• 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 Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.103-128
• /
• 2021

Recently, investors' interest and the influence of stock-related information dissemination are being considered as significant factors that explain stock returns and volume. Besides, companies that develop, distribute, or utilize innovative new technologies such as artificial intelligence have a problem that it is difficult to accurately predict a company's future stock returns and volatility due to macro-environment and market uncertainty. Market uncertainty is recognized as an obstacle to the activation and spread of artificial intelligence technology, so research is needed to mitigate this. Hence, the purpose of this study is to propose a machine learning model that predicts the volatility of a company's stock price by using the internet search volume of artificial intelligence-related technology keywords as a measure of the interest of investors. To this end, for predicting the stock market, we using the VAR(Vector Auto Regression) and deep neural network LSTM (Long Short-Term Memory). And the stock price prediction performance using keyword search volume is compared according to the technology's social acceptance stage. In addition, we also conduct the analysis of sub-technology of artificial intelligence technology to examine the change in the search volume of detailed technology keywords according to the technology acceptance stage and the effect of interest in specific technology on the stock market forecast. To this end, in this study, the words artificial intelligence, deep learning, machine learning were selected as keywords. Next, we investigated how many keywords each week appeared in online documents for five years from January 1, 2015, to December 31, 2019. The stock price and transaction volume data of KOSDAQ listed companies were also collected and used for analysis. As a result, we found that the keyword search volume for artificial intelligence technology increased as the social acceptance of artificial intelligence technology increased. In particular, starting from AlphaGo Shock, the keyword search volume for artificial intelligence itself and detailed technologies such as machine learning and deep learning appeared to increase. Also, the keyword search volume for artificial intelligence technology increases as the social acceptance stage progresses. It showed high accuracy, and it was confirmed that the acceptance stages showing the best prediction performance were different for each keyword. As a result of stock price prediction based on keyword search volume for each social acceptance stage of artificial intelligence technologies classified in this study, the awareness stage's prediction accuracy was found to be the highest. The prediction accuracy was different according to the keywords used in the stock price prediction model for each social acceptance stage. Therefore, when constructing a stock price prediction model using technology keywords, it is necessary to consider social acceptance of the technology and sub-technology classification. The results of this study provide the following implications. First, to predict the return on investment for companies based on innovative technology, it is most important to capture the recognition stage in which public interest rapidly increases in social acceptance of the technology. Second, the change in keyword search volume and the accuracy of the prediction model varies according to the social acceptance of technology should be considered in developing a Decision Support System for investment such as the big data-based Robo-advisor recently introduced by the financial sector.

• Journal of Korean Society of Forest Science
• /
• v.111 no.1
• /
• pp.61-71
• /
• 2022

Data from an investigation of vulnerable conifer species in the subalpine zone in Korea obtained by the Korea Forest Service in 2017-2018 and monitoring research conducted by the National Institute of Forest Science since 2014 were used to analyze the status of distribution and growing condition of three major conifer species (Abies nephrolepis, Abies koreana, and Picea jezoensis) in the subalpine zone in the Baekdudaegan protected area. The distribution area of the studied species in the Baekdudaegan protected area was ca. 74% (8,035 ha) of the total distribution area in Korea, indicating that Baekdudaegan is a core area for conservation and restoration of subalpine conifer species. From decline index [A. nephrolepis in Mt. Taebaeksan and Mt. Deogyusan increased by 77.3% and 29.6%, respectively; A. koreana in Mt. Jirisan (Chunwangbong Peak) increased by 45.2% in four years; and P. jezoensis in Mt. Jirisan (Chunwangbong Peak) increased by 47.8% in two years] and seedling frequency (lower frequency of newly recruited seedlings than dead seedlings) results, the studied species are expected to face difficulties in sustainability. In contrast, at Mt. Seseoksan and Chunwangbong Peak in Mt. Jirisan, the health of trees and seedling frequency showed a partial tendency to recover and increase. In addition, we identified the relationship between the decline index and seedling frequency. These results will support the implementation of conservation strategies for vulnerable conifer species in the subalpine zone.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.1
• /
• pp.167-174
• /
• 2022

Since the Promotion Committee was established on March 25, 2021, urging the enactment of the Detective Business Act, many opinions and attention from all walks of life have been gathered. The Detective Business system, which is also one of the presidential pledges of the current 19th President Moon Jae In, is expected to be significant in that it can promote the development of a welfare state as well as efficient parts such as meeting the demand for security reinforcement services, improving the judicial system, and enhancing internationalization. In accordance with the consensus of the nine judges of the Constitutional Court that the lower part of Article 40 of the "Act on the Use and Protection of Credit Information" which prohibits the use of similar names such as investigating the general life of certain people does not violate the Constitution, detective work became possible regardless of the general life investigation. In particular, the detective job officially appeared on August 5, 2020, and it will be able to provide effective work services to the public by competing with prosecutors, police, and lawyers who have occupied exclusive positions in the field of a criminal investigations. However, although the role of detectives is gradually expanding and society is rapidly changing, illegal activities are prevalent throughout society, and more than 1,600 companies are currently operating suspiciously using the only name of "detectives", but the police are virtually letting go of the situation saying that they are "unauthorized.", and the damage is only going to the people, so at this point, the most worrisome thing is the absence of the law. Meanwhile, amid concerns over institutions overseeing illegal activities caused by the emergence of the detective industry, private security and detectives are similar to each other as in the United States, and it is expected to be able to gain public trust by entrusting the police in charge of managing and supervising private security companies. Therefore, at this time when most OECD countries except Korea legislate the Detective Business Act, prematurely allowing only the detective industry without enacting industry-related laws and systems can further fuel social confusion and hinder the detective industry along with the new fourth industry.

• Korean Journal of Heritage: History & Science
• /
• v.55 no.1
• /
• pp.111-132
• /
• 2022

The comprehensive examination on tendering system has been introduced to the Cultural Heritage repair and restoration field since 2016 to remedy the repair issues of South Gate in 2014. The Cultural Heritage Administration tried to attain the high performance of the cultural heritage repair and restoration works securing the proper payment for the repair and restoration works. It is high time to review the operating performance of the comprehensive examination on tendering system (hereinafter referred to as the "CEOTS"), as the system has been run for over 5 years to correspond with its original goal, i.e., "The Proper Payment in return for the High Performance of Repair and Restoration works." This study intends to analyze 114 tenders of CEOTS from 2016 to 2020. As a result of the analysis of 114 tenders, firstly, more than half of bid winners were in the top 20% of repair & restoration capacity disclosure amount list, which mostly fulfilled the goal of 'attaining high performance.' Secondly, as the winning bid rate is decreasing from 86.847% in 2017 to 85.488% in 2020, the goal of 'guarantee of a proper payment' is not achieved yet. Thirdly, the influence of Economic Evaluation section in CEOTS has been grown since the change of scoring system in CEOTS in 2019. This study identifies two reasons why the winning bid rate of CEOTS has decreased. Firstly, it is caused by the fact that 'the group that got more than 1st place' and 'the first place group' that are more than half of the total bidders have the decreasing bidding rate trend as the years go by. Secondly, the exclusion rate of 'the group that got more than 1st place' is higher than the exclusion rate of 'the group that got less than 1st place', which means the expected winning rate would be lowered. It is proposed that the revision of CEOTS code is needed, i.e. easing the strict rule concerning the exclusion rate as well as setting up the lower bidding limit to prevent the excessive decreasing winning bid rate.

• Journal of Korea Entertainment Industry Association
• /
• v.14 no.3
• /
• pp.191-200
• /
• 2020

Companies are seeking to maximize profits through exports and imports in the ultra-fast, ultra-high-speed modern society. It is only possible to sustain its survival if it targets the global market, not based on any specific region. The K-POP group is also targeting overseas markets in a manner similar to the various global strategies used when companies make inroads into foreign markets, including exports, contracts and direct investment. The K-POP group is engaged in various forms of activities, ranging from simple forms of performance (export) that are visited and staged by an invitation from a certain foreign country to series performances (license) by an invitation from a local promoter and tour performances using its capabilities. The K-POP group is seeking to go beyond the art of single-stage performances and make a systematic plan and make inroads into foreign countries in the form of direct investment suitable for each foreign country. The K-POP group made inroads into overseas markets in the form of simple performances from the late 1990s to 2005, when 'Korean Wave' was first introduced. Group H.O.T., etc. are typical examples. Since then, it has sought to enter overseas markets in the form of franchises by accepting overseas members by 2018, starting with Super Junior in 2005. Since then, the K-POP group in the form of joint investment attempted as group IZ*ONE in 2018 appeared, and a voice story came out in September 2018 when South Korea's JYP Entertainment and Tencent of China joined forces. Unlike K-POP Group, which has entered foreign markets with a global strategy based on the existing export method (H.O.T.), 'Boystory' is a representative group that is made with joint investment, which is a direct investment method. In February 2020, RBW released 'D1Verse,' a five-member group selected by Vietnam's reality show, as a joint investment-type group. This shows the possibility that domestic and foreign companies will release a group in the form of joint investment in order to pursue both globalization and localization.

• The Journal of the Korea Contents Association
• /
• v.22 no.10
• /
• pp.658-675
• /
• 2022

With the advent of the OTT platform, the world has become an era in which the same media content is shared and reacted in real time by being grouped into one culture. This study attempts a producer study of web novel writers, who are producers of the web novel market that is expanding into webtoons, dramas, and movies with IP (intellectual property rights) of the original story at a time when Korean K-content such as "Squid Game" and "Weird Lawyer Woo Young-woo" leads the global market. In this study, web novel writers were viewed as producers of commercial media content, not just 'Novelist', and their identities and characteristics of the labor process were examined. Web novel writers began writing web novels as a side job or two jobs, and cited the fact that they can make profits alone without barriers to entry and without incurring capital or facility costs. Although there is no barrier to entry, most writers experience severe failure in their first work, which is attributed to the misunderstanding that the word "writer" is someone who writes what they want in any genre. Web novels are different, so writers go through the process of realizing that in order to succeed by writing web novels, they must be thoroughly in the audience's shoes and write them according to the trends and codes they want. Web novel writers expressed their identity as "story sellers," "story producers," "people who can produce IP alone," and "people who satisfy fantasies that cannot be achieved in reality," and in common, there was a strong sense of being a person who provides stories and makes profits or sales. Regarding the burden of writing a huge amount of web novels, the writer with a high income expressed a generous position that "the income is higher than the effort," but ordinary writers complained of difficulties in the hard work, saying, "It seems like I am working hard on writing that I have to write constantly.

• 한국노년학
• /
• v.40 no.1
• /
• pp.197-216
• /
• 2020

This study aimed to suggest leisure activities and policy-level support in the light of the characteristics and needs among the elderly by examining constraint factors of leisure activities among the elderly. Data of 3887 elderly with the age of 65 and above with economic burden and health problems from the 6th Korean Retirement and Income study were used for the statistical analyses. Hierarchical linear models were tested by entering factors stepswise; demographic factors(age, gender, marriage status, single household, region, living expenses, health status) in the first step, leisure factors(leisure time, leisure motivation) in the second step, and lastly leisure activity factors(desired leisure activities, undesired leisure activities) in the third step. The results were as follows: First, major factors that constrict leisure activities of the elderly were financial burden and health problems. Second, there were significant differences among three(financial constraint, health constraint, and financial and health constraint) groups. Financial constraint group was the highest in the level of leisure satisfaction but leisure time was the shortest. The major reason to do leisure activities of the financial constraint group was to keep relationships with families and friends. In terms of desired leisure activities, health constraint group wanted resting, financial constraint group wanted hobbies and entertainment, and the financial-and-health constraint group wanted social activities. Third, financial constraint group demonstrated higher levels of leisure activity satisfaction when they wanted to take care of pets or gardens; however, they showed lower levels of leisure activity satisfaction when they wanted to domestic trips for desired leisure activities. In case of health constraint group, they demonstrated lower levels of leisure activity satisfaction whether or not they wanted resting like watching TV or listening to the radio. And, the showed higher levels of leisure activity satisfaction when they wanted social activities such as participation in religion or social gathering organizations. For the financial-and-health constraint group, whereas they showed lower levels of leisure activity satisfaction when they wanted walking around or watching TV, and domestic trips for desired leisure activities, they demonstrated higher levels of leisure activity satisfaction when they wanted entertainment doing the game of go, or chess, and hobbies like hiking and social activities. Practice and policy level suggestions to offer leisure activities that meet the needs of the elderly were made based on the study results.

• Korean Journal of Environment and Ecology
• /
• v.36 no.4
• /
• pp.361-367
• /
• 2022

This study was conducted to identify annual variation of observation and activity pattern of Korean chipmunk (Tamias sibiricus) using camera traps in the Seoraksan and Jirisan National Parks, South Korea from May 2019 to May 2021. The annual variation was identified based on the observed frequency through weekly observations. Daily activity patterns of the species were also analyzed by season. The daily activity pattern of chipmunk appeared to be constantly diurnal across the years regardless of habitat or season. The Korean chipmunks living in the two different regions were observed in different time periods throughout the year. While the chipmunks inhabiting the Seoraksan were observed from 18^th to 45^th week, the chipmunks inhabiting the Jirisan National Park were observed from 7^th to 48^th week. This may be influenced by the hibernation period of chipmunks in the two different regions. In both regions, chipmunks were most frequently observed in autumn. It is considered that seasonal variation on population dynamic and activity patterns of chipmunks were reflected in the observation frequency. Although the observation frequency of camera trap is an indirect indicator and thus having a limitation that it cannot distinguish the population density and amount of activity for the target species, camera trapping is still an effective survey technique for monitoring mammals due to its high accessibility and easy use.

• Journal of agricultural medicine and community health
• /
• v.47 no.3
• /
• pp.181-188
• /
• 2022

Objectives: The prevalence of diabetes mellitus was approximately 16% in populations of over age 30 years, and deaths from diabetes mellitus became the sixth most prevalent cause of death by disease. To assess the relationship between HbA1c and heavy metal level in blood and urine, targeted residents were evaluated in a vast steel industrial complex. Methods: We selected 414 subjects for analysis after applying the following exclusion criterion: 18 persons with diabetes mellitus. They took part in a questionnaire survey and underwent blood and urinary assessments. HbA1c and lead (Pb) level were measured in blood and, cadmium (Cd), inorganic arsenic (iAs) and mercury (Hg) were evaluated in urine. Two subgroups were divided by HbA1c 6.5%. Each subgroup was divided by 10th, 20th, 30th, 40th, 50th, 60th, 70th, 80th and 90th percentile levels of biological exposure index of the heavy metals for logistic regression. Results: Odd ratios have a tendency to increase as they go from the 90th to the 10th percentile of cadmium. However, lead, arsenic and mercury did not have significant relationships with HbA1c. In correction of age, region, gender and smoking history, a higher distribution in the subgroup with cadmium above 0.8318 ㎍/g creatinine (30th percentile) was demonstrated in the subgroup with HbA1c levels above the 6.5%, with an odds ratio of 5.26 (95% C.I. ; 1.44~19.17). Conclusion: This study found a significant correlation between urinary levels of cadmium and HbA1c in correction of several factors. It is meaningful that this outcome may be used as a basis for a study to establish the acceptable limit of urinary cadmium in Korea.