• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.355-357
• /
• 2020

최근 에너지 효율의 중요성이 높아지고 에너지 공급 형태가 다변화하면서 다양한 에너지원을 효율적으로 관리할 수 있는 마이크로그리드 개념이 중요해지고 있다. 본 연구의 산업단지 마이크로그리드 열거래 플랫폼은 실증사이트의 전기 및 열에너지 모니터링 기능과 열에너지 거래 정산 기능을 가지며, 이를 위해 정확하고 안정적인 실증사이트 데이터가 필요하다. 하지만 실증사이트 데이터는 에너지 단위의 불일치, 센서 및 현장 운영상태에 따른 불안정성 등의 문제가 있어 수집 직후 열거래 플랫폼에서 활용할 수 없다. 따라서 수집된 데이터를 활용하기 위해 엔진 최대 출력량, 최대 전력 사용량 등의 변수별 특성을 고려하여 데이터 전처리 프로세스를 설계 및 적용하였다.

• Korean Journal of Construction Engineering and Management
• /
• v.19 no.1
• /
• pp.65-73
• /
• 2018

Since unfair trading practices between participants in construction project are common, the government has enforced several policies and systems to prevent or minimize the unfair trading practices in construction industry. However, not much attention has been paid to figure out which policies or acts are working or not. This paper analyzed the effectiveness of the policies and acts which are being implemented to prevent unfair trading practices and provided several suggestions to improve the performance of those acts. Survey was conducted to industry experts to collect data regarding their perceptions on those policies and acts. Then the effectiveness of the policies and acts were analyzed in terms of their importance and performance through IPA (Importance-Performance Analysis) based on the survey result. It was found through IPA that execution related acts such as investigation, exposure, and punishment for unfair trading practice have shown low effectiveness in entire construction process and dispute arbitration and mediation related center operated by authority showed low performance too. To improve the effectiveness of those acts, dispute arbitration system improvement, investigation & reporting system consolidation and enhancement practical binding force of punishment and penalty were suggested. Most of all, rules and culture for fair trading should become more established in construction industry by preventing conflict among participants through active communication.

• Journal of Science Education
• /
• v.43 no.2
• /
• pp.239-257
• /
• 2019

This study attempts to understand the context of shared learning in the trading zone formed by teachers from different backgrounds and the process in which this shared learning varies in the educational context, focusing on the case of 'Woodwork Science Education Study Group.' To do this, data was collected through in-depth interviews with eight teachers who participated in the 'Woodworking Science Education Research Group' and analyzed their responses based on grounded theory. As a result, the causal conditions of the teachers' research group were 'various contexts of entering the trading zone' and the central phenomenon was 'encounter with learning in the trading zone.' Contextual conditions affecting this phenomenon were 'woodwork as a boundary object and individual transfiguration experience,' and action/interaction strategy was 'various efforts and influences in the field.' The intervention condition was 'practical effort and experience in educational field.' Final result in this model is 'the new practice of learning shared in the trading zone.' In selective coating, it was found that the practice of the teacher's research group appears as four types of' 'Extracurricular creative experience type,' 'career education type,' 'curricula education type,' and 'school management type.' The results of this study suggest that the shared learning and antonymous practice among teachers in the teachers' research group as trading zone do not only meet their learning needs but also lead to various teaching practices in the individual teachers' context of education and improve the diversity and quality of education.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.147-155
• /
• 2022

In this study, we developed a system to dynamically balance a daily stock portfolio and performed trading simulations using gradient boosting and genetic algorithms. We collected various stock market data from stocks listed on the KOSPI and KOSDAQ markets, including investor-specific transaction data. Subsequently, we indexed the data as a preprocessing step, and used feature engineering to modify and generate variables for training. First, we experimentally compared the performance of three popular gradient boosting algorithms in terms of accuracy, precision, recall, and F1-score, including XGBoost, LightGBM, and CatBoost. Based on the results, in a second experiment, we used a LightGBM model trained on the collected data along with genetic algorithms to predict and select stocks with a high daily probability of profit. We also conducted simulations of trading during the period of the testing data to analyze the performance of the proposed approach compared with the KOSPI and KOSDAQ indices in terms of the CAGR (Compound Annual Growth Rate), MDD (Maximum Draw Down), Sharpe ratio, and volatility. The results showed that the proposed strategies outperformed those employed by the Korean stock market in terms of all performance metrics. Moreover, our proposed LightGBM model with a genetic algorithm exhibited competitive performance in predicting stock price movements.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.1
• /
• pp.161-170
• /
• 2013

The FX (Foreign Exchange) is a form of exchange for the global decentralized trading of international currencies. The simple sense of Forex is simultaneous purchase and sale of the currency or the exchange of one country's currency for other countries'. We can find the consistent rules of trading by comparing the gradient boosting method and the decision trees methods. Methods such as time series analysis used for the prediction of financial markets have advantage of the long-term forecasting model. On the other hand, it is difficult to reflect the rapidly changing price fluctuations in the short term. Therefore, in this study, gradient boosting method and decision tree method are applied to analyze the short-term data in order to make the rules for the revenue structure of the FX market and evaluated the stability and the prediction of the model.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.157-177
• /
• 2022

Investors are trading stocks by keeping a close watch on the order information submitted by domestic and foreign investors in real time through Limit Order Book information, so-called price current provided by securities firms. Will order information released in the Limit Order Book be useful in stock price prediction? This study analyzes whether it is significant as a predictor of future stock price up or down when order imbalances appear as investors' buying and selling orders are concentrated to one side during intra-day trading time. Using classification algorithms, this study improved the prediction accuracy of the order imbalance information on the short-term price up and down trend, that is the closing price up and down of the day. Day trading strategies are proposed using the predicted price trends of the classification algorithms and the trading performances are analyzed through empirical analysis. The 5-minute KOSPI200 Index Futures data were analyzed for 4,564 days from January 19, 2004 to June 30, 2022. The results of the empirical analysis are as follows. First, order imbalance information has a significant impact on the current stock prices. Second, the order imbalance information observed in the early morning has a significant forecasting power on the price trends from the early morning to the market closing time. Third, the Support Vector Machines algorithm showed the highest prediction accuracy on the day's closing price trends using the order imbalance information at 54.1%. Fourth, the order imbalance information measured at an early time of day had higher prediction accuracy than the order imbalance information measured at a later time of day. Fifth, the trading performances of the day trading strategies using the prediction results of the classification algorithms on the price up and down trends were higher than that of the benchmark trading strategy. Sixth, except for the K-Nearest Neighbor algorithm, all investment performances using the classification algorithms showed average higher total profits than that of the benchmark strategy. Seventh, the trading performances using the predictive results of the Logical Regression, Random Forest, Support Vector Machines, and XGBoost algorithms showed higher results than the benchmark strategy in the Sharpe Ratio, which evaluates both profitability and risk. This study has an academic difference from existing studies in that it documented the economic value of the total buy & sell order volume information among the Limit Order Book information. The empirical results of this study are also valuable to the market participants from a trading perspective. In future studies, it is necessary to improve the performance of the trading strategy using more accurate price prediction results by expanding to deep learning models which are actively being studied for predicting stock prices recently.

• Journal of Distribution Science
• /
• v.20 no.9
• /
• pp.73-81
• /
• 2022

Purpose: This study aimed to examine whether key audit matters (KAMs) readability influences investor reaction. Research design, data, and methodology: The signaling theory was applied to explain the behavior of investors when they receive useful information for their decisions. Data were collected from 1,866 firm-year observations from Thai listed companies in both the Stock Exchange of Thailand (SET) and the Market for Alternative Investment (MAI) for the fiscal years of 2016-2019. The study was based on secondary data, which were collected from the SET Market Analysis and Reporting Tool (SETSMART) database and the Stock Exchange of Thailand's website (www.set.or.th). A statistical regression method was used with panel data analysis to evaluate possible associations between KAMs readability and investor reaction. The study relied on popular readability measures (Fog Index). Moreover, investor reaction was measured by absolute cumulative abnormal return and abnormal trading volume. Results: It was found that the KAMs readability has positive significance on both absolute cumulative abnormal return and abnormal trading volume. Conclusion: This study showed a significant contribution to the implication of KAMs in an emerging economy. The results reveal that more readable KAMs disclosure distributed new insights and useful information to investors and led to reducing the information gap between auditors and investors.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.2
• /
• pp.196-204
• /
• 2002

This paper examines the price discovery role of the KOSPI 200 futures index for its cash index. It was used the intrady data for KOSPI 200 and futures index from July 1998 to June 2001. The existing Preceding study for KOSPI 200 futures index was used the data of early market installation, but this study is distinguished to use a recent data accompanied with the great volume of transaction and various investors. We established three hypothesis to examine whether there is the price discovery role in the KOPSI 200 futures index and the characteristics of that. First, to examine whether the lead-lag relation is induced by the infrequent trading of component stocks, observations are sorted by the size of the trading volume of cash index. In a low trading volume, the long lead time is reported and the short lead time in a high volume. It is explained that the infrequent trading effect have an influence on the price discovery role. Second, to examine whether the lead-lag relation is different under bad news and good news, observations are sorted by the sign and size of cash index returns. In a bad news the long lead time is reported and the short lead time in a good news. This is explained by the restriction of"short selling" of the cash index Third, we compared estimates of the lead and lag relationships on the expiration day with those on days prior to expiration using a minute-to-minute data. The futures-to-spot lead time on the expiration day was at least as long as other days Prior to expiration, suggesting that "expiration day effects" did not demonstrate a temporal character substantially different form earlier days. Thus, while arbitrage activity may be presumed to be the greatest at expiration, such arbitrage transactions were not sufficiently strong or Pervasive to alter the empirical price relationship for the entire day. for the entire day.

• Journal of IKEEE
• /
• v.22 no.2
• /
• pp.324-329
• /
• 2018

As the environment of power systems changes, the demand and necessity for new electrical energy market are increasing. Especially, efforts to increase the efficiency of electric energy use by using demand response programs are being studied constantly in advanced countries and it is operated as a real market. This paper presents a study on the baseline load estimation required in the new power market, such as demand response, P2P electricity trading etc. The proposed method estimates the baeline load through analysis of the load pattern and verifies the effectiveness of the proposed method using actual data.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.4
• /
• pp.348-353
• /
• 2013

Recently, control theory including stochastic optimal control and various machine-learning-based artificial intelligence methods have become major tools in the field of financial engineering. In this paper, we briefly review some recent papers utilizing stochastic optimal control theory in the fields of the pair trading for mean-reverting markets and the trend-following strategy, and consider a couple of strategies utilizing both stochastic optimal control theory and machine learning methods to acquire more flexible and accessible tools. Illustrative simulations show that the considered strategies can yield encouraging results when applied to a set of real financial market data.