• Asia pacific journal of information systems
• /
• v.24 no.2
• /
• pp.233-253
• /
• 2014

Can the stock market really be predicted? Stock market prediction has attracted much attention from many fields including business, economics, statistics, and mathematics. Early research on stock market prediction was based on random walk theory (RWT) and the efficient market hypothesis (EMH). According to the EMH, stock market are largely driven by new information rather than present and past prices. Since it is unpredictable, stock market will follow a random walk. Even though these theories, Schumaker [2010] asserted that people keep trying to predict the stock market by using artificial intelligence, statistical estimates, and mathematical models. Mathematical approaches include Percolation Methods, Log-Periodic Oscillations and Wavelet Transforms to model future prices. Examples of artificial intelligence approaches that deals with optimization and machine learning are Genetic Algorithms, Support Vector Machines (SVM) and Neural Networks. Statistical approaches typically predicts the future by using past stock market data. Recently, financial engineers have started to predict the stock prices movement pattern by using the SNS data. SNS is the place where peoples opinions and ideas are freely flow and affect others' beliefs on certain things. Through word-of-mouth in SNS, people share product usage experiences, subjective feelings, and commonly accompanying sentiment or mood with others. An increasing number of empirical analyses of sentiment and mood are based on textual collections of public user generated data on the web. The Opinion mining is one domain of the data mining fields extracting public opinions exposed in SNS by utilizing data mining. There have been many studies on the issues of opinion mining from Web sources such as product reviews, forum posts and blogs. In relation to this literatures, we are trying to understand the effects of SNS exposures of firms on stock prices in Korea. Similarly to Bollen et al. [2011], we empirically analyze the impact of SNS exposures on stock return rates. We use Social Metrics by Daum Soft, an SNS big data analysis company in Korea. Social Metrics provides trends and public opinions in Twitter and blogs by using natural language process and analysis tools. It collects the sentences circulated in the Twitter in real time, and breaks down these sentences into the word units and then extracts keywords. In this study, we classify firms' exposures in SNS into two groups: positive and negative. To test the correlation and causation relationship between SNS exposures and stock price returns, we first collect 252 firms' stock prices and KRX100 index in the Korea Stock Exchange (KRX) from May 25, 2012 to September 1, 2012. We also gather the public attitudes (positive, negative) about these firms from Social Metrics over the same period of time. We conduct regression analysis between stock prices and the number of SNS exposures. Having checked the correlation between the two variables, we perform Granger causality test to see the causation direction between the two variables. The research result is that the number of total SNS exposures is positively related with stock market returns. The number of positive mentions of has also positive relationship with stock market returns. Contrarily, the number of negative mentions has negative relationship with stock market returns, but this relationship is statistically not significant. This means that the impact of positive mentions is statistically bigger than the impact of negative mentions. We also investigate whether the impacts are moderated by industry type and firm's size. We find that the SNS exposures impacts are bigger for IT firms than for non-IT firms, and bigger for small sized firms than for large sized firms. The results of Granger causality test shows change of stock price return is caused by SNS exposures, while the causation of the other way round is not significant. Therefore the correlation relationship between SNS exposures and stock prices has uni-direction causality. The more a firm is exposed in SNS, the more is the stock price likely to increase, while stock price changes may not cause more SNS mentions.

• Journal of Digital Convergence
• /
• v.19 no.3
• /
• pp.161-166
• /
• 2021

The macroeconomic concept represents the movement of a country's economy, and it affects the overall economic activities of business, government, and households. In the macroeconomy, by looking at changes in national income, inflation, unemployment, currency, interest rates, and raw materials, it is possible to understand the effects of economic actors' actions and interactions on the prices of products and services. The US Federal Reserve System (FED) is leading the world economy by offering various stimulus measures to overcome the corona economic recession. Although the stock price continued to decline on March 20, 2020 due to the current economic recession caused by the corona, the US S&P 500 index began rebounding after March 23 and to 3,694.62 as of December 15 due to quantitative easing, a powerful stimulus for the FED. Therefore, the FED's economic stimulus measures based on macroeconomic indicators are more influencing, rather than judging the stock price forecast from the corporate financial statements. Therefore, this study was conducted to reduce losses in stock investment and establish sound investment by analyzing the FED's economic stimulus measures and its effect on stock prices.

• Journal of Digital Convergence
• /
• v.18 no.11
• /
• pp.259-266
• /
• 2020

Many developments have been steadily carried out by researchers with applying knowledge-based expert system or machine learning algorithms to the financial field. In particular, it is now common to perform knowledge based system trading in using stock prices. Recently, deep learning technologies have been applied to real fields of stock trading marketplace as GPU performance and large scaled data have been supported enough. Especially, LSTM has been tried to apply to stock price prediction because of its compatibility for time series data. In this paper, we implement stock price prediction using LSTM. In modeling of LSTM, we propose a fitness combination of model parameters and activation functions for best performance. Specifically, we propose suitable selection methods of initializers of weights and bias, regularizers to avoid over-fitting, activation functions and optimization methods. We also compare model performances according to the different selections of the above important modeling considering factors on the real-world stock price data of global major companies. Finally, our experimental work brings a fitness method of applying LSTM model to stock price prediction.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.47-56
• /
• 2020

The stock index is used not only as an economic indicator for a country, but also as an indicator for investment judgment, which is why research into predicting the stock index is ongoing. The task of predicting the stock price index involves technical, basic, and psychological factors, and it is also necessary to consider complex factors for prediction accuracy. Therefore, it is necessary to study the model for predicting the stock price index by selecting and reflecting technical and auxiliary factors that affect the fluctuation of the stock price according to the stock price. Most of the existing studies related to this are forecasting studies that use news information or macroeconomic indicators that create market fluctuations, or reflect only a few combinations of indicators. In this paper, this we propose to present an effective combination of the news information sentiment analysis and various macroeconomic indicators in order to predict the US Dow Jones Index. After Crawling more than 93,000 business news from the New York Times for two years, the sentiment results analyzed using the latest natural language processing techniques BERT and NLTK, along with five macroeconomic indicators, gold prices, oil prices, and five foreign exchange rates affecting the US economy Combination was applied to the prediction algorithm LSTM, which is known to be the most suitable for combining numeric and text information. As a result of experimenting with various combinations, the combination of DJI, NLTK, BERT, OIL, GOLD, and EURUSD in the DJI index prediction yielded the smallest MSE value.

• The Korean Journal of Financial Management
• /
• v.24 no.2
• /
• pp.41-79
• /
• 2007

This study examines the expiration-day effects of stock index futures and options in the Korean stock market. The so-called 'expiration-day effects', which are the abnormal stock price movements on derivatives expiration days, arise mainly from cash settlement. Index arbitragers have to bear the risk of their positions unless they liquidate their index stocks on the expiration day. If many arbitragers execute large buy or sell orders on the expiration day, abnormal trading volumes are likely to be observed. If a lot of arbitragers unwind positions in the same direction, temporary trading imbalances induce abnormal stock market volatility. By contrast, if some information arrives at market, the abnormal trading activity must be considered a normal process of price discovery. Stoll and Whaley(1987) investigated the aggregate price and volume effects of the S&P 500 index on the expiration day. In a related study, Stoll and Whaley(1990) found a similarity between the price behavior of stocks that are subject to program trading and of the stocks that are not. Thus far, there have been few studies about the expiration-day effects in the Korean stock market. While previous Korean studies use the KOSPI 200 index data, we analyze the price and trading volume behavior of individual stocks as well as the index. Analyzing individual stocks is important for two reasons. First, stock index is a market average. Consequently, it cannot reflect the behavior of many individual stocks. For example, if the expiration-day effects are mainly related to a specific group, it cannot be said that the expiration of derivatives itself destabilizes the stock market. Analyzing individual stocks enables us to investigate the scope of the expiration-day effects. Second, we can find the relationship between the firm characteristics and the expiration-day effects. For example, if the expiration-day effects exist in large stocks not belonging to the KOSPI 200 index, program trading may not be related to the expiration-day effects. The examination of individual stocks has led us to the cause of the expiration-day effects. Using the intraday data during the period May 3, 1996 through December 30, 2003, we first examine the price and volume effects of the KOSPI 200 and NON-KOSPI 200 index following the Stoll and Whaley(1987) methodology. We calculate the NON-KOSPI 200 index by using the returns and market capitalization of the KOSPI and KOSPI 200 index. In individual stocks, we divide KOSPI 200 stocks by size into three groups and match NON-KOSPI 200 stocks with KOSPI 200 stocks having the closest firm characteristics. We compare KOSPI 200 stocks with NON-KOSPI 200 stocks. To test whether the expiration-day effects are related to order imbalances or new information, we check price reversals on the next day. Finally, we perform a cross-sectional regression analysis to elaborate on the impact of the firm characteristics on price reversals. The main results seem to support the expiration-day effects, especially on stock index futures expiration days. The price behavior of stocks that are subject to program trading is shown to have price effects, abnormal return volatility, and large volumes during the last half hour of trading on the expiration day. Return reversals are also found in the KOSPI 200 index and stocks. However, there is no evidence of abnormal trading volume, or price reversals in the NON-KOSPI 200 index and stocks. The expiration-day effects are proportional to the size of stocks and the nearness to the settlement time. Since program trading is often said to be concentrated in high capitalization stocks, these results imply that the expiration-day effects seem to be associated with program trading and the settlement price determination procedure. In summary, the expiration-day effects in the Korean stock market do not exist in all stocks, but in large capitalization stocks belonging to the KOSPI 200 index. Additionally, the expiration-day effects in the Korean stock market are generally due, not to information, but to trading imbalances.

• The Journal of Society for e-Business Studies
• /
• v.25 no.4
• /
• pp.61-75
• /
• 2020

The scope of data for understanding or predicting stock prices has been continuously widened from traditional structured format data to unstructured data. This study investigates whether commentary data collected from SNS may affect future stock prices. From "Stock Discussion Room" in Naver, we collect 20 stocks' commentary data for six months, and test whether this data have prediction power with respect to one-hour ahead price direction and price range. Deep neural network such as LSTM and CNN methods are employed to model the predictive relationship. Among the 20 stocks, we find that future price direction can be predicted with higher than the accuracy of 50% in 13 stocks. Also, the future price range can be predicted with higher than the accuracy of 50% in 16 stocks. This study validate that the investors' sentiment reflected in SNS community such as Naver's "Stock Discussion Room" may affect the demand and supply of stocks, thus driving the stock prices.

• Journal of Information Technology Applications and Management
• /
• v.21 no.4
• /
• pp.97-125
• /
• 2014

This study investigates the relationship between stock index and its associated nearby futures markets based on the cost-of-carry model. The purpose of this study is to explore the existence of mispriced futures contracts, and to test whether traders can earn trading profits in real financial market using the information about the mispriced futures contracts. This study suggests the concordance correlation coefficient to investigate the existence of mispriced futures contracts. The concordance correlation coefficient gives a desirable result for trading profits that results from a comparative analysis among profits from trading at the time to indicate trading opportunities determined by the degree of the difference between the observed market price and the theoretical price of a futures contract. In addition, this study also explains that the concordance correlation coefficient developed from the mean square error (MSE) has a statistically theoretical meaning. In conclusion, this study shows that the concordance correlation coefficient is appropriate for analyzing the relationship between the observed stock index futures market price and the theoretical stock index futures price derived from the cost-of-carry model.

• The KIPS Transactions:PartB
• /
• v.15B no.6
• /
• pp.603-608
• /
• 2008

In this paper an approach to building fuzzy model to predict daily open, close, high, and low stock prices is presented. One of prior problems in building a stock prediction model is to select most effective indicators for the stock prediction. The problem is overcome by the selection of information used in the analysis of stick-chart as the input variables of our fuzzy model. The fuzzy rules have the premise and the consequent, in which they are composed of trapezoidal membership functions, and nonlinear equations, respectively. DE(Differential Evolution) searches optimal fuzzy rules through an evolutionary process. To evaluate the effectiveness of the proposed approach numerical example is considered. The fuzzy models to predict open, high, low, and close prices of KOSPI(KOrea composite Stock Price Index) on a daily basis are built, and their performances are demonstrated and compared with those of neural network.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.52 no.3
• /
• pp.220-231
• /
• 2016

Yield-per-recruit (YPR) analysis is used to provide management guidance for the efficient use of a fish cohort. However, the individual fish price per unit weight of small yellow croaker (Larimichthys polyactis) or hairtail (Trichiurus lepturus) increases dramatically by size in Korea. Therefore, age-based production value-per-recruit (PPR) analysis has recently been developed (Zhang et al., 2014). Since age determination requires a substantial amount of money and time and it is even impossible for some fish species, it is difficult to obtain age information to apply the age-based PPR model. Thus, we attempted to develop an alternative method, which uses length data rather than age information, called the length-based PPR analysis. The results revealed that length-based PPR analysis was much more conservative for stock management than the YPR analysis. Furthermore, the PPR analysis was more economically beneficial than the YPR analysis, which can prevent the fish stock from the economic overfishing. In conclusion, the length-based PPR analysis could be a proper approach for stock assessment in the case that the individual fish price per unit weight increases dramatically by size, and this analysis is useful to obtain vital management parameters under data-deficient situation when traditional stock assessment methods are not applicable.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.6 no.4
• /
• pp.297-305
• /
• 2010

Employment number by areas is composed of various factors for groups and time series. In this paper, we use the panel data for finding various variables and using this, we analyzed the factors that is major influence to employment number by areas. For analysis we looked at employment number by areas, the region for analysis consist of seven groups, that is, the metropolitan city(such as Busan, Daegu, Incheon, Gwangiu, Daejeon, Ulsan.) and Seoul. Analyzing period be formed over a 63 time points(2005.01.- 2010.03). We examined the data in relation to the employment number by occupational job, unemployment rate, monthly household income, preceding business composite index, consumer price index, composite stock price index. In looking at the factors which determine employment number by areas job, evidence was produced supporting the hypothesis that there is a significant negative relationship between unemployment rate and monthly household income the consumer price index. The consumer price index and composite stock price index are significant positive relationship, preceding business composite index is positive relationship, it are not significant variables in terms of employment number by areas job.