• Journal of the Korea Society of Computer and Information
• /
• v.21 no.6
• /
• pp.9-19
• /
• 2016

In finance literature, stock liquidity showing how stocks can be cashed out in the market has received rich attentions from both academicians and practitioners. The reasons are plenty. First, it is known that stock liquidity affects significantly asset pricing. Second, macroeconomic announcements influence liquidity in the stock market. Therefore, stock liquidity itself affects investors' decision and managers' decision as well. Though there exist a great deal of literature about stock liquidity in finance literature, it is quite clear that there are no studies attempting to investigate the stock liquidity issue as one of decision making problems. In finance literature, most of stock liquidity studies had dealt with limited views such as how much it influences stock price, which variables are associated with describing the stock liquidity significantly, etc. However, this paper posits that stock liquidity issue may become a serious decision-making problem, and then be handled by using data mining techniques to estimate its future extent with statistical validity. In this sense, we collected financial data set from a number of manufacturing companies listed in KRX (Korea Exchange) during the period of 2010 to 2013. The reason why we selected dataset from 2010 was to avoid the after-shocks of financial crisis that occurred in 2008. We used Fn-GuidPro system to gather total 5,700 financial data set. Stock liquidity measure was computed by the procedures proposed by Amihud (2002) which is known to show best metrics for showing relationship with daily return. We applied five data mining techniques (or classifiers) such as Bayesian network, support vector machine (SVM), decision tree, neural network, and ensemble method. Bayesian networks include GBN (General Bayesian Network), NBN (Naive BN), TAN (Tree Augmented NBN). Decision tree uses CART and C4.5. Regression result was used as a benchmarking performance. Ensemble method uses two types-integration of two classifiers, and three classifiers. Ensemble method is based on voting for the sake of integrating classifiers. Among the single classifiers, CART showed best performance with 48.2%, compared with 37.18% by regression. Among the ensemble methods, the result from integrating TAN, CART, and SVM was best with 49.25%. Through the additional analysis in individual industries, those relatively stabilized industries like electronic appliances, wholesale & retailing, woods, leather-bags-shoes showed better performance over 50%.

• International Journal of Railway
• /
• v.1 no.4
• /
• pp.129-133
• /
• 2008

Over the last $15{\sim}20$years, many countries have adopted policies of railway privatization to keep up with increasing competition from road and air transport. Although each country and case has its own history, market characteristics, political context as well as administrative process, railway privatizations (including railway restructure, concession etc.) in the west usually are accompanied with the establishment of new regulatory regimes. Therefore, railway governance has been innovating towards an interaction of government, regulator, industry bodies, user groups, trade unions and other interested groups within the regulatory framework. However, it is not the case in China. Although China had seen a partial privatization in some branch lines and is experiencing a much larger-scale privatization by establishing joint-ventures to build and operate high-speed passenger lines and implementing an asset-based securitization program, administrative control still occupies absolutely dominant position in the railway governance in China. Ministry of Railway (MOR) acts as the administrator, operator as well as regulator. There is no national policy that clearly positions railway in the transportation network and clarifies the role of government in railway development. There is also little participation from interested groups in the railway policy making, pricing, service standard or safety matter. Railway in China is solely governed by the mere executive agency. Efficiency-focused economic perspective explanation is far from satisfaction. A wider research perspective from political and social regime is of great potential to better explain and solve the problem. In the west, separation and constrains of power had long been established as a fundamental rule. In addition to internal separation of political power(legislation, execution and jurisdiction), rise of corporation in the 19th century and association revolution in the 20th century greatly fostered the growth of economic and social power. Therefore, political, social and economic organizations cooperate and compete with each other, which leads to a balanced and resonable power structure. While in China, political power, mainly party-controlled administrative power has been keeping a dominated position since the time of plan economy. Although the economic reform promoted the growth of economic power of enterprises, it is still not strong enough to compete with political power. Furthermore, under rigid political control, social organizations usually are affiliated to government, independent social power is still too weak to function. So, duo to the limited and slow reform in political and social regime in China, there is an unbalanced power structure within which political power is dominant, economic power expanding while social power still absent. Totally different power structure in China determines the fundamental institutional environment of her railway privatization and governance. It is expected that the exploration of who act behind railway governance and their acting strength (a power theory) will present us a better picture of railway governance as a relevant transportation mode. The paper first examines the railway governance in China and preliminarily establishes a linkage between railway governance and its fundamental institutional environment, i.e. power structure in a specific country. Secondly, the reason why there is no national policy in China is explored in the view of political power. In China, legislative power is more symbolic while party-controlled administrative power dominates political process and plays a fundamental role in Chinese railway governance. And then, in the part three railway finance reform is analyzed in the view of economic power, esp. the relationship of political power and economic power.

• Journal of the Economic Geographical Society of Korea
• /
• v.12 no.4
• /
• pp.665-680
• /
• 2009

This study aims at analyzing the performance of Real Estate Investment Trusts(REITs) by Risk Adjustment Model. The main results are as follows. Firstly, most property types of REITs gain positive(+) excess overall returns at first and second period. On the contrary, most property types of REITs gain negative(-) excess overall returns and their standard deviations are larger at financial crisis period. Secondly, lodging, regional mall and commercial mortgage show lower risk-lower return, and freestanding, apartment and specialty show higher risk-higher return than average REITs, according to the CAPM results of . Moreover CAPM results of show the characteristics of REITs as investment commodities changes into higher risk-higher return for financial crisis period. Lastly, risk adjusted demanded returns of REITs are affected positively(+) by systemic risks and negatively(-) by unsystemic risks, according to the Risk Adjustment Model results of both and . Comparing risk adjusted demanded returns of REITs with their realized returns, healthcare reveals the largest outperformance.

• Management & Information Systems Review
• /
• v.37 no.4
• /
• pp.63-74
• /
• 2018

Recently, in the asset management industry, the smart beta strategy, which has an intermediate nature between passive and active strategies, is attracting attention. In this smart beta strategy, value, momentum, low volatility, and quality index are widely used. In this study, we analyzed the quality index which is not clear and complicated to calculate. According to the MSCI methodology, the quality index was calculated using three variables: return on equity, debt to equity, and earnings variability. In addition, we use the index using only return on equity variable, the index using only two variables of return on equity and debt to equity, and the KOSPI index as comparison targets for the quality index. In order to evaluate the performance of the indices used in the analysis, the arithmetic mean return, the coefficient of variation, and the geometric mean return were used. In addition, Fama and French (1993) model, which is widely used in related studies, was used as a pricing model to test whether abnormal returns in each index are occurring. The results of the empirical analysis are as follows. First, in all period analysis, quality index was the best in terms of holding period returns. Second, the quality index performed best in the currency crisis and the global financial crisis. Third, abnormal returns were not found in all indices before the global financial crisis. Fourth, in the period after the global financial crisis, the quality index has the highest abnormal return.

• Journal of Industrial Convergence
• /
• v.20 no.11
• /
• pp.75-83
• /
• 2022

This study analyzes whether investor sentiment and liquidity explain the momentum phenomenon in the Korean stock market and whether it is a risk factor for the asset pricing model. The empirical analysis used the monthly returns of non-financial companies listed on the stock market during the period 2000-2021. As a result of the analysis, first, it was found that there is a momentum effect in Korea. This is the same result as the previous study, and since 2000, the momentum effect has been accepted as a general phenomenon in the Korean stock market. Second, if we look at the portfolio based on investor sentiment, investor sentiment is influencing momentum. In particular, when investor sentiment is negative, the return on the winner portfolio is high. Third, as a result of the analysis based on liquidity, the momentum effect disappears and a reversal effect appears. Fourth, it was found that investor sentiment and liquidity influence the momentum effect. This is a result of the strong momentum effect in the illiquid stock group with negative investor sentiment. Fifth, as a result of analyzing the effect of each factor on stock returns, it was found that both investor psychology and liquidity factors have a significant impact on returns. The estimated results provide evidence that the inclusion of these two factors in the Carhart four-factor model significantly increases the predictive power of the model. Therefore, it can be said that investor sentiment factors and liquidity factors are important factors in determining stock returns.

• Land and Housing Review
• /
• v.14 no.4
• /
• pp.63-76
• /
• 2023

Investors should understand and actively consider factors like location, future value, policies, pricing, market trends, and their income, as these elements can shift with changing local, social, economic, and policy environments. This study seeks to clarify the impact of investment factors on the performance and reinvestment intentions of Sejong City investors by surveying those who have invested in real estate. This study employs a structural equation model with confirmatory factor analysis, focusing on four aspects: value, economic and policy, psychological, and financial. We find that the investment value factor has the largest impact on investment performance, indicating that investors prioritize the investment value of real estate in Sejong City. In addition, factors increasing asset value and expected satisfaction were significant, indicating that real estate investment in Sejong City yields high returns and investor satisfaction. with a positive outlook for future reinvestment.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.

• The Korean Journal of Financial Management
• /
• v.21 no.2
• /
• pp.125-151
• /
• 2004

This study tests the price discovery from US Treasury bond markets to Korean bond markets using the daily returns of Korean bond data (CD, 3-year T-note, 5-year T-note, 5-year corporate note) and US treasury bond markets (3-month T-bill, 5-year T-note 10-year T-bond) from July 1, 1998 to December 31, 2003. For further research, we divide full data into two sub-samples on the basis of the start-up of bond valuation system in Korean bond market July 1, 2000, employing uni-variate AR(1)-GARCH(1,1)-M model. The main results are as follows. First the volatility spillover effects from US Treasury bond markets (3-month T-bill, 5-year T-note, 10-year T-bond) to Korean Treasury and Corporate bond markets (CD, 3-year T-note, 5-year T-note, 5-year corporate note) are significantly found at 1% confidence level. Second, the price discovery function from US bond markets to Korean bond markets in the sub-data of the pre-bond valuation system exists much stronger and more persistent than those of the post-bond valuation system. In particular, the role of 10-year T-bond compared with 3-month T-bill and 5-year T-note is outstanding. We imply these findings result from the international capital market integration which is accelerated by the broad opening of Korean capital market after 1997 Korean currency crisis and the development of telecommunication skill. In addition, these results are meaningful for bond investors who are in charge of capital asset pricing valuation, risk management, and international portfolio management.