• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.129-148
• /
• 2023

Bitcoin is a blockchain technology-based digital currency that has been recognized as a representative cryptocurrency and a financial investment asset. Due to its highly volatile nature, Bitcoin has gained a lot of attention from investors and the public. Based on this popularity, numerous studies have been conducted on price and trend prediction using machine learning and deep learning. This study employed LSTM (Long Short Term Memory) and CNN (Convolutional Neural Networks), which have shown potential for predictive performance in the finance domain, to enhance the classification accuracy in Bitcoin price trend prediction. XAI(eXplainable Artificial Intelligence) techniques were applied to the predictive model to enhance its explainability and interpretability by providing a comprehensive explanation of the model. In the empirical experiment, CNN was applied to technical indicators and Google trend data to build a Bitcoin price trend prediction model, and the CNN model using both technical indicators and Google trend data clearly outperformed the other models using neural networks, SVM, and LSTM. Then SHAP(Shapley Additive exPlanations) was applied to the predictive model to obtain explanations about the output values. Important prediction drivers in input variables were extracted through global interpretation, and the interpretation of the predictive model's decision process for each instance was suggested through local interpretation. The results show that our proposed research framework demonstrates both improved classification accuracy and explainability by using CNN, Google trend data, and SHAP.

• 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.

• KDI Journal of Economic Policy
• /
• v.30 no.1
• /
• pp.1-31
• /
• 2008

Various opinions have been suggested to explain the slump in equipment investment, such as increased government regulations, shareholder-oriented management by expanded foreign equity investment, response against M&A threats, conservative investment trends seen after a series of bankruptcy of large conglomerates (amidst crumbling myth of "Too Big to Fail"), and financial restructuring. Some also argued that the increased uncertainty in business environment is mainly responsible for conservative management, though there are few domestic studies made regarding the situation. But, in other countries, including the U.S., studies have shown that more volatility is seen now surrounding stock prices, profitability, and sales growth rate reflecting business performance. Also, there are other studies showing such expanded volatility have led to conservative management by businesses. In this regard, this study reviews the volatility conditions of business performance of Korean companies based on profitability, and then attempts to analyze the impact on investment brought on by increased volatility. Each company's profitability volatility used here is from the standard deviation of companies for the past five years. As a profitability indicator, the ROA (= operating profit/total asset) is used. According to the analysis, profitability volatility has remarkably increased from the mid 3% in 1994 to low 5% in 2005. Profitability volatility of the Korean companies has expanded to a great extent since the financial crisis. The crisis might have served to raise the volatility in the macroeconomic conditions. If increased volatility observed during the economic crisis had gradually declined after the crisis, the situation could be interpreted as a temporary phenomenon, not to be too concerned over. But, this was not the case for Korea. The volatility level, after the crisis, has not dropped back to its pre-crisis level. Hence, in the Korea's case, high volatility cannot be explained by the impact of financial crisis. Not only that, the fact that such expansion is seen in every industrial sector indicates that this phenomenon cannot be explained by the composition change of industries alone. An undergoing study shows that with a rapid spread of globalization, industries fiercely competing with China experience more volatility. Such increased volatility tends to contract investment, and since the crisis the impact of volatility on investment has slightly increased. It is noteworthy that this study only includes a part of 'uncertainty' that could be measured statistically. For instance, the profitability volatility indicator used in this study is unable to reflect all the effects that the tacit reduction of protection by the government or regulations might have made. So, the result here also indicates that other 'uncertain' factors not mentioned in this study may have served to contract investment sentiment. It would be impossible for policies to completely remove uncertainties measured by profitability volatility, but at least it is necessary to put effort to reduce the macroeconomic volatility in the future economic management. Stabilized macroeconomic management may not be enough to diminish all volatility that occurs within each company, but it would make a meaningful contribution in encouraging investment.

• Journal of the Economic Geographical Society of Korea
• /
• v.17 no.3
• /
• pp.502-516
• /
• 2014

This study has decomposed the Gini coefficient using Korean Labor & Income Panel Study data and empirically analyzed the impact of demographic characteristics and source-specific income of householder on the household income gap using panel analysis. The scope of areas were divided into 'nationwide,' 'metropolitan areas,' and 'non-metropolitan areas,' and the period before and after the global financial crisis was examined. The analysis findings are as follows. First, when the entire period was examined by income source using Gini decomposition with division of areas into 'nationwide,' 'metropolitan areas,' and 'non-metropolitan areas', the following results were revealed. The absolute and relative contribution level of property income to the gross income was the largest in the category of 'nationwide' and 'metropolitan areas,' while the contribution level of earned income was the largest in the category of 'non-metropolitan areas'. In addition, property income worsened the household income gap the most in the category of 'nationwide' and 'metropolitan areas.' Second, property income worsened the household income gap less after the financial crisis than before the crisis. It is probably because the price of real estate skyrocketed before the global financial crisis, worsening the household income gap, whereas the price drop after the crisis temporarily alleviated the gap. Third, a correlation analysis revealed that households with older householders whose education is high school graduation or below had relatively low gross income, and households with higher source-specific income, especially earned income, had relatively high gross income. Fourth, when the household income determinants were compared through panel analysis with division of areas into 'nationwide,' 'metropolitan areas,' and 'non-metropolitan areas,' the following results were obtained. While the impact of earned income, financial income, and other incomes was greater in non-metropolitan areas than in metropolitan areas, the impact of property income was greater in metropolitan areas than in non-metropolitan areas. To reduce the income gap, the government should impose higher taxes on the high-income class and provide tax benefits to the low-income class, with efforts to create a wide variety of jobs. In addition, since income inequality gets worse as the proportion of incomes generated through asset holdings becomes higher, the government should focus on stabilizing property prices while paying attention to the regional differentiation when carrying out related policies.

• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.147-168
• /
• 2017

There have been many studies on accurate stock market forecasting in academia for a long time, and now there are also various forecasting models using various techniques. Recently, many attempts have been made to predict the stock index using various machine learning methods including Deep Learning. Although the fundamental analysis and the technical analysis method are used for the analysis of the traditional stock investment transaction, the technical analysis method is more useful for the application of the short-term transaction prediction or statistical and mathematical techniques. Most of the studies that have been conducted using these technical indicators have studied the model of predicting stock prices by binary classification - rising or falling - of stock market fluctuations in the future market (usually next trading day). However, it is also true that this binary classification has many unfavorable aspects in predicting trends, identifying trading signals, or signaling portfolio rebalancing. In this study, we try to predict the stock index by expanding the stock index trend (upward trend, boxed, downward trend) to the multiple classification system in the existing binary index method. In order to solve this multi-classification problem, a technique such as Multinomial Logistic Regression Analysis (MLOGIT), Multiple Discriminant Analysis (MDA) or Artificial Neural Networks (ANN) we propose an optimization model using Genetic Algorithm as a wrapper for improving the performance of this model using Multi-classification Support Vector Machines (MSVM), which has proved to be superior in prediction performance. In particular, the proposed model named GA-MSVM is designed to maximize model performance by optimizing not only the kernel function parameters of MSVM, but also the optimal selection of input variables (feature selection) as well as instance selection. In order to verify the performance of the proposed model, we applied the proposed method to the real data. The results show that the proposed method is more effective than the conventional multivariate SVM, which has been known to show the best prediction performance up to now, as well as existing artificial intelligence / data mining techniques such as MDA, MLOGIT, CBR, and it is confirmed that the prediction performance is better than this. Especially, it has been confirmed that the 'instance selection' plays a very important role in predicting the stock index trend, and it is confirmed that the improvement effect of the model is more important than other factors. To verify the usefulness of GA-MSVM, we applied it to Korea's real KOSPI200 stock index trend forecast. Our research is primarily aimed at predicting trend segments to capture signal acquisition or short-term trend transition points. The experimental data set includes technical indicators such as the price and volatility index (2004 ~ 2017) and macroeconomic data (interest rate, exchange rate, S&P 500, etc.) of KOSPI200 stock index in Korea. Using a variety of statistical methods including one-way ANOVA and stepwise MDA, 15 indicators were selected as candidate independent variables. The dependent variable, trend classification, was classified into three states: 1 (upward trend), 0 (boxed), and -1 (downward trend). 70% of the total data for each class was used for training and the remaining 30% was used for verifying. To verify the performance of the proposed model, several comparative model experiments such as MDA, MLOGIT, CBR, ANN and MSVM were conducted. MSVM has adopted the One-Against-One (OAO) approach, which is known as the most accurate approach among the various MSVM approaches. Although there are some limitations, the final experimental results demonstrate that the proposed model, GA-MSVM, performs at a significantly higher level than all comparative models.