• Title/Summary/Keyword: 오류 자료

Search Result 866, Processing Time 0.029 seconds

Performance of Investment Strategy using Investor-specific Transaction Information and Machine Learning (투자자별 거래정보와 머신러닝을 활용한 투자전략의 성과)

  • Kim, Kyung Mock;Kim, Sun Woong;Choi, Heung Sik
    • 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.

Development and Feasibility Study of the Nature of Science Instrument for Elementary School Students (초등학생용 과학의 본성 검사 도구 개발 및 타당성 검토)

  • Park, Jaehyeon;Park, Jaeyong
    • Journal of Korean Elementary Science Education
    • /
    • v.41 no.4
    • /
    • pp.701-724
    • /
    • 2022
  • In this study, the Nature of Science (NOS) instrument for elementary school students in the form of open questionnaires was developed specifically to reveal elementary school students' perceptions of the NOS, and its validity and effectiveness were investigated. To develop a NOS instrument for elementary school students, problems that may occur when applying the existing NOS instruments to elementary school students were analyzed and based on this, the development direction of the NOS instrument was established. In addition, after selecting seven NOS types suitable for the level of elementary school students, the preliminary instrument was produced by modifying and supplementing the items in the existing instruments for each type or by developing new items. Finally, the NOS instrument consisting of eight questions was developed by adding one question asking for a comprehensive understanding of science to seven questions related to each type of NOS after a content validity test of the science education expert group. To verify the practical effect of the developed instrument, pre- and post-tests were conducted on 50 students in two classes of sixth grade at two elementary schools in Seoul: 'existing instrument → development instrument' in one class, and 'development instrument → existing instrument' in the other class. The collected data were then compared and evaluated through summary content analysis and analyzed by executing the Wilcoxon signed-rank test. As a result of comparing and analyzing students' responses to the existing NOS instrument and the developed NOS instrument, students' perspectives on the NOS were more diverse when using the developed instrument, and the level of error in the response caused by misinterpreting the intention of the question was reduced. In addition, when using the developed instrument, the responses of the majority of students at a statistically significant level changed more specifically. In this study, the implications for the development of NOS instruments suitable for elementary school students were discussed based on these results.

A Monitoring for Citizen Participation in Artificial Nest Boxes Using Mobile Applications (모바일 애플리케이션을 활용한 시민참여 인공새집 모니터링 방안 연구)

  • Kyeong-Tae Kim;Hyun-Jung Lee;Chae-Young Kim;Whee-Moon Kim;Won-Kyong Song
    • Korean Journal of Environment and Ecology
    • /
    • v.37 no.3
    • /
    • pp.221-231
    • /
    • 2023
  • Great tit (Parus major) is a bioindicator species that can measure environmental changes in urban ecosystems and plays an important role in maintaining health as a representative insectivorous bird. Researchers have utilized artificial nest box surveys to understand the reproductive ecology of the Paridae family of birds, including the Great tits, but it is difficult to conduct a macroscopic study due to spatial and temporal limitations. This study designed and applied a citizen-participatory monitoring of artificial nest boxes project to transcend the limitations of expert-centered monitoring methods. The Suwon Front Yard Bird Monitoring Team installed artificial nest boxes in green spaces in Suwon, Gyeonggi Province and observed the reproductive ecology of the Paridae family through the participation of voluntary citizen surveyors. Participants were recruited through an online survey from February 9 to February 22, 2021, and they directly performed from installation to observation of artificial next boxes from February 23 to August 31, 2021. Online education was provided to the volunteers for the entire monitoring process to lower the entry barrier for non-expert citizen surveyors and collect consistent data, and observation records were collected through a mobile app. A total of 98 citizen surveyors participated in the citizen-participatory monitoring of artificial nest boxes project, and 175 (84.95%) of the 256 distributed artificial nest boxes were installed in green spaces in Suwon City. Among the installed artificial nest boxes, the results of the citizen science project were confirmed for 173 (83.98%), excluding two boxes with position coordinate generation errors. A total of 987 artificial nest box observation records were collected from citizen surveyors, with a minimum of one time, a maximum of 26 times, and an average of 5.71±4.37 times. The number of observations of artificial birdhouses per month was 70 times (7.09%) in February, 444 times (44.98%) in March, 284 times (28.77%) in April, 133 times (13.48%) in May, 46 times (4.66%) in June, 6 times (0.61%) in July, and 4 times (0.41%) in August. Birds using the artificial nest boxes were observed in 57 (32.95%) of the 173 installed artificial nest boxes, and they included Great tit (Parus major) using 12 boxes (21.05%), Varied Tit (Parus varius) using 7 boxes (12.28%), and unidentified birds using 38 boxes (66.67%). This study is the first to consider citizen participation in the monitoring of artificial nest boxes, a survey method for the reproductive ecology of the Paridae family, including Great tits, and it can be utilized as basic data for the design of ecological monitoring combined with citizen science in the future.

Research on Making a Disaster Situation Management Intelligent Based on User Demand (사용자 수요 기반의 재난 상황관리 지능화에 관한 연구)

  • Seon-Hwa Choi;Jong-Yeong Son;Mi-Song Kim;Heewon Yoon;Shin-Hye Ryu;Sang Hoon Yoon
    • Korean Journal of Remote Sensing
    • /
    • v.39 no.5_2
    • /
    • pp.811-825
    • /
    • 2023
  • In accordance with the government's stance of actively promoting intelligent administrative service policies through data utilization, in the disaster and safety management field, it also is proceeding with disaster and safety management policies utilizing data and constructing systems for responding efficiently to new and complex disasters and establishing scientific and systematic safety policies. However, it is difficult to quickly and accurately grasp the on-site situation in the event of a disaster, and there are still limitations in providing information necessary for situation judgment and response only by displaying vast data. This paper focuses on deriving specific needs to make disaster situation management work more intelligent and efficient by utilizing intelligent information technology. Through individual interviews with workers at the Central Disaster and Safety Status Control Center, we investigated the scope of disaster situation management work and the main functions and usability of the geographic information system (GIS)-based integrated situation management system by practitioners in this process. In addition, the data built in the system was reclassified according to purpose and characteristics to check the status of data in the GIS-based integrated situation management system. To derive needed to make disaster situation management more intelligent and efficient by utilizing intelligent information technology, 3 strategies were established to quickly and accurately identify on-site situations, make data-based situation judgments, and support efficient situation management tasks, and implementation tasks were defined and task priorities were determined based on the importance of implementation tasks through analytic hierarchy process (AHP) analysis. As a result, 24 implementation tasks were derived, and to make situation management efficient, it is analyzed that the use of intelligent information technology is necessary for collecting, analyzing, and managing video and sensor data and tasks that can take a lot of time of be prone to errors when performed by humans, that is, collecting situation-related data and reporting tasks. We have a conclusion that among situation management intelligence strategies, we can perform to develop technologies for strategies being high important score, that is, quickly and accurately identifying on-site situations and efficient situation management work support.

Incidence of Hypertension in a Cohort of an Adult Population (성인코호트에서 고혈압 발생률)

  • Kam, Sin;Oh, Hee-Sook;Lee, Sang-Won;Woo, Kook-Hyeun;Ahn, Moon-Young;Chun, Byung-Yeol
    • Journal of Preventive Medicine and Public Health
    • /
    • v.35 no.2
    • /
    • pp.141-146
    • /
    • 2002
  • Objectives : This study was peformed in order to assess the incidence of hypertension based on two-years follow-up of a rural hypertension-free cohort in Korea. Methods : The study cohen comprised 2,580 subjects aged above 20 (1,107 men and 1,473 women) of Chung-Song County in Kyungpook Province judged to be hypertensive-free at the baseline examination in 1996. For each of two examinations in the two-year follow-up, those subjects free of hypertension were followed for the development of hypertension to the next examination one year (1997) and two years later (1998). The drop-out rate was 24.7% in men and 19.6% in women. Hypertension was defined as follows 1) above mild hypertension as a SBP above 140 mmHg or a DBP above 90 mmMg,2) above moderate hypertension as a SBP above 160 mmHg or a DBP above 100 mmHg or when the participant reported having used antihypertensive medication after beginning this survey. Results : The age-standardized incidence of above mild hypertension was 6 per 100 person years (PYS) in men and that of above moderate hypertension was 1.2. In women, the age-standardized rate for above mild hypertension was 5.7 and 1.5 for above mild and moderate hypertension, respectively. However, the rates of incidence as calculated by the risk method were 4.8% and 1.0% in men and 4.6%, 1.2% in women, respectively. In both genders, incidence was significantly associated with advancing age(p<0.01), In men, the incidences of above moderate hypertension by age group were 0.5 per 100 PYS aged 20-39, 0.7 aged 40-49, 1.7 aged 50-59, 3.6 aged 60-69, and 5.8 aged above 70(p<0.01). In women, those the incidence measured 0.6 per 100 PYS aged 20-39, 1.8 aged 40-49, 1.3 aged 50-59, 3.3 aged 60-69, and 5.6 aged above 70(p<0.01). After age 60, the incidence of hypertension increased rapidly. Conclusions : The incidence data of hypertension reported in this study may serve as a reference data for evaluating the impact of future public efforts in the primary prevention of hypertension in Korea.

A Study on the Palsapum (八賜品, Eight-Bestowed Things), Treasure No. 440, in Tong-Yong Shrine to the Loyal Dead in Korea (보물 제440호 통영 충렬사 팔사품(八賜品) 연구)

  • Jang, Kyung-hee
    • Journal of Korean Historical Folklife
    • /
    • no.46
    • /
    • pp.195-237
    • /
    • 2014
  • Palsapum are ornaments to reveal the purpose of commander of three naval forces as well as symbols to remember the greatness of admiral Yi, Sun-Shin. In 1966, ther were designated as a treasure No. 440 based on their value; however, they have not received attention from academia because they are relics from China. This study compares and analyzes the document, paintings, and relevant references from Korea and China focusing on Palsapum, understands their formal characteristics, and examines their historical value such as years and location of creation. As a result, the study determines five of them are original, but three of them were newly created by the later generations. The five, Dodogin (都督印, Commander's seal)·Yeongpae (令牌, Commander's tablet)·Gwido (鬼刀, Replica of the devil sword)·Chamdo (斬刀, Replica of the decapitation swor d)·and Gognapal (bugle) were created by Ming Dynasty before 1598, and delivered by the hands of General Chen Lin. The other three, Dokjeongi (督戰 旗, Battle flag)·Hongsoryeonggi (紅小令旗, Commander's flag)·and Namsoryeonggi (藍小令旗, Commander's flag), were created in 19th century by Joseon Dynasty. After analysis on the former relics, the study determines that they are not official relics with the dignity of Ming Dynasty but personal relics with regional characteristics; in other words, Palsamun are not the royal gifts from Emperor Shenzong to Admiral Yi, Sun-Shin. but personal momentoes left by General Chen Lin in the Tongjeyoung to celebrate the admiral. The names, variety, numbers, and appurtenances of Palsapum have been changed with time as follows. First, the scholars of Jeseon in 17the century only focused on Dodogin. It was certainly created in Ming Dynasty; however, it was a personal stamp, so considered to be not from the emperor but from General Chen Lin. Second, Palsapum was called Palsamul and consisted of 14 pieces of 8 kinds in 18the century, ; it is confirmed on the 「Dosul(圖說, stories with pictures of」 『Yi Chungmugong Literary Collection』 The sizes of five relics including Dodogin are similar to the records, but their patterns and shapes are exotic, or cannot be found in Joseon. Thus, they reflect the regional characteristics of Guangdong province. Third, they were called Palsapum, and consisted on 15 pieces of 8 kinds in 19th century; it is confirmed on , a sixteen-fold folding screen drawn by Shin, Gwan-Ho in 1861. The stamp box, tablet bag, and three flags were newly created to engrave Joseon style letters and patterns on damageable materials such as leather and cloth. The relics easy to be destroyed have been renewed even after 19th century. Last, there are many misunderstandings about Palsapum by governmental indifference and improper management of records even though they were designated as a treasure in very early times. Thus, authorities should be concerned with Palsapum to provide the measures for stable maintenance of the relics; this will let people remember not only the history of cooperation between Korea and China to stop the Japanese ambition, but also Admiral Yi, Sun-Shin and General Chen Lin to bring victory in Japanese invasions of Korea.