• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.241-254
• /
• 2011

Financial time-series forecasting is one of the most important issues because it is essential for the risk management of financial institutions. Therefore, researchers have tried to forecast financial time-series using various data mining techniques such as regression, artificial neural networks, decision trees, k-nearest neighbor etc. Recently, support vector machines (SVMs) are popularly applied to this research area because they have advantages that they don't require huge training data and have low possibility of overfitting. However, a user must determine several design factors by heuristics in order to use SVM. For example, the selection of appropriate kernel function and its parameters and proper feature subset selection are major design factors of SVM. Other than these factors, the proper selection of instance subset may also improve the forecasting performance of SVM by eliminating irrelevant and distorting training instances. Nonetheless, there have been few studies that have applied instance selection to SVM, especially in the domain of stock market prediction. Instance selection tries to choose proper instance subsets from original training data. It may be considered as a method of knowledge refinement and it maintains the instance-base. This study proposes the novel instance selection algorithm for SVMs. The proposed technique in this study uses genetic algorithm (GA) to optimize instance selection process with parameter optimization simultaneously. We call the model as ISVM (SVM with Instance selection) in this study. Experiments on stock market data are implemented using ISVM. In this study, the GA searches for optimal or near-optimal values of kernel parameters and relevant instances for SVMs. This study needs two sets of parameters in chromosomes in GA setting : The codes for kernel parameters and for instance selection. For the controlling parameters of the GA search, the population size is set at 50 organisms and the value of the crossover rate is set at 0.7 while the mutation rate is 0.1. As the stopping condition, 50 generations are permitted. The application data used in this study consists of technical indicators and the direction of change in the daily Korea stock price index (KOSPI). The total number of samples is 2218 trading days. We separate the whole data into three subsets as training, test, hold-out data set. The number of data in each subset is 1056, 581, 581 respectively. This study compares ISVM to several comparative models including logistic regression (logit), backpropagation neural networks (ANN), nearest neighbor (1-NN), conventional SVM (SVM) and SVM with the optimized parameters (PSVM). In especial, PSVM uses optimized kernel parameters by the genetic algorithm. The experimental results show that ISVM outperforms 1-NN by 15.32%, ANN by 6.89%, Logit and SVM by 5.34%, and PSVM by 4.82% for the holdout data. For ISVM, only 556 data from 1056 original training data are used to produce the result. In addition, the two-sample test for proportions is used to examine whether ISVM significantly outperforms other comparative models. The results indicate that ISVM outperforms ANN and 1-NN at the 1% statistical significance level. In addition, ISVM performs better than Logit, SVM and PSVM at the 5% statistical significance level.

• Journal of Korea Port Economic Association
• /
• v.27 no.1
• /
• pp.263-280
• /
• 2011

The global financial crisis, triggered by the subprime mortgage crisis in 2007, has put the world economy into the recession with financial market turmoil. I tested whether variables were cointegrated or whether there was an equilibrium relationship. Also, Generalized impulse-response function (GIRF) and accumulation impulse-response function (AIRF) may be used to understand and characterize the time series dynamics inherent in economical systems comprised of variables that may be highly interdependent. Moreover, the IRFs enables us to simulate the response in freight to a shock in the USD/JPY exchange rate, Dow Jones industrial average index, Dow Jones volatility, Chinese Import volatility. The result on the cointegration test show that the hypothesis of no cointergrating vector could be rejected at the 5 percent level. Also, the empirical analysis of cointegrating vector reveals that the increases of USD/JPY exchange rate have negative relations with freight. The result on the impulse-response analysis indicate that freight respond negatively to volatility, and then decay very quickly. Consequently, the results highlight the potential usefulness of the multivariate time series techniques accounting to behavior of Freight.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.3
• /
• pp.1151-1156
• /
• 2011

Leveraged buyouts (LBO) means the acquisition of a company using bonds and loans. There are the prolific volumes of LBO transactions in the international M&A markets, and its influence to the financial market is increasingly huge. However, there are very few LBO transaction in the domestic M&A market and there are also few researches in this field due to the private nature of LBO transactions. Once a company is privatized through a LBO transaction, it is not so long before it is relisted on the stock exchange or it is resold to a third-party investor. In order to repay the borrowed money, an LBO investor may decide to end a company's private status through an exit via an initial public offering (IPO) or a takeover. In this paper, we expand Kaplan's study on the organizational status of post leveraged buyout (LBO) transaction. We find that there is a significant change starting 1986. Most notably, fewer LBOs remain private, the median holding period of the LBO was cut in half to 3.2 years and of those that exit, IPO exits had significantly shorter holding periods. Regression analysis shows that good market conditions lengthen the holding period of a LBO investment whereas the size of the transaction shortens it.

• KDI Journal of Economic Policy
• /
• v.14 no.2
• /
• pp.3-27
• /
• 1992

In 1988, the government provided to the low income people 34.1% of the stocks of Pohang Iron & Steel Company through the People's Share Program of Privatization for the first time, and then in 1989 21% of the share of the Korea Electric Power Corporation were also provided to the low income classes through the same way. The purpose of the People's Share Program was known to be to support the low income classes through participating the profit of public enterprises, and also to expand the capital market through the diversification of stock holding structure. Initially, the government planned that the government share of enterprises such as the Citizens National Bank, the Korea Telecommunication Authority would be sold to the low income classes through the People's Share Program step by step. The income support policy, however, was no longer driven after 1989 when the overall stock prices started to decline. In this paper we tried to measure the effect of the privatization scheme of the public enterprises through the People's Share Program. The problems of the People's Share Program of the Pohang Iron & Steel Commpany and the Korea Electric Power Corperation were also identified. Several implications of the privatization scheme of the public enterprise through the People's Share Program by stages were found. The People's Share Program was found to be a non-stable policy measure for the income support of low income classes. The efficiency impact of the privatization through the People's Share Program was found to be non-significant.

• Land and Housing Review
• /
• v.14 no.4
• /
• pp.17-37
• /
• 2023

The rental housing market in South Korea, specifically monthly rent with deposit, has been expanding over the last three decades (8.2% in 1990 to 21.0% in 2020), partly replacing the traditional Jeonse market. The distribution of rent has changed due to public rental subsidies and the emergence of luxury rental housing, while the distribution of rental household income has been polarized because of the emergence of rich renters. This study attempts to measure the structural changes in the rental market by developing a new indicator of income-rent mismatch. Using the seven series of the Korea Housing Survey, this study analyzed the changes in rent (reflecting the conversion rate) and income levels of rental households in 2006 (base year) and 10-15 years later (the analysis year) at the national level and at the spatial unit of 16 metropolitan cities and provinces (excluding Sejong), respectively, by dividing them into quartile data. The result reveals that rental housing was undersupplied in middle- and high-income rental housing due to the decline in the highest quartile (25%→18%) and the third quartile groups (25%→20%), while the supply of public rental housing expanded for the second quartile (25%→28%) and the lowest quartile (25%→35) groups. On the demand side, the highest income quartile shrank (25%→21%), while the lowest income quartile grew (25%→31%). Comparing the 16 metropolitan cities and provinces, there were significant regional differences in the direction and intensity of changes in rent and renter household income. In particular, the rental market in Seoul was characterized by supply polarization, which led to an imbalance in the income distribution of rental households. The structural changes in the apartment rental market were different from those in the non-apartment rental market. The findings of this study can be used as a basis for future regional rental housing markets. The findings can support securing affordable rental housing stock for each income quartile group on monthly rent and developing housing stability measures for a balance between income and rent distribution in each region.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.2
• /
• pp.463-474
• /
• 2016

As IT environment has changed, paths of information security in financial environment which is based on IT have become more diverse and damage caused by information leakage has been more serious. Among security incidents, personal information leakage incident is liable to give the greatest damage. Personal information leakage incident is more serious than any other types of information leakage incidents in that it may lead to secondary damage. The purpose of this study is to find how much personal information leakage incident influences corporate value by analyzing 21 cases of personal information leakage incident for the last 15 years 1,899 listing firm through case research method and inferring investors' response of to personal information leakage incident surveying a change in transaction before and after personal information leakage incident. This study made a quantitative analysis of what influence personal information leakage incident has on outcome of investment by types of investors by classifying types of investors into foreign investors, private investors and institutional investors. This study is significant in that it helps improve awareness of importance of personal information security by providing data that personal information leakage incident can have a significant influence on outcome of investment as well as corporate value in Korea stock market.

• Management & Information Systems Review
• /
• v.31 no.1
• /
• pp.221-246
• /
• 2012

The study examines the effects that non-audit service and firm's ownership structure might have on the value relevance directly or indirectly. This investigation is based on prior research which suggests that the audit firms' non-audit services is likely to adversely affect investors' perceptions of the credibility of financial reporting and that corporate governance are likely to mitigate the adverse this kind of non-audit services effects. The sample consists of non-banking firms listed on the Korea Exchange that reported annual financial statements over the period from 2004 to 2008. In the setting, stock returns as proxy for capital market response, auditor quality(measured as the discretionary accruals) is endogenously determined. This study employs a structural equation model to take into account the endogenous variables under study. The analysis influences through the path analysis that ownership structure suppress the market response through audit quality and also the non-audit service have influence on the market response through audit quality. The results of this study contribute to the literature in the following ways. First, this provides direct evidence that there is a negative association between audit firms' client importance and the value relevance. Second, the findings that the negative association is attenuated for audit quality support the findings of prior studies which present that corporate governance provide higher credibility of financial reports.

• Journal of Global Scholars of Marketing Science
• /
• v.16 no.1
• /
• pp.117-141
• /
• 2006

Daily sales volume in retailers seems to be changed because of five-days-work in a week resulting in growth of leisure time in Korea recently. The day of the week effect of sales volume that can not be theoretically explained, which sales pattern varies depending on days systematically and consistently, is so important. Especially the day of the week effect of sales volume exists in which retail branch and the extents of the day of the week effect from the perspective of marketing in retailing is very important. Thus, the purpose of this study was to investigate whether the day of the week effect of sales volume exists in men's clothing retailers and if so, there is difference in daily sales volume. There was insufficient researches in the field of anomaly such as the day of the week effect of sales volume in marketing. For this reason, this study has drawn upon research findings of finance, general demand theory, and previous studies of the day of the week effect in stock markets. In doing so, these works are referenced in theoretical background and applicability in retailing market of this study. This study empirically investigated the day of the week effect of sales volume through the revenues of a men's clothing retailers (P company) in past five years. As the result of this study, the day of the week effect of sales volume existed in men's clothing retailers and the day of the week effect showed positive from Monday to Sunday, which means Sunday, the biggest. Also, the day of the week effect by season was different. The result of this study is expected to provide some helpful evidence that offers effective operational strategies to retailers.

• International Area Studies Review
• /
• v.15 no.1
• /
• pp.291-314
• /
• 2011

We examine the motives of foreigner's investments in the Korean bonds by maturity and try to prove that market impacts are different by their investment maturity. Foreign investors initially focused on short-term bonds, but have expanded to mid- to long-term bonds since 2010. The previous studies found that covered interest arbitrage was the main reason for foreign investment. However, there should be some other reasons as their investment in mid- to long-term bonds might have nothing to do with arbitrage. In the empirical analysis, we found that foreign investment in bonds with less than 2 year maturity is driven by arbitrage as previous studies. However, investment in bonds with 2-5 year maturity is sensitive to the FX volatility and the stock market performance compared with the U.S. and investment in bonds with more than 5 year maturity is driven by the CDS premium differential between Korea and PIIGS countries. The more foreigners have invested mid- to long-term bonds, the stronger downward pressure has been on the bond yields. In addition, foreign investors indirectly affected the spreads. Meanwhile, the government should prepare some policy measures since concerns over side effects such as the Korean won appreciation and an abrupt capital outflow are arising.

• The Journal of Fisheries Business Administration
• /
• v.24 no.2
• /
• pp.1-16
• /
• 1993

Because of the radical changes in the domestic and foreign economic circumstances Koreaa fisheries is confronted with difficulties. Along the end of the UR marine products of other nations are rushing into Korea. Also migration of labor to other industries and rise of wage level in Korean fisheries deteriorate managerial conditions. But in Korea which has little natural resourses fisheries is still more important. That is \circled1 creating job opportunites \circled2 increase of income \circled3 supply of foodstuffs and animal protein \circled4 acquisition of foreign currency \circled5 enlargement of domestic market for industrial products \circled6 development of other interrelated industries \circled7 rational use of domestic resourses \circled8 diversification of population and production activites \circled9 contribution to balanced growth of national economy by the developing regional economy. These roles of fisheries in national economy mentioned above are to be excuted forward. In spite of the radical change in the economic circumstances at the end of the UR fisheries if crucial in Korea as a industry. For this our fisheries is to be made to compete with foreign fisheries. Through the cheap price and high quality our fisheries must be came to compete with foreign fisheries and meet the people's needs for marine products. For this it is necessary to maintain high productivity and competitive power. Now with the exception of a portion of the deep - sea fishing, our fisheries is generally paltry, Especially inshore fishery which is the main stock in our fisheries is very paltry and so productivity and competetive power are very low. So to develop our fisheries which has s comparative disadvantage active polices that follows below are to be promoted on a large scale. \circled1 improvement of structure \circled2 augmentation of productivity in fishing ground by making fisheries resourses \circled3 enlargement of finantial and monetary assistance \circled4 effective administration of fisheries cooperative union \circled5 activation of R&D etc These polices which need to be scientific and comprehensive are very valuable. Especially without making fishieries resources we cannot expect economy of scale, promotion of productivity and development of fisheries. And we do also endeavour to gather the results of the study and investigation about fisheries domestic and foreign and do ceaselessly put these to practical use systimatically.