• Management & Information Systems Review
• /
• v.29 no.2
• /
• pp.1-25
• /
• 2010

This study attempted to empirically test the determinants of stock returns in Korean stock market applying multi-factor model proposed by Haugen and Baker(1996). Regression models were developed using 16 variables related to liquidity, risk, historical price, price level, and profitability as independent variables and 690 stock monthly returns as dependent variable. For the statistical analysis, the data were collected from the Kis Value database and the tests of forecasting power in this study minimized various possible bias discussed in the literature as possible. The statistical results indicated that: 1) Liquidity, one-month excess return, three-month excess return, PER, ROE, and volatility of total return affect stock returns simultaneously. 2) Liquidity, one-month excess return, three-month excess return, six-month excess return, PSR, PBR, ROE, and EPS have an antecedent influence on stock returns. Meanwhile, realized returns of decile portfolios increase in proportion to predicted returns. This results supported previous study by Haugen and Baker(1996) and indicated that firm-characteristic model can better predict stock returns than CAPM. 3) The firm-characteristic model has better predictive power than Fama-French three-factor model, which indicates that a portfolio constructed based on this model can achieve excess return. This study found that expected return factor models are accurate, which is consistent with other countries' results. There exists a surprising degree of commonality in the factors that are most important in determining the expected returns among different stocks.

• Asia pacific journal of information systems
• /
• v.24 no.4
• /
• pp.559-575
• /
• 2014

Individual investors are increasingly flocking to message boards to seek, clarify, and exchange information. Businesses like Seekingalpha.com and business magazines like Fortune are evaluating, synthesizing, and reporting the comments made on message boards or blogs. In March of 2012, Yahoo! Finance Message Boards recorded 45 million unique visitors per month followed by AOL Money and Finance (19.8 million), and Google Finance (1.6 million) [McIntyre, 2012]. Previous studies in the finance literature suggest that online communities often provide more accurate information than analyst forecasts [Bagnoli et al., 1999; Clarkson et al., 2006]. Some studies empirically show that the volume of posts in online communities have a positive relationship with market activities (e.g., trading volumes) [Antweiler and Frank, 2004; Bagnoli et al., 1999; Das and Chen, 2007; Tumarkin and Whitelaw, 2001]. The findings indicate that information in online communities does impact investors' investment decisions and trading behaviors. However, research explicating the correlation between information on online communities and stock market activities (e.g., trading volume) is still evolving. Thus, it is important to ask whether a volume of posts on online communities influences trading volumes and whether trading volumes also influence these communities. Online stock message boards offer two different types of information, which can be explained using an economic and a psychological perspective. From a purely economic perspective, one would expect that stock message boards would have a beneficial effect, since they provide timely information at a much lower cost [Bagnoli et al., 1999; Clarkson et al., 2006; Birchler and Butler, 2007]. This indicates that information in stock message boards may provide valuable information investors can use to predict stock market activities and thus may use to make better investment decisions. On the other hand, psychological studies have shown that stock message boards may not necessarily make investors more informed. The related literature argues that confirmation bias causes investors to seek other investors with the same opinions on these stock message boards [Chen and Gu, 2009; Park et al., 2013]. For example, investors may want to share their painful investment experiences with others on stock message boards and are relieved to find they are not alone. In this case, the information on these stock message boards mainly reflects past experience or past information and not valuable and predictable information for market activities. This study thus investigates the two roles of stock message boards-providing valuable information to make future investment decisions or sharing past experiences that reflect mainly investors' painful or boastful stories. If stock message boards do provide valuable information for stock investment decisions, then investors will use this information and thereby influence stock market activities (e.g., trading volume). On the contrary, if investors made investment decisions and visit stock message boards later, they will mainly share their past experiences with others. In this case, past activities in the stock market will influence the stock message boards. These arguments indicate that there is a correlation between information posted on stock message boards and stock market activities. The previous literature has examined the impact of stock sentiments or the number of posts on stock market activities (e.g., trading volume, volatility, stock prices). However, the studies related to stock sentiments found it difficult to obtain significant results. It is not easy to identify useful information among the millions of posts, many of which can be just noise. As a result, the overall sentiments of stock message boards often carry little information for future stock movements [Das and Chen, 2001; Antweiler and Frank, 2004]. This study notes that as a dependent variable, trading volume is more reliable for capturing the effect of stock message board activities. The finance literature argues that trading volume is an indicator of stock price movements [Das et al., 2005; Das and Chen, 2007]. In this regard, this study investigates the correlation between a number of posts (information on stock message boards) and trading volume (stock market activity). We collected about 100,000 messages of 40 companies at KOSPI (Korea Composite Stock Price Index) from Paxnet, the most popular Korean online stock message board. The messages we collected were divided into in-trading and after-trading hours to examine the correlation between the numbers of posts and trading volumes in detail. Also we collected the volume of the stock of the 40 companies. The vector regression analysis and the granger causality test, 3SLS analysis were performed on our panel data sets. We found that the number of posts on online stock message boards is positively related to prior stock trade volume. Also, we found that the impact of the number of posts on stock trading volumes is not statistically significant. Also, we empirically showed the correlation between stock trading volumes and the number of posts on stock message boards. The results of this study contribute to the IS and finance literature in that we identified online stock message board's two roles. Also, this study suggests that stock trading managers should carefully monitor information on stock message boards to understand stock market activities in advance.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.135-149
• /
• 2020

Artificial intelligences are changing world. Financial market is also not an exception. Robo-Advisor is actively being developed, making up the weakness of traditional asset allocation methods and replacing the parts that are difficult for the traditional methods. It makes automated investment decisions with artificial intelligence algorithms and is used with various asset allocation models such as mean-variance model, Black-Litterman model and risk parity model. Risk parity model is a typical risk-based asset allocation model which is focused on the volatility of assets. It avoids investment risk structurally. So it has stability in the management of large size fund and it has been widely used in financial field. XGBoost model is a parallel tree-boosting method. It is an optimized gradient boosting model designed to be highly efficient and flexible. It not only makes billions of examples in limited memory environments but is also very fast to learn compared to traditional boosting methods. It is frequently used in various fields of data analysis and has a lot of advantages. So in this study, we propose a new asset allocation model that combines risk parity model and XGBoost machine learning model. This model uses XGBoost to predict the risk of assets and applies the predictive risk to the process of covariance estimation. There are estimated errors between the estimation period and the actual investment period because the optimized asset allocation model estimates the proportion of investments based on historical data. these estimated errors adversely affect the optimized portfolio performance. This study aims to improve the stability and portfolio performance of the model by predicting the volatility of the next investment period and reducing estimated errors of optimized asset allocation model. As a result, it narrows the gap between theory and practice and proposes a more advanced asset allocation model. In this study, we used the Korean stock market price data for a total of 17 years from 2003 to 2019 for the empirical test of the suggested model. The data sets are specifically composed of energy, finance, IT, industrial, material, telecommunication, utility, consumer, health care and staple sectors. We accumulated the value of prediction using moving-window method by 1,000 in-sample and 20 out-of-sample, so we produced a total of 154 rebalancing back-testing results. We analyzed portfolio performance in terms of cumulative rate of return and got a lot of sample data because of long period results. Comparing with traditional risk parity model, this experiment recorded improvements in both cumulative yield and reduction of estimated errors. The total cumulative return is 45.748%, about 5% higher than that of risk parity model and also the estimated errors are reduced in 9 out of 10 industry sectors. The reduction of estimated errors increases stability of the model and makes it easy to apply in practical investment. The results of the experiment showed improvement of portfolio performance by reducing the estimated errors of the optimized asset allocation model. Many financial models and asset allocation models are limited in practical investment because of the most fundamental question of whether the past characteristics of assets will continue into the future in the changing financial market. However, this study not only takes advantage of traditional asset allocation models, but also supplements the limitations of traditional methods and increases stability by predicting the risks of assets with the latest algorithm. There are various studies on parametric estimation methods to reduce the estimated errors in the portfolio optimization. We also suggested a new method to reduce estimated errors in optimized asset allocation model using machine learning. So this study is meaningful in that it proposes an advanced artificial intelligence asset allocation model for the fast-developing financial markets.

• 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.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.10
• /
• pp.441-450
• /
• 2014

The stock market is constantly changing and sometimes the stock prices unaccountably plummet or surge. So, the stock market is recognized as a complex system and the change on the stock prices is unpredictable. Recently, many researchers try to understand the stock market as the network among individual stocks and to find a clue about the change of the stock prices from big data being created in real time from Internet. We focus on the correlation between the stock prices and the human interactions in Internet especially in the stock message boards. To uncover this correlation, we collected and investigated the articles concerning with 57 target companies, members of KOSPI200. From the analysis result, we found that there is no significant correlation between the stock prices and the article volume, but the strength of correlation between the article volume and the stock prices is relevant to the stock return. We propose a new method for recommending stock portfolio base on the result of our analysis. According to the simulated investment test using the article data from the stock message boards in 'Daum' portal site, the returns of our portfolio is about 1.55% per month, which is about 0.72% and 1.21% higher than that of the Markowitz's efficient portfolio and that of the KOSPI average respectively. Also, the case using the data from 'Naver' portal site, the stock returns of our proposed portfolio is about 0.90%, which is 0.35%, 0.40%, and 0.58% higher than those of our previous portfolio, Markowitz's efficient portfolio, and KOSPI average respectively. This study presents that collective human behavior on Internet stock message board can be much helpful to understand the stock market and the correlation between the stock price and the collective human behavior can be used to invest in stocks.