• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.1-17
• /
• 2019

Because stock price forecasting is an important issue both academically and practically, research in stock price prediction has been actively conducted. The stock price forecasting research is classified into using structured data and using unstructured data. With structured data such as historical stock price and financial statements, past studies usually used technical analysis approach and fundamental analysis. In the big data era, the amount of information has rapidly increased, and the artificial intelligence methodology that can find meaning by quantifying string information, which is an unstructured data that takes up a large amount of information, has developed rapidly. With these developments, many attempts with unstructured data are being made to predict stock prices through online news by applying text mining to stock price forecasts. The stock price prediction methodology adopted in many papers is to forecast stock prices with the news of the target companies to be forecasted. However, according to previous research, not only news of a target company affects its stock price, but news of companies that are related to the company can also affect the stock price. However, finding a highly relevant company is not easy because of the market-wide impact and random signs. Thus, existing studies have found highly relevant companies based primarily on pre-determined international industry classification standards. However, according to recent research, global industry classification standard has different homogeneity within the sectors, and it leads to a limitation that forecasting stock prices by taking them all together without considering only relevant companies can adversely affect predictive performance. To overcome the limitation, we first used random matrix theory with text mining for stock prediction. Wherever the dimension of data is large, the classical limit theorems are no longer suitable, because the statistical efficiency will be reduced. Therefore, a simple correlation analysis in the financial market does not mean the true correlation. To solve the issue, we adopt random matrix theory, which is mainly used in econophysics, to remove market-wide effects and random signals and find a true correlation between companies. With the true correlation, we perform cluster analysis to find relevant companies. Also, based on the clustering analysis, we used multiple kernel learning algorithm, which is an ensemble of support vector machine to incorporate the effects of the target firm and its relevant firms simultaneously. Each kernel was assigned to predict stock prices with features of financial news of the target firm and its relevant firms. The results of this study are as follows. The results of this paper are as follows. (1) Following the existing research flow, we confirmed that it is an effective way to forecast stock prices using news from relevant companies. (2) When looking for a relevant company, looking for it in the wrong way can lower AI prediction performance. (3) The proposed approach with random matrix theory shows better performance than previous studies if cluster analysis is performed based on the true correlation by removing market-wide effects and random signals. The contribution of this study is as follows. First, this study shows that random matrix theory, which is used mainly in economic physics, can be combined with artificial intelligence to produce good methodologies. This suggests that it is important not only to develop AI algorithms but also to adopt physics theory. This extends the existing research that presented the methodology by integrating artificial intelligence with complex system theory through transfer entropy. Second, this study stressed that finding the right companies in the stock market is an important issue. This suggests that it is not only important to study artificial intelligence algorithms, but how to theoretically adjust the input values. Third, we confirmed that firms classified as Global Industrial Classification Standard (GICS) might have low relevance and suggested it is necessary to theoretically define the relevance rather than simply finding it in the GICS.

• The Korean Journal of Financial Management
• /
• v.24 no.4
• /
• pp.75-106
• /
• 2007

In this study, it is analyzed whether oil price plays a major role in the pricing return on Koran stock market and examined why the covariance risk between oil and return on stock is different in each industry. Firstly, this study explores whether the expected rate of return on stock is pricing due to global oil price factors as a function of risk premium by using a two-factor APT. Also, it is examined whether spill-over effects of oil price volatility affect the beta risk to oil price. Considering the asymmetry of oil price volatility, we use the GJR model. As a result, it shows that oil price is an independent pricing factor and oil price volatility transmits to stock return in only electricity and electrical equipment. Secondly, the two step-analyzing process is introduced to find why the covariance between oil price factor and stock return is different in each industry. The first step is to study whether beta risk exists in each industry by using two proxy variables like size and liquidity as control variables. The second step is to grasp the systematic relationship between the difference of liquidity and size and beta to oil price factor by using the panel-data model which can be analyzed efficiently using the cross-sectional data formed with time series. Through the analysis, we can argue that oil price factor is an independent pricing factor in only electricity and electrical equipment having the greatest market capitalization, and know that beta risk to oil price factor is a proxy of size in the other industries. According to the result of panel-data model, it is argued that the beta to oil price factor augments when market capitalization increases and this fact supports the first assertion. In conclusion, the expected rate of return of electricity and electrical equipment works as a function of risk premium to market portfolio and oil price, and the reason to make beta risk power differentiated in each industry attributes to the size.

• Environmental and Resource Economics Review
• /
• v.20 no.3
• /
• pp.489-529
• /
• 2011

When greenhouse gas mitigation policies are implemented, energy intensive manufacturing industries are influenced much due to an increase in cost. However, industries that have price setting power are damaged less by the policies. Therefore, this paper analyzes vulnerability of energy intensive manufacturing industries to the policies by measuring price setting power of the industries. We analyzed price setting power model through ECM, employing the import prices and wages as independent variables. The industries that their prices react to import prices are price takers, which their prices are determined by rival's ones. On the other hand, the industry that their prices react to wages that mean domestic cost are price setters, and they will be less vulnerable to the policies. In addition, fluctuation of energy prices would be reflected in import prices because it influences other countries than my one. Thus, we employed energy prices as control variable to measure the net effects of import prices. As empirical results, petroleum products, chemical products, non-metallic mineral products, textiles, and motor vehicles sector have price setting power, so the industries have competitiveness on greenhouse gas mitigation policies.

• Journal of Environmental Science International
• /
• v.18 no.4
• /
• pp.389-400
• /
• 2009

In this research, we measured the number of lanes, distance, disposition of apartment that are affecting the road traffic noise to evaluate the current condition of G city's road traffic noise. We decide on a basis regarding an apartment price formation factor, and the apartment current price and the results that compared. To have a point scale, we set the maximum road traffic noise at a 8 lane road for 5 points, give 4 points for a 6 lane road, which has a $2.1{\sim}2.5\;dB(A)$ difference compared to a 8 lane road, give 3 points for a 4 lane road, which has a $5.2{\sim}5.5\;dB(A)$ difference compared to a 8 lane road, and set 2 points for a 2 lane road and lower. If we set the standard floor plan as horizontal and a living room facing the roadside, the horizontal and living room facing the opposite side of the road is 1 point because it differs by 14.1 dB(A), and the vertical is 3 points since the difference is 5.3 dB(A). If we make grades by the distance, making standard the fifth floor with little soundproof effect from apartment to road, we observe a measurement below 2.9 dB(A) at a distance of less than 10 m and 5 dB(A), decreased at a distance of 20 m. Therefore, 4 points were given for less than 10m, 3 points for $10{\sim}20\;m$, 2 points for more than 20 m as we can apply the effect of a decay distance of line sound source and the decrease in noise effects of more than 6 dB(A), 1 point for more than 40m, and 0 points for more that 80 m since it is negligible. 28 apartments got 0 points because there is no effect of road traffic noise from other apartments, and 50 apartments where only the road at one side effect them got $5{\sim}10$ points. 4 apartments (17-2, 6-3, 10-4, 3-3) received over 20 points. 15 cases showed a difference between developer price and resale price, and 11 cases (73%) among them showed the same trend (price increases with a low road traffic noise restriction factor point) with the point of road traffic noise restriction factor. 4 cases demonstrated the opposite trend, showing price increases with a high restriction factor point. Among the 4 cases, case numbers 2,6 and 9 appear to be more affected by the location factor (business district) than the road traffic noise restriction factor, and case number 1 appears to be affected by the building factor (openness and direction).

• Journal of the Korean Geographical Society
• /
• v.38 no.6
• /
• pp.949-960
• /
• 2003

The marginal implicit price of air quality can be measured by taking a partial derivative of hedonic price function (HPF) with respect to the level of air quality. It has been pointed out that the size of the marginal implicit price varies with the use of different function forms, different estimation methods, and the different ways of measuring air quality level in estimating HPF. In addition to these factors, this study shows theoretically and empirically the way housing properties are represented on a digital map could differentiate the size of marginal implicit price of air quality when GIS is used to measure location attributes of the housing properties in the Korean apartment market. Furthermore, this study shows that the degree of difference in the marginal implicit price due to the manner in which housing properties are represented on a digital map can be larger than the degree of difference in the marginal implicit price due to using different function forms and estimation methods. The major implication from the results of this study is that one should carefully try diverse ways of representing housing properties in the Korean apartment market on a digital map in the process of estimating HPF, as he or she usually tries diverse function forms and estimation methods, to see if the value of the marginal implicit price of air quality varies substantially.

• Journal of Digital Convergence
• /
• v.20 no.3
• /
• pp.231-240
• /
• 2022

This study empirically analyzed the effect of complex commercial facilities on the price of nearby apartments in a Hedonic price model. The spatial range of this study was the walking area of H Department Store located in Pangyo among the second new towns suburb of Seoul, and the time range was 2020. The dependent variable was the real transaction price of the apartment, and independent variable were the characteristics of the housing, the characteristics of the complex, and the characteristics of the region. As a result of the analysis, the area of exclusive use space, the transaction floor, and the highway accessibility had a positive effect on the price of the apartment, and the elapsed year had a negative effect on the price of the apartment. However, the size of the apartment had little effect on apartment prices, and the distance from the complex commercial facilities was shown to be related to apartment prices, indicating that apartment prices declined as it moved away from the complex commercial facilities. Therefore, this is much more influential than the influence of distance from subway stations on apartment price. This confirms that the effect factors of apartment prices and the size of their influence appear differently in the new town area and the existing metropolitan area.

• Journal of Preventive Medicine and Public Health
• /
• v.30 no.4 s.59
• /
• pp.697-707
• /
• 1997

This study was performed to estimate the quantity of the effects of tobacco price raise on the smoking rate, and the smoking attributable deaths in Korea. The data were collected by questionnaire survey from 538 male of male workers. The questionnaire contained items on age, sex, living place, status of education, smoking history, the intention to quit smoking when the tobacco price be raised. The questionnaire, were distributed to the offices of enterprises, hospitals, research centers, and public agencies and then collected. Data were analyzed by using the age specific smoking rate, relative risks of eight major smoking related diseases, vital statistics, and the population attributable risk of deaths of smoking males. On the other hand, the impact of the tobacco price raise on the population attributable risk of death due to smoking in Korea was estimated by applying the presumed smoking rate after the price raise. The results obtained were as follows: 1. The smoking rate of male white color workers in large cities was 59.5%. 2. The proportion of male smokers who has the intention to quit smoking when the tobacco price be raised was 61.5%. 3. The proportion of male smokers who has the intention to quit smoking if the price of tobacco be raised was proportional to the degree of increasing tobacco price. It is estimated that if the tobacco price were raised more than four times as now, the presumed smoking rate goes down as low as 26.7%. If the tobacco price be raised 20% each year, presumed smoking rate is 46.2%. 4. The number of attributable male death of smoking estimated by using 8 major smoking related diseases(lung cancer, laryngeal cancer, esophageal cancer, stomach cancer, pancreatic cancer, cerebrovascular disease, ischemic heart disease, chronic obstructive pulmonary disease) was 25,863 death each year. That is 20.1% of total age over 20 male deaths. 5. f the tobacco price were raised more than four times as now and all smokers who has intention to quit smoking quits smoking, 12,336 lives, or 47.7% of smoking related deaths could be saved. 6. IF the actual practice rate of quitting smoking among male smokers with intention to stop smoking when the price of tobacco be raised is 10%, 25%, or 50%, then the expected decrease of death numbers when the tobacco price were raised more than four times as now can be 1,112, 3,483, 5,796 respectively.

• Journal of Distribution Science
• /
• v.9 no.4
• /
• pp.15-27
• /
• 2011

Although a huge number of academic researchers have paid considerable attention to exploring both the degree to which store image influences retailer brand customers and how to develop store personality, they have overlooked the contemporary retail context in which retailers have developed many different types of retailer brands, that is, price-oriented or quality-oriented retailer brands. Rather than focusing on the latter, much literature has looked at the former. Accordingly, even though there are many articles related to store image, a few authors have shown their interest in identifying the extent to which store personality affects customers purchasing retailer brands at lower prices. As a result, their efforts have been to illustrate the relationship between store image and consumer behaviours buying retailer brands. In that multiple retailers over the world such as E-Mart, Lotte-Mart, Tesco Korea and Tesco UK have actively introduced not only the quality-focused retailer brands that quality is better than, or equal to national brands, and prices are slightly higher than, or equal to them, but also price-focused retailer brands, academicians should make an effort to investigate how store image affects customers purchasing a quality-oriented retailer brand, comparing with previous research results. That is why the authors illustrate the extent to which store personality components influence retailer brand customers, including particularly quality-oriented retailer brand customers through an empirical research. By adopting a questionnaire method as a research technique to illuminate the relationship between store image components and retailer brand customers, research validity increases and further, data gathered through a field survey are analysed through a few statistic analysis methods, in order to minimise statistical deviations. Compared with the prior research concentrated on price-focused retailer brands, the authors have significantly shed light on customer behaviours purchasing retailer brand products with higher quality. When it comes to store personality components, the research suggests the following five items: merchandise attributes, services, physical facilities, promotions, and institutional image, considering the subcomponents mentioned by the previous research. Proposing the conceptual research model which those elements are differently hypothesised, according to retailer brand types: PR (Price-oriented Retailer brand) and QR (Quality-oriented Retailer brand), the research is proceeded. Through empirical research, the authors found that amongst the five items, only promotion influenced retailer brand customers in the Korean retailing marketplace, unlike other countries explored by many researchers, such as UK. Although much literature emphasises that those elements are closely related to retailer brand buying proneness, it is completely not fit to the Korean market. Also, research findings provide new insights into the degree of store image effects on retailer brand customers for academiciansand practitioners. Whether the retailer brand development program that a retailer has carried simultaneously both price-focused and quality-focused retailer brand types is practically profitable should be explored in the future.

• KDI Journal of Economic Policy
• /
• v.29 no.3
• /
• pp.29-73
• /
• 2007

This paper evaluates the effects of the Basic Subsidy Program provided to families with infants cared for in private day care centers. There has been a discrepancy in the price and quality level between public and private day care centers. Public day care centers which receive government support in their labor costs are able to maintain relatively higher quality at lower price than their private counterparts, while the majority of children are cared for at private day care centers. To reduce the gap of the price and quality of care between public and private day care centers by improving the quality and decreasing the price of private day care centers, the Basic Subsidy Program was introduced in 2006 to the private day care centers. The subsidies mainly aim to improve the quality and the accessibility of child care, and encourage mothers' labor supply. For this purpose, the provision of the Basic Subsidy Program imposed prerequisites to the care providers including minimum wage and four major insurances for teachers, and child-staff ratio. I examine whether the subsidies improve the quality of care, help mothers balancing work and family, and increase satisfaction with child care from mothers' perspective. Since the outcome variables that measure the quality of care are difficult to obtain, I instead use the input variables for quality production. Child-staff ratio, teachers' welfare, and care environment are considered. The relationship between these variables and the introduction of subsidies is examined. The 2004 National Survey of Child Care and Education and the 2004 National Survey of Day Care Centers are used for the base data set. To reflect the outcomes after the Basic Subsidy Program, equivalent data sets for households and care providers are constructed by the KDI Data Analysis Unit. Using these nationally representative data sets, information regarding child care is collected. The findings show that the subsidies contribute to the quality of care improving the input variables of quality production. The welfare of teachers is improved, and the child-staff ratio significantly decreases. As a result, the usage of private day care centers greatly increases even though the price level rarely changes. However, mothers' satisfaction with child care are rarely affected by the subsidies. Although the subsidies with no eligibility criteria enlarge the recipients, the actual effects to increase maternal labor supply or to improve satisfaction is limited. Given this findings, I suggest some modifications of subsidies to raise the effectiveness of the subsidy program.

• Environmental and Resource Economics Review
• /
• v.26 no.2
• /
• pp.257-286
• /
• 2017

This paper estimates the effects of imaginary repeated increases in excise duties on fuel oil consumption and on their income redistribution according to changes in consumer price index, if the inflation indexation system was introduced right after the second Energy Tax Reform ended in July, 2007 in Korea. In fact, nominal excise rates have not been adjusted since 2007. As a result, the real excise rates on fuel oils have been diminished inversely proportional to the consumer price index. Own- and cross-price elasticities of fuel oils such as gasoline and diesel oil are estimated under the general equilibrium framework based on the linear expenditure system. Counterfactual analyses through microsimulation in a static model are adopted to estimate the effects of introducing inflation indexation into the fuel tax in 2007 when the second Energy Tax reform ended on the fuel consumption and income redistribution in 2014. Microsimulations suggest that its introduction could have reduced the consumption of gasoline and diesel oil by 8.8% and 5.4%, respectively, ending up with increased excise revenue by 11.9%. The revenue increase in spite of decreased consumption is mainly because their demands are price inelastic. It could also have increased positive income redistributive effect by 0.01%p (from 0.12% to 0.13%), which is measured in terms of percentage decrease in Gini coefficient. In other words, the fuel excise on the two fuel oils decreased by 0.13% the Gini coefficient of before and after fuel tax income in 2014. This implies that the inflation indexation could have enlarged the income redistributive effect up to 0.13% in 2014, if it is introduced in 2007.