• /
• v.6 no.3
• /
• pp.211-219
• /
• 2010

This paper designs the dynamic symbol automatic trading system in Korean option market. This system is based on Multichart program which is convenient and efficient system trading tool. But the Multichart has an important restriction which has only one constant symbol per chart. This restriction causes very useful strategies impossible. The proposed design uses global variables, signal chart selection and position order exchange. So an automatic trading system with dynamic symbol works on Multichart program. To verify the proposed system, BS(Buythensell)-SB(Sellthenbuy) strategies are tested which uses the change of open-interest of stock index futures within a day. These strategies buy both call and put option in ATM at start candle and liquidate all at 12 o'clock and then sell both call and put option in ATM at 12 o'clock and also liquidate all at 14:40. From 23 March 2009 to 31 May 2010, 301-trading days, is adopted for experiment. As a result, the average daily profit rate of this simple strategies riches 1.09%. This profit rate is up to eight times of commision price which is 0.15 % per option trade. If the method which raises the profitable rate of wining trade or lower commission than 0.15% is found, these strategies make fascinated lossless trading system which is based on the proposed dynamic symbol automatic trading system.

• The KIPS Transactions:PartB
• /
• v.11B no.2
• /
• pp.207-212
• /
• 2004

This paper presents a reinforcement learning framework for stock trading systems. Trading system parameters are optimized by Q-learning algorithm and neural networks are adopted for value approximation. In this framework, cooperative multiple agents are used to efficiently integrate global trend prediction and local trading strategy for obtaining better trading performance. Agents Communicate With Others Sharing training episodes and learned policies, while keeping the overall scheme of conventional Q-learning. Experimental results on KOSPI 200 show that a trading system based on the proposed framework outperforms the market average and makes appreciable profits. Furthermore, in view of risk management, the system is superior to a system trained by supervised learning.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.485-486
• /
• 2007

In the deregulated power market, suppliers, consumers and transmission companies try to maximize their profits by economical behaviors. In particular, generating companies like to sell more electricity for the revenue. Their situations will lead to various power system planning as optimal solutions for each supplier. In this paper, fundamental approaches of optimal power system planning under market positions of generating company are presented. The profit-maximizing approaches are modeled mathematically. By this analysis, each optimal planning is proved in risk of cost and monetary risk will be the economical signal for participants.

• The Journal of Information Systems
• /
• v.26 no.3
• /
• pp.63-90
• /
• 2017

Purpose This study proposes a novel system trading model using case-based reasoning (CBR) based on absolute similarity threshold. The proposed model is designed to optimize the absolute similarity threshold, feature selection, and instance selection of CBR by using genetic algorithm (GA). With these mechanisms, it enables us to yield higher returns from stock market trading. Design/Methodology/Approach The proposed CBR model uses the absolute similarity threshold varying from 0 to 1, which serves as a criterion for selecting appropriate neighbors in the nearest neighbor (NN) algorithm. Since it determines the nearest neighbors on an absolute basis, it fails to select the appropriate neighbors from time to time. In system trading, it is interpreted as the signal of 'hold'. That is, the system trading model proposed in this study makes trading decisions such as 'buy' or 'sell' only if the model produces a clear signal for stock market prediction. Also, in order to improve the prediction accuracy and the rate of return, the proposed model adopts optimal feature selection and instance selection, which are known to be very effective in enhancing the performance of CBR. To validate the usefulness of the proposed model, we applied it to the index trading of KOSPI200 from 2009 to 2016. Findings Experimental results showed that the proposed model with optimal feature or instance selection could yield higher returns compared to the benchmark as well as the various comparison models (including logistic regression, multiple discriminant analysis, artificial neural network, support vector machine, and traditional CBR). In particular, the proposed model with optimal instance selection showed the best rate of return among all the models. This implies that the application of CBR with the absolute similarity threshold as well as the optimal instance selection may be effective in system trading from the perspective of returns.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.3A
• /
• pp.217-224
• /
• 2010

In this paper, we propose a hard handover algorithm for a base station's self-optimization, one of the automatic operational technologies for the 3GPP LTE systems. The proposed algorithm simultaneously considers a mixed target sell selection method for optimal selection and a multiple parameter based active hysteresis method with the received signal strength from adjacent cells and the cell load information of the candidate target cells from information exchanges between eNBs through X2 interface. The active hysteresis method chooses optimal handover hysteresis value considering the costs of the various environmental parameters effect to handover performance. The algorithm works on the optimal target cell and the hysteresis value selections for a base station's automatic operational optimization of the LTE system with the gathered informaton effects to the handover performance. The simulation results show distinguished handover performances in terms of the most important performance indexes of handover, handover failure rate and load balancing.

• The Korean Journal of Financial Management
• /
• v.25 no.1
• /
• pp.51-84
• /
• 2008

We investigate the signaling effect of repurchase preceding new equity issue using Korean data. In a short time span, firms announce stock repurchases and equity offerings. The proximity of two events in Korean firms indicates that those are not independent of each other. In this paper, we test the signaling effect of repurchase on equity offerings on the two measures. One is announcement effect, which is measured as CAR(0, +2). The other is the effectiveness which is measured as CAR(0, +30) because the price movement during this window influences on the price of new issues. Previous studies that stock repurchase convey positive signal to equity offerings-Billet and Xue(2004) and Jung(2004)-construct sample without the limit of time interval between two events. This causes the unclear relation between those because of the long time interval. In this study we consider only samples of being within one year each other to reduce this problem and clarify the signal of repurchase on equity offerings. Korean firms are allowed to repurchase own shares with two different method. One is direct repurchase as same as open market repurchase. The other is stock stabilization fund and stock trust fund which trust company or bank buy and sell their shares on the behalf of firms. Generally, the striking different characteristic between direct repurchase and indirect repurchase is following. Direct repurchase is applied by more strict regulation than indirect repurchase. Therefore, the direct repurchase is more informative signal to the equity offering than the indirect repurchase. We construct two sample firms- firms with direct repurchase preceding-equity offerings and indirect repurchase-preceding equity offering, and one control firms-equity offerings only firms-to investigate the announcement effect and the effectiveness of repurchases. Our findings are as follows. Direct repurchase favorably affect the price of new issues favorably. CAR(0, +2) of firms with direct repurchase is not different from that of equity offerings only firms but CAR(0, +30) is higher than that of equity offerings only firms. For firms with indirect repurchase and equity offerings, Both the announcement effect and the effectiveness does not exist. Jung(2004) suggest the possibilities of how indirect stock repurchase can be regarded as one of unfair trading practices on based on the survey results that financial managers of some of KSE listed firms have been asked of their opinion on the likelihood of the stock repurchase being used in unfair trading. This is not objective empirical evidence but opinion of financial managers. To investigate whether firms announce false signal before equity offerings to boost the price of new issues, we calculate the long-run performance following equity offerings. If firms have announced repurchase to boost the price of new issues intentionally, they would undergo the severe underperformance. The empirical results do not show the severer underperformance of both sample firms than equity offerings only firms. The suggestion of false signaling of repurchase preceding equity offerings is not supported by our evidence.

• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.77-97
• /
• 2010

Market timing is an investment strategy which is used for obtaining excessive return from financial market. In general, detection of market timing means determining when to buy and sell to get excess return from trading. In many market timing systems, trading rules have been used as an engine to generate signals for trade. On the other hand, some researchers proposed the rough set analysis as a proper tool for market timing because it does not generate a signal for trade when the pattern of the market is uncertain by using the control function. The data for the rough set analysis should be discretized of numeric value because the rough set only accepts categorical data for analysis. Discretization searches for proper "cuts" for numeric data that determine intervals. All values that lie within each interval are transformed into same value. In general, there are four methods for data discretization in rough set analysis including equal frequency scaling, expert's knowledge-based discretization, minimum entropy scaling, and na$\ddot{i}$ve and Boolean reasoning-based discretization. Equal frequency scaling fixes a number of intervals and examines the histogram of each variable, then determines cuts so that approximately the same number of samples fall into each of the intervals. Expert's knowledge-based discretization determines cuts according to knowledge of domain experts through literature review or interview with experts. Minimum entropy scaling implements the algorithm based on recursively partitioning the value set of each variable so that a local measure of entropy is optimized. Na$\ddot{i}$ve and Booleanreasoning-based discretization searches categorical values by using Na$\ddot{i}$ve scaling the data, then finds the optimized dicretization thresholds through Boolean reasoning. Although the rough set analysis is promising for market timing, there is little research on the impact of the various data discretization methods on performance from trading using the rough set analysis. In this study, we compare stock market timing models using rough set analysis with various data discretization methods. The research data used in this study are the KOSPI 200 from May 1996 to October 1998. KOSPI 200 is the underlying index of the KOSPI 200 futures which is the first derivative instrument in the Korean stock market. The KOSPI 200 is a market value weighted index which consists of 200 stocks selected by criteria on liquidity and their status in corresponding industry including manufacturing, construction, communication, electricity and gas, distribution and services, and financing. The total number of samples is 660 trading days. In addition, this study uses popular technical indicators as independent variables. The experimental results show that the most profitable method for the training sample is the na$\ddot{i}$ve and Boolean reasoning but the expert's knowledge-based discretization is the most profitable method for the validation sample. In addition, the expert's knowledge-based discretization produced robust performance for both of training and validation sample. We also compared rough set analysis and decision tree. This study experimented C4.5 for the comparison purpose. The results show that rough set analysis with expert's knowledge-based discretization produced more profitable rules than C4.5.