• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.65-82
• /
• 2021

Stock market investors are generally split into foreign investors, institutional investors, and individual investors. Compared to individual investor groups, professional investor groups such as foreign investors have an advantage in information and financial power and, as a result, foreign investors are known to show good investment performance among market participants. The purpose of this study is to propose an investment strategy that combines investor-specific transaction information and machine learning, and to analyze the portfolio investment performance of the proposed model using actual stock price and investor-specific transaction data. The Korea Exchange offers daily information on the volume of purchase and sale of each investor to securities firms. We developed a data collection program in C# programming language using an API provided by Daishin Securities Cybosplus, and collected 151 out of 200 KOSPI stocks with daily opening price, closing price and investor-specific net purchase data from January 2, 2007 to July 31, 2017. The self-organizing map model is an artificial neural network that performs clustering by unsupervised learning and has been introduced by Teuvo Kohonen since 1984. We implement competition among intra-surface artificial neurons, and all connections are non-recursive artificial neural networks that go from bottom to top. It can also be expanded to multiple layers, although many fault layers are commonly used. Linear functions are used by active functions of artificial nerve cells, and learning rules use Instar rules as well as general competitive learning. The core of the backpropagation model is the model that performs classification by supervised learning as an artificial neural network. We grouped and transformed investor-specific transaction volume data to learn backpropagation models through the self-organizing map model of artificial neural networks. As a result of the estimation of verification data through training, the portfolios were rebalanced monthly. For performance analysis, a passive portfolio was designated and the KOSPI 200 and KOSPI index returns for proxies on market returns were also obtained. Performance analysis was conducted using the equally-weighted portfolio return, compound interest rate, annual return, Maximum Draw Down, standard deviation, and Sharpe Ratio. Buy and hold returns of the top 10 market capitalization stocks are designated as a benchmark. Buy and hold strategy is the best strategy under the efficient market hypothesis. The prediction rate of learning data using backpropagation model was significantly high at 96.61%, while the prediction rate of verification data was also relatively high in the results of the 57.1% verification data. The performance evaluation of self-organizing map grouping can be determined as a result of a backpropagation model. This is because if the grouping results of the self-organizing map model had been poor, the learning results of the backpropagation model would have been poor. In this way, the performance assessment of machine learning is judged to be better learned than previous studies. Our portfolio doubled the return on the benchmark and performed better than the market returns on the KOSPI and KOSPI 200 indexes. In contrast to the benchmark, the MDD and standard deviation for portfolio risk indicators also showed better results. The Sharpe Ratio performed higher than benchmarks and stock market indexes. Through this, we presented the direction of portfolio composition program using machine learning and investor-specific transaction information and showed that it can be used to develop programs for real stock investment. The return is the result of monthly portfolio composition and asset rebalancing to the same proportion. Better outcomes are predicted when forming a monthly portfolio if the system is enforced by rebalancing the suggested stocks continuously without selling and re-buying it. Therefore, real transactions appear to be relevant.

• Journal of Digital Convergence
• /
• v.12 no.8
• /
• pp.493-499
• /
• 2014

This study aims to verify the effects of the life redesign educational program based on the baby boomer (11 members of experimental group, 12 members of control group). The program was conducted for two hours two times in a week in the area of Chungnam (Total 8weeks 16sessions). First, in the result of the Wilcoxon's pairs signed-ranks test between the pre-post tests for the analysis on the program effectiveness of the experimental group of baby boomer, the baby boomer of experimental group showed an improved perception of preparing the volunteer work in the perception of preparing their old age, and there was no pre-post significant differences in the control group. In case of the experimental group, perception of the post-retirement preparation, such as a physical preparation, emotional preparation, financial preparation, volunteer work preparation and leisure activities preparation increased in average. Second, the satisfaction for the program's educational process, educational contents, educational data, educational method, instructor and the educational environment were shown to be more than 3.5 points out of 5 points in full.

• Science of Emotion and Sensibility
• /
• v.17 no.4
• /
• pp.19-28
• /
• 2014

The number of people using on-line shopping has rapidly increased over time. In particular, open-market is the most potential on-line market. Since there are too many products in open-market, customers have serious troubles finding products they want. Thus, interface should be improved so that open-market is able to offer products they want effectively. This study analyzed web interface based on main web pages of four major open-market companies in Korea, and performed satisfaction evaluation according to the analyzed factors. As a result, it reveals that what kind of factors the customers prefer and there is a causal relation between the most satisfactory open-market and the preferred factors of the customers.

• Science of Emotion and Sensibility
• /
• v.23 no.3
• /
• pp.3-10
• /
• 2020

This study is aimed at investigating drivers' reactions to yellow signal dilemma situations as a result of the existing signal system, and developing a new signal system. A driver-centered coping model was developed through bio-signal analysis. The driver's physiological response in the existing signal system was observed, and the signal system was developed by applying intersection road driving conditions using a car graphic simulator. Participants were classified into a control group (existing signal system) and an experimental group for a new yellow signal system (new signal system). Based on the results, the emergence of parasympathetic nerves was higher in the experimental group than in the control group, where a statistically significant difference was observed (p < 0.05). The newly developed signal system appeared to cause tension among drivers; however, the sympathetic to parasympathetic nerve ratio was 6: 4, which could be interpreted as an ideal balance. We conclude that drivers can drive more stably if the coping signal system developed in this study is applied to the traffic system.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.26 no.3
• /
• pp.35-45
• /
• 1984

Generally speaking, agriculture exist in a climatic environment of uncertainty. Namely, normal rainfall value, as given by the mean values, does not exist. Thought on exists, itl does not affect like extreme Precipitation value on the part of agriculture and of others. Therefore, it is important that we measure the duration and severity index of drought caused by extreme precipitation deficit. In this purpose, this study was dealt with the calculation of drought duration and severity indexs by the method of monthly weighting coefficient. There is no quantitive definition of drought that is universally acceptable. Most of the criteria was used to identify drought have been arbitrary because a drought is a 'non-event' as opposed to a distinct event such as a flood. Therefore, confusion arises when an attempt is made to define the drought phenomenon, the calculation of duration, drought index is based on the following four fundamental question, and this study was dealt with the answers of these four questions as they related to this analytical method, as follows. First, the primary interest in this study is to be the lack of precipitation as it relates to agricultural effective rainfall. Second, the time interval was used to be month in this analysis. Third, Drought event, distinguished analytically from other event, is noted by monthly weighting coefficient method based on monthly rainfall data. Fin-ally, the seven regions used in this study have continually affected by drought on account of their rainfall deficit. The result from this method was very similar to the previous papers studied by many workers. Therefore, I think that this method is very available in Korea to identify the duration of drought, the deficit of precipitation and severity index of drought, But according to the climate of Korea exist the Asia Monsoon zone. The monthly weighting coefficient is modify a little, Because get out of 0.1-0.4 occasionally.

• The Journal of the Korea Contents Association
• /
• v.17 no.7
• /
• pp.101-112
• /
• 2017

The purpose of this study is to find out what kind of experience and effect the learner - centered team - based learning (tbl)method has on pre - nursing learner's nursing English course. Participants were 12 preliminary nursing learner, it was analyzed through learning result recording, study observation, learning satisfaction, learner's report, peer evaluation. And described the meaning of the learning experience, individual and team scores were analyzed using frequency analysis, paired-t test. The results showed that the score of each team was higher than the score of individual in both. The tbl experience has been a form of intimacy with colleagues, a motivation for learning, self-study, easy to learn the medical terminology felt through repeated learning, to improve their score by having them secondary group test and they remembered it as a pleasant learning time.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.8
• /
• pp.2888-2898
• /
• 2010

It has been over a decade since the business consulting services by SMBA started in order to build up competitiveness through supporting small and medium enterprises under the business environment of globalization. No matter how there is no post empirical data of evaluation. Therefore, this study is focused on analysing the practical performance of Coupon System Management Consulting(CSMC) by comparing the financial condition for a few years before and behind since the companies have been involving in. As a result, the statistical significances of research hypotheses were rejected for the most part. Moreover, the growth rates of sales and total assets of which each of them is one of the indicators concerning growth and activity, are negatively significant, which means that CSMC the needs comprehensive consideration about its efficiency and in all its aspects.

• 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.

• Journal of Digital Convergence
• /
• v.18 no.11
• /
• pp.347-354
• /
• 2020

The purpose of this study is to develop a competency model for the revision of the dentistry education curriculum based on the competency of W College of Dentistry. For this, this study made progress of the competency model development procedure in three stages. The preparation stages of the competency model was developed by performing an analysis about the awareness investigation of the members, and the development stages were progressed through the competency level and behavioral index, etc. The content validity was verified by an expert for the evaluation stage. As a result, content validity index was high with CVI of .91 and a competency model was developed with the 4 key competencies, which are the common competencies of the university linked with job competency, the major competency. This study holds significance by the fact that the competency model development case developed through this procedure provided basic data for research that requires the development of the competency model and the education curriculum revision based on the competency of W College of Dentistry is planned to also be applied.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2008.11a
• /
• pp.581-584
• /
• 2008

In this study, it is willing to present that fundamental data for proposing quantitatively shrinkage cracking evaluation method such as plat-ring type restrained test method. To examine suitable size of specimen of plat-ring type restrained test method, Evaluated concrete about restrained shrinkage crack properties of numerical analysis of 3D solid element using the MIDAS program, drying shrinkage deformation, restrained shrinkage stress, crack area and crack point with inside ring diameter of specimen in 100mm, 150mm, 200mm and high of Specimen in 30mm, 50mm after curing in condition of constant temperature and usual habit of temperature 20${\pm}$3$^{\circ}$C, humidity 60${\pm}$5%. As a result, it was available about suitable estimation with inside ring diameter of specimen in more than 150mm and high of Specimen in 50mm. Hereafter, it is considered that the study concerning environmental condition and mixing factor in plat-ring type restrained test method is need.