• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.127-146
• /
• 2017

Services using artificial intelligence have begun to emerge in daily life. Artificial intelligence is applied to products in consumer electronics and communications such as artificial intelligence refrigerators and speakers. In the financial sector, using Kensho's artificial intelligence technology, the process of the stock trading system in Goldman Sachs was improved. For example, two stock traders could handle the work of 600 stock traders and the analytical work for 15 people for 4weeks could be processed in 5 minutes. Especially, big data analysis through machine learning among artificial intelligence fields is actively applied throughout the financial industry. The stock market analysis and investment modeling through machine learning theory are also actively studied. The limits of linearity problem existing in financial time series studies are overcome by using machine learning theory such as artificial intelligence prediction model. The study of quantitative financial data based on the past stock market-related numerical data is widely performed using artificial intelligence to forecast future movements of stock price or indices. Various other studies have been conducted to predict the future direction of the market or the stock price of companies by learning based on a large amount of text data such as various news and comments related to the stock market. Investing on commodity asset, one of alternative assets, is usually used for enhancing the stability and safety of traditional stock and bond asset portfolio. There are relatively few researches on the investment model about commodity asset than mainstream assets like equity and bond. Recently machine learning techniques are widely applied on financial world, especially on stock and bond investment model and it makes better trading model on this field and makes the change on the whole financial area. In this study we made investment model using Support Vector Machine among the machine learning models. There are some researches on commodity asset focusing on the price prediction of the specific commodity but it is hard to find the researches about investment model of commodity as asset allocation using machine learning model. We propose a method of forecasting four major commodity indices, portfolio made of commodity futures, and individual commodity futures, using SVM model. The four major commodity indices are Goldman Sachs Commodity Index(GSCI), Dow Jones UBS Commodity Index(DJUI), Thomson Reuters/Core Commodity CRB Index(TRCI), and Rogers International Commodity Index(RI). We selected each two individual futures among three sectors as energy, agriculture, and metals that are actively traded on CME market and have enough liquidity. They are Crude Oil, Natural Gas, Corn, Wheat, Gold and Silver Futures. We made the equally weighted portfolio with six commodity futures for comparing with other commodity indices. We set the 19 macroeconomic indicators including stock market indices, exports & imports trade data, labor market data, and composite leading indicators as the input data of the model because commodity asset is very closely related with the macroeconomic activities. They are 14 US economic indicators, two Chinese economic indicators and two Korean economic indicators. Data period is from January 1990 to May 2017. We set the former 195 monthly data as training data and the latter 125 monthly data as test data. In this study, we verified that the performance of the equally weighted commodity futures portfolio rebalanced by the SVM model is better than that of other commodity indices. The prediction accuracy of the model for the commodity indices does not exceed 50% regardless of the SVM kernel function. On the other hand, the prediction accuracy of equally weighted commodity futures portfolio is 53%. The prediction accuracy of the individual commodity futures model is better than that of commodity indices model especially in agriculture and metal sectors. The individual commodity futures portfolio excluding the energy sector has outperformed the three sectors covered by individual commodity futures portfolio. In order to verify the validity of the model, it is judged that the analysis results should be similar despite variations in data period. So we also examined the odd numbered year data as training data and the even numbered year data as test data and we confirmed that the analysis results are similar. As a result, when we allocate commodity assets to traditional portfolio composed of stock, bond, and cash, we can get more effective investment performance not by investing commodity indices but by investing commodity futures. Especially we can get better performance by rebalanced commodity futures portfolio designed by SVM model.

• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.59-77
• /
• 2012

This study focuses on predicting which firms will increase capital by issuing new stocks in the near future. Many stakeholders, including banks, credit rating agencies and investors, performs a variety of analyses for firms' growth, profitability, stability, activity, productivity, etc., and regularly report the firms' financial analysis indices. In the paper, we develop predictive models for rights issues using these financial analysis indices and data mining techniques. This study approaches to building the predictive models from the perspective of two different analyses. The first is the analysis period. We divide the analysis period into before and after the IMF financial crisis, and examine whether there is the difference between the two periods. The second is the prediction time. In order to predict when firms increase capital by issuing new stocks, the prediction time is categorized as one year, two years and three years later. Therefore Total six prediction models are developed and analyzed. In this paper, we employ the decision tree technique to build the prediction models for rights issues. The decision tree is the most widely used prediction method which builds decision trees to label or categorize cases into a set of known classes. In contrast to neural networks, logistic regression and SVM, decision tree techniques are well suited for high-dimensional applications and have strong explanation capabilities. There are well-known decision tree induction algorithms such as CHAID, CART, QUEST, C5.0, etc. Among them, we use C5.0 algorithm which is the most recently developed algorithm and yields performance better than other algorithms. We obtained data for the rights issue and financial analysis from TS2000 of Korea Listed Companies Association. A record of financial analysis data is consisted of 89 variables which include 9 growth indices, 30 profitability indices, 23 stability indices, 6 activity indices and 8 productivity indices. For the model building and test, we used 10,925 financial analysis data of total 658 listed firms. PASW Modeler 13 was used to build C5.0 decision trees for the six prediction models. Total 84 variables among financial analysis data are selected as the input variables of each model, and the rights issue status (issued or not issued) is defined as the output variable. To develop prediction models using C5.0 node (Node Options: Output type = Rule set, Use boosting = false, Cross-validate = false, Mode = Simple, Favor = Generality), we used 60% of data for model building and 40% of data for model test. The results of experimental analysis show that the prediction accuracies of data after the IMF financial crisis (59.04% to 60.43%) are about 10 percent higher than ones before IMF financial crisis (68.78% to 71.41%). These results indicate that since the IMF financial crisis, the reliability of financial analysis indices has increased and the firm intention of rights issue has been more obvious. The experiment results also show that the stability-related indices have a major impact on conducting rights issue in the case of short-term prediction. On the other hand, the long-term prediction of conducting rights issue is affected by financial analysis indices on profitability, stability, activity and productivity. All the prediction models include the industry code as one of significant variables. This means that companies in different types of industries show their different types of patterns for rights issue. We conclude that it is desirable for stakeholders to take into account stability-related indices and more various financial analysis indices for short-term prediction and long-term prediction, respectively. The current study has several limitations. First, we need to compare the differences in accuracy by using different data mining techniques such as neural networks, logistic regression and SVM. Second, we are required to develop and to evaluate new prediction models including variables which research in the theory of capital structure has mentioned about the relevance to rights issue.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.123-139
• /
• 2019

The Korean NPL market was formed by the government and foreign capital shortly after the 1997 IMF crisis. However, this market is short-lived, as the bad debt has started to increase after the global financial crisis in 2009 due to the real economic recession. NPL has become a major investment in the market in recent years when the domestic capital market's investment capital began to enter the NPL market in earnest. Although the domestic NPL market has received considerable attention due to the overheating of the NPL market in recent years, research on the NPL market has been abrupt since the history of capital market investment in the domestic NPL market is short. In addition, decision-making through more scientific and systematic analysis is required due to the decline in profitability and the price fluctuation due to the fluctuation of the real estate business. In this study, we propose a prediction model that can determine the achievement of the benchmark yield by using the NPL market related data in accordance with the market demand. In order to build the model, we used Korean NPL data from December 2013 to December 2017 for about 4 years. The total number of things data was 2291. As independent variables, only the variables related to the dependent variable were selected for the 11 variables that indicate the characteristics of the real estate. In order to select the variables, one to one t-test and logistic regression stepwise and decision tree were performed. Seven independent variables (purchase year, SPC (Special Purpose Company), municipality, appraisal value, purchase cost, OPB (Outstanding Principle Balance), HP (Holding Period)). The dependent variable is a bivariate variable that indicates whether the benchmark rate is reached. This is because the accuracy of the model predicting the binomial variables is higher than the model predicting the continuous variables, and the accuracy of these models is directly related to the effectiveness of the model. In addition, in the case of a special purpose company, whether or not to purchase the property is the main concern. Therefore, whether or not to achieve a certain level of return is enough to make a decision. For the dependent variable, we constructed and compared the predictive model by calculating the dependent variable by adjusting the numerical value to ascertain whether 12%, which is the standard rate of return used in the industry, is a meaningful reference value. As a result, it was found that the hit ratio average of the predictive model constructed using the dependent variable calculated by the 12% standard rate of return was the best at 64.60%. In order to propose an optimal prediction model based on the determined dependent variables and 7 independent variables, we construct a prediction model by applying the five methodologies of discriminant analysis, logistic regression analysis, decision tree, artificial neural network, and genetic algorithm linear model we tried to compare them. To do this, 10 sets of training data and testing data were extracted using 10 fold validation method. After building the model using this data, the hit ratio of each set was averaged and the performance was compared. As a result, the hit ratio average of prediction models constructed by using discriminant analysis, logistic regression model, decision tree, artificial neural network, and genetic algorithm linear model were 64.40%, 65.12%, 63.54%, 67.40%, and 60.51%, respectively. It was confirmed that the model using the artificial neural network is the best. Through this study, it is proved that it is effective to utilize 7 independent variables and artificial neural network prediction model in the future NPL market. The proposed model predicts that the 12% return of new things will be achieved beforehand, which will help the special purpose companies make investment decisions. Furthermore, we anticipate that the NPL market will be liquidated as the transaction proceeds at an appropriate price.

• The Journal of Natural Sciences
• /
• v.14 no.1
• /
• pp.83-121
• /
• 2004

This study was carried out to examine how solid the production foundation of rice in Chung-Nam Province is, and, if not, to probe alternative measures through the size of farms specializing in rice, of which direction would be a pivot of rice industry-oriented policy. The results obtained can be summarized as follows : 1. The amount of rice production in Chung-Nam Province is highest in Korea and the size of paddy field area is the second largest : This implying that the probability that rice production in Chung-Nam Province would be severely influenced by a global trend of market conditions. The number of farms specializing in rice becoming the core group of rice farming account for 7.7 percent of the total number of farm household in Korea. Average field area financial support which had been input to farm household by Government had a noticeable effect on the improvement of the policy of farm-size program. 2. Farm-size program in Chung-Nam Province established from 1980 to 2002 in creased the cultivation size of paddy field to 19,484 hectares, and this program enhanced the buying and selling of farmland and the number of farmland bargain reached 6,431 household and 16,517 hectares, respectively, in 1995-2002. Meanwhile, long-term letting and hiring of farmland appeared so active that the bargain acreage reached 6,970 hectares, and farm involved was 7,059 households, however, the farm-exchange-and-unity program did not satisfy our expectation, because the retirement farm operators reluctantly participated to sell their farms. Another reason that had delayed the bargain of farms rested on the general category of social complication attendant upon the exchange and unity operation for scattered farm. Such difficulties would work negative effects out to carry on the target of farm-size work in general. 3. The following measures were presented to propel the farm-size promotion program : a. Occupation shift project, followed by the social security program for retirement and elderly farm operators, should be promptly established and also a number of types of incentives for promoting the letting and hiring work and farm-exchange-and-unity program would also be set up. b. To establish the effective key system of rice production, all the farm operators should increase the unit area yield of rice and lower the production cost. To do so, a great deal of production teams of rice equipped with managerial techniques and capabilities need to be organized. And, also, there should be appropriate arrays of facilities including information system. This plan is desirable to be in line with a diversity of the structural implement of regional integration based on farm system building. c. To extend the size of farm and to improve farm management, we have to devise the enlargement of individual size of farm for maximized management and the utilization of farm-size grouping method. In conclusion, it can be said that the farm-size project in Chung-Nam Province which has continued since the 1980s was satisfactorily achieved. However, we still have a lot of problems to be solved to break down the barrier for attainment of the desirable farm-size operation work.. Farm-size project has fairly close relation with farm specialization in rice and, thus, the positive support for farm household including the integrated program for both retirement farmers and off-farm operators should be considered to pursue the progressive development of the farm-size program, which is key means to successful achievement of rice farming enforcement in Chung-Nam Province.

• Korean journal of food and cookery science
• /
• v.17 no.1
• /
• pp.13-22
• /
• 2001

This study was to investigate the reason of family restaurant cook part employee's turnover. One hundred and forty seven family restaurant employees in Seoul area were surveyed to obtain the information from Oct. 1 to 10 in 2000. There were sixty males and eighty seven females. The group of twenty years old to twenty nine years old(95,2%) was the largest one by age, and the group of junior college graduated(71.4%) was the largest one by learning. On order, manager was 4.1%, captain was 13.6%, and employee was 82.3%. Except 15.6% employee, almost family restaurant cook part employees' service of duty was under 2 years. The highest scored turnover factor was work system(3.59), and then human relation(3.18), another way(3.11), unbelievable management(3.04). The rest factors effected on turnover not too much. The mean of female's turnover factor score(3.06) is higher then male(3.00), the group of over fifty years 0Id(3.32) had the highest mean score in aged group, on learning, the group of Master degree's mean score(4.24) is highest. The manager's mean score(3.23) was highest in order, and the employees who's service duty was over five years(3.35) had the highest mean score in service duty group.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.35 no.2
• /
• pp.112-118
• /
• 2015

This study was carried out to offer basic information for the promotion of the goat industry and the improvement of mountainous-pasture management by investigating seasonal changes in forage and livestock productivity according to the grazing-pasture type. The forage productivity of rangeland was the highest (p < 0.05) in summer and decreased in autumn; but that of pasture was the largest (p < 0.05) in spring and had relatively stable productivity with minor seasonal differences, although it decreased slightly in autumn. The dry matter content was not seasonally different at pasture, but it was changeable from spring to autumn at rangeland. The crude protein content increased in autumn at pasture (p < 0.05), and decreased in summer and autumn compared with spring at rangeland. The crude fiber content was lower and the ether extract was higher at pasture compared with rangeland. The average daily gain of the goats was different depending on forage productivity and pasture type; consequently, the lowered forage productivity at rangeland compared with pasture means that rangeland needs to be changed or improved to a pasture type that provides a more effective grazing system for goats.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.22 no.6
• /
• pp.731-737
• /
• 2016

To understand the characteristics and strength of the cold water that has caused damage to marine-culturing farms around Guryongpo, in the southwestern part of Korea, surface and water column temperatures were collected from temperature loggers deployed at a sea squirt farm during August-November 2007 and from a Real-time Information System for Aquaculture environment operated by NIFS (National Institute of Fisheries Science) during July-August 2015 and 2016. During the study period, surface temperature at Guryongpo decreased sharply when south/southwestern winds prevailed (the 18-26th of August and 20-22nd of September 2007 and the 13-15th of July 2015) as a result of upwelling. However, the deep-water (20-30m) temperature increased during periods of strong north/northeasterly winds (the 5-7th and 16-18th of September 2007) as a result of downwelling. Among the cold water events that occurred at Guryongpo, the mass death of cultured fish followed strong cold water events (surface temperatures below $10^{\circ}C$) that were caused by more than two days of successive south/southeastern winds with maximum speeds higher than 5 m/s. A Cold Water Index (CWI) was defined and calculated using maximum wind speed and direction as measured daily at Pohang Meteorological Observatory. When the average CWI over two days ($CWI_{2d}$) was higher than 100, mass fish mortality occurred. The four-day average CWI ($CWI_{4d}$) showed a high negative correlation with surface temperature from July-August in the Guryongpo area ($R^2=0.5$), suggesting that CWI is a good index for predicting strong cold water events and massive mortality. In October 2007, the sea temperature at a depth of 30 m showed a high fluctuation that ranged from $7-23^{\circ}C$, with frequency and spectrum coinciding with tidal levels at Ulsan, affected by the North Korean Cold Current. If temperature variations at the depth of fish cages also regularly fluctuate within this range, damage may be caused to the Guryongpo fish industry. More studies are needed to focus on this phenomenon.

• Journal of Animal Environmental Science
• /
• v.9 no.2
• /
• pp.123-130
• /
• 2003

In this study, current status of domestic deer farms and its feeding were surveyed. The information of supply and demand of feed f3r deers including its industry were also examined and then analyzed to make fundamental data for deer farms and government policy. The results are as follows. 1. Over 40 years old farmers were about 63％ of total deer farms while 20­30 years olds were less than 1％ indicating that young people still evade agriculture. Moreover, considering education, over 52％ of the farmers have bachelor degree showing much higher rates compared to the other agricultural fields. The reason can be assumed that the labor burden is not serious in deer farming while it is not dirty job compared to the other livestock management. Those high­educated people can be easily trained as experts of deer farming to improve its international competition. 2. Most of investigated farms raise Korean spotted deers and Elk showing that the percentage of Elk has greatly increased(However, many farmers have complained about purchasing methods and they insisted that the sales organization should be controlled by government). 3. 57％ of total cost of production is for feed while most of feeds are imported from abroad. It indicated that it is urgent to make counterplan for saving feed cost. 4. It is necessary to develop feeds for deers in the near future while most of the examined farmers currently use normal assorted feed. Typical roughage sources feeds are rice straw, alfalfa hay, browses feed, and so on. Most of them are currently imported except the rice straw indicating urgently needed to develop domestic bulky feed. 5. The present questions are development of processed goods of velvet antler, establishment of reasonable management system, difficulty of velvet antler selling, feed supply, and so on. It is necessary for government and academic world to develop reasonable policy and scientific research program.

• Knowledge Management Research
• /
• v.21 no.3
• /
• pp.45-65
• /
• 2020

It is desirable to invest in wine that increases its value, but wine investment itself is unfamiliar in Korea. Also, the process itself is unreasonable, and information is often forged, because pricing in the wine market is done by a small number of people. With the right solution, however, the wine market can be a desirable investment destination in that the longer one invests, the higher one can expect. Also, it is expected that the domestic wine consumption market will expand through the steady increase in domestic wine imports. This study presents the consortium block chain framework for revitalizing the wine market and enhancing transparency as the "right solution" of the nation's wine investment market. Blockchain governance can compensate for the shortcomings of the wine market because it guarantees desirable decision-making rights and accountability. Because the data stored in the block chain can be checked by consumers, it reduces the likelihood of counterfeit wine appearing and complements the process of unreasonably priced. In addition, digitization of assets resolves low cash liquidity and saves money and time throughout the supply chain through smart contracts, lowering entry barriers to wine investment. In particular, if the governance of the block chain is composed of 'chateau-distributor-investor' through consortium blockchains, it can create a desirable wine market. The production process is stored in the block chain to secure production costs, set a reasonable launch price, and efficiently operate the distribution system by storing the distribution process in the block chain, and forecast the amount of orders for futures trading. Finally, investors make rational decisions by viewing all of these data. The study presented a new perspective on alternative investment in that ownership can be treated like a share. We also look forward to the simplification of food import procedures and the formation of trust within the wine industry by presenting a framework for wine-owned sales. In future studies, we would like to expand the framework to study the areas to be applied.

• Food Science of Animal Resources
• /
• v.27 no.1
• /
• pp.122-126
• /
• 2007

Expenditure on meat and meat products has been increased in Korea due to the increase of income and the change of diet. From raising farm animals to eating the meat, various hazardous elements can make their ways into the meat and meat products. Recently the issues on food safety and hygiene are drawing a lot of attention, and the current system for managing the safety of foods is still needed to be improved. This survey was aimed to monitor the current situation of country-of-origin labels and hygiene for the meat markets at 4 regions Korea. The survey was performed by collecting samples from whole- sale and retail stores in the nation, which were selling beef. The markets were divided into groups as to territory and the size of the market (Large size, Medium size, and Small size). In terms of size distribution, small butcher shops occupied the highest percentage. On the itemized suitability test of unpacked and packed beef, all the market of 4 regions showed good agreements. However, such labels indicating the methods of cooking and storage were not properly posted on the products. Especially for Ho-nam region, corrections are needed. The results of monitoring sanitation conditions for the butcher shops at 4 regions in Korea showed relatively low suitability. Especially, there were serious lack of knowledge about wearing the sanitation clothing, caps, and shoes. The problem with food safety is so complicated that producer, consumer, food manufacturer, the press, the government, and scholar should solve altogether. It is necessary to educate farmers, food handlers, consumers, etc. and provide them with an accurate information and knowledge.