• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.1
• /
• pp.32-41
• /
• 2023

Recently, many studies are being conducted to extract emotion from text and verify its information power in the field of finance, along with the recent development of big data analysis technology. A number of prior studies use pre-defined sentiment dictionaries or machine learning methods to extract sentiment from the financial documents. However, both methods have the disadvantage of being labor-intensive and subjective because it requires a manual sentiment learning process. In this study, we developed a financial sentiment dictionary that automatically extracts sentiment from the body text of analyst reports by using modified Bayes rule and verified the performance of the model through a binary classification model which predicts actual stock price movements. As a result of the prediction, it was found that the proposed financial dictionary from this research has about 4% better predictive power for actual stock price movements than the representative Loughran and McDonald's (2011) financial dictionary. The sentiment extraction method proposed in this study enables efficient and objective judgment because it automatically learns the sentiment of words using both the change in target price and the cumulative abnormal returns. In addition, the dictionary can be easily updated by re-calculating conditional probabilities. The results of this study are expected to be readily expandable and applicable not only to analyst reports, but also to financial field texts such as performance reports, IR reports, press articles, and social media.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.3
• /
• pp.539-549
• /
• 2021

This study aims to examine the relationship between corporate social responsibility (CSR) expenditures and both financial and non-financial performance of Jordanian commercial banks during the period 2008-2018. To measure the variables of interest, secondary data published on Amman Stock Exchange (ASE) website were processed to become preliminary data suitable for the nature of the study. The study sample amounted to 13 commercial banks, which represent all Jordanian commercial banks listed on ASE.. The study found that there is a positive, statistically significant relationship between CSR expenditures and financial performance, as the study showed that the return on equity (ROE) has a positive and significant relationship with CSR expenditure, while the return on assets (ROA) and Tobin's Q model have a statistically significant negative relationship with CSR expenditure, while the market stock price (MSP) had a positive, but not statistically significant. The study also found that there is a positive, statistically significant relationship between CSR expenditures and non-financial performance, which was represented by total deposits and total training expenditures in Jordanian commercial banks. Accordingly, the study recommends encouraging banks to prepare sustainability reports and CSR reports, which are considered comprehensive, and not only with disclosures within the annual reports.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.3
• /
• pp.123-130
• /
• 2022

Pair trading is a statistical arbitrage investment strategy. Traditionally, cointegration has been utilized in the pair exploring step to discover a pair with a similar price movement. Recently, the clustering analysis has attracted many researchers' attention, replacing the cointegration method. This study tests a clustering-driven pair trading investment strategy in the Korean stock market. If a pair detected through clustering has a large spread during the spread exploring period, the pair is included in the portfolio for backtesting. The profitability of the clustering-driven pair trading strategies is investigated based on various profitability measures such as the distribution of returns, cumulative returns, profitability by period, and sensitivity analysis on different parameters. The backtesting results show that the pair trading investment strategy is valid in the Korean stock market. More interestingly, the clustering-driven portfolio investments show higher performance compared to benchmarks. Note that the hierarchical clustering shows the best portfolio performance.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.3
• /
• pp.1249-1256
• /
• 2021

This study investigates the company value determinant by observing the effect of financial performance and Corporate Social Responsibility (CSR) and its role in moderating performance achievement. The macro-economy variables such as inflation and interest rate are also used as the controlling variable. This research employs the sample of manufacturing companies of the food and beverage sub-sector listed on the Indonesia Stock Exchange. This study used panel data from 2013 to 2017, with the moderating regression analysis. The result shows that the profitability of the current or previous period affects the company's value. CSR and company size affect the company value at the next period shows that stock price, which reflects the investor's perception today, will be affected by the CSR, Size, and Return On Asset of the previous year. CSR also shows that it can be the substitute for profitability since a company that performs CSR is the one that has a good performance. The regression moderating model and the profitability of the previous period have a higher explanatory power than the higher R square value in explaining company value.

• The Korean Journal of Applied Statistics
• /
• v.23 no.4
• /
• pp.651-668
• /
• 2010

Various estimators of two risk measures of a specific financial portfolio, Value-at-Risk and Expected Shortfall, are compared for each case of 1-day and 10-day horizons. We use the Korea Composite Stock Price Index data of 20-year period including the year 2008 of the global financial crisis. Indexes of five foreign stock markets are also used for the empirical comparison study. The estimator considering both the heavy tail of loss distribution and the conditional heteroscedasticity of time series is of main concern, while other standard and new estimators are considered too. We investigate which estimator is best for the Korean stock market and which one shows the best overall performance.

• Journal of Fashion Business
• /
• v.12 no.1
• /
• pp.129-146
• /
• 2008

The purpose of this study is to identify components of CEO image and to examine predictors to affect company's market value. To explore the social construction of the CEO Image depicted in the popular business newspaper, the Wall Street Journal and daily newspaper of Korea, was analyzed. Then, the reconstructed image of the CEO was compared with the firm's stock price change to see their relationship, if any. This paper focused on the case of Carly Fiorina as previous chief of Hewlett-Packard, who was the Fortune's ranking of the 50 most powerful women in business is presented. The period for the analysis was five years and eight months from her inauguration(July, 1999) to the release(February, 2005). The results, four predictors such as nature, management ability, leadership style, appearance character had statistically significant relationship with both company's market value and the image of CEO. In addition to revealed that media coverage of Carly Filoina was commensurate with the financial performance, particularly stock price change of the Hewlett-Packard. In general, the best image of the CEO is highly transcends to the image of the company as well. Therefore it is need to manage effectively components of CEO image to enhance brand image and its brand value, which are further expected to enhance company's market value.

• Communications for Statistical Applications and Methods
• /
• v.31 no.2
• /
• pp.213-234
• /
• 2024

In recent decades, increasing research attention has been directed toward predicting the price of stocks in financial markets using deep learning methods. For instance, recurrent neural network (RNN) is known to be competitive for datasets with time-series data. Long short term memory (LSTM) further improves RNN by providing an alternative approach to the gradient loss problem. LSTM has its own advantage in predictive accuracy by retaining memory for a longer time. In this paper, we combine both supervised and unsupervised dimension reduction methods with LSTM to enhance the forecasting performance and refer to this as a dimension reduction based LSTM (DR-LSTM) approach. For a supervised dimension reduction method, we use methods such as sliced inverse regression (SIR), sparse SIR, and kernel SIR. Furthermore, principal component analysis (PCA), sparse PCA, and kernel PCA are used as unsupervised dimension reduction methods. Using datasets of real stock market index (S&P 500, STOXX Europe 600, and KOSPI), we present a comparative study on predictive accuracy between six DR-LSTM methods and time series modeling.

• Management & Information Systems Review
• /
• v.30 no.4
• /
• pp.147-173
• /
• 2011

It is generally accepted that there are momentum effects in the short term and reversal effects in the long term, which makes abnormal excess returns in the major stock markets in the world. In Korea stock market, however, the previous studies demonstrate that contrarian strategies based on reversal effects are more effective than momentum strategies following momentum effects in the short term as well as in the long term. This paper examines wether contrarian strategies are still effective In Korea stock market from 1980 to 2009, and the short term reversals may be changed after the foreign exchange crisis in 1997-1998. Moreover, this paper investigates how contrarian profits are shown considering the state of market. In my research, unlike previous studies, I find that both of contrarian strategies using price change and price level cannot gain excess risk adjusted returns in Korea stock market from 1980 to 2009, but this result is due to the fact that reversal effects existed before the foreign exchange crisis but momentum effects does after the foreign exchange crisis in 1997-1998. Specially, after the foreign exchange crisis, it is confirmed momentum strategies using 52 week high price, that is, price level are more effective than momentum strategies using price change. And following the strategies using 52 week high price after the foreign exchange crisis, the momentum is not only observed in the up market but also in the down market, which is different with the results of the studies regarding to American market, where the momentum is just found in the up market.

• Journal of Distribution Science
• /
• v.13 no.9
• /
• pp.37-45
• /
• 2015

Purpose - This paper's aim is to investigate whether or not gross profitability explains the cross-sectional variation of the stock returns in the Korean stock market. Gross profitability is an alternative profitability measure proposed by Novy-Marx in 2013 to predict cross-sectional variation of stock returns in the US. He shows that the gross profitability adds explanatory power to the Fama-French 3 factor model. Interestingly, gross profitability is negatively correlated with the book-to-market ratio. By confirming the gross profitability premium in the Korean stock market, we may provide some implications regarding the well-known value premium. In addition, our empirical results may provide opportunities for the fund distribution industry to promote brand new styles of funds. Research design, data, and methodology - For our empirical analysis, we collect monthly market prices of all the companies listed on the Korea Composite Stock Price Index (KOSPI) of the Korea Exchanges (KRX). Our sample period covers July1994 to December2014. The data from the company financial statementsare provided by the financial information company WISEfn. First, using Fama-Macbeth cross-sectional regression, we investigate the relation between gross profitability and stock return performance. For robustness in analyzing the performance of the gross profitability strategy, we consider value weighted portfolio returns as well as equally weighted portfolio returns. Next, using Fama-French 3 factor models, we examine whether or not the gross profitability strategy generates excess returns when firmsize and the book-to-market ratio are controlled. Finally, we analyze the effect of firm size and the book-to-market ratio on the gross profitability strategy. Results - First, through the Fama-MacBeth cross-sectional regression, we show that gross profitability has almost the same explanatory power as the book-to-market ratio in explaining the cross-sectional variation of the Korean stock market. Second, we find evidence that gross profitability is a statistically significant variable for explaining cross-sectional stock returns when the size and the value effect are controlled. Third, we show that gross profitability, which is positively correlated with stock returns and firm size, is negatively correlated with the book-to-market ratio. From the perspective of portfolio management, our results imply that since the gross profitability strategy is a distinctive growth strategy, value strategies can be improved by hedging with the gross profitability strategy. Conclusions - Our empirical results confirm the existence of a gross profitability premium in the Korean stock market. From the perspective of the fund distribution industry, the gross profitability portfolio is worthy of attention. Since the value strategy portfolio returns are negatively correlated with the gross profitability strategy portfolio returns, by mixing both portfolios, investors could be better off without additional risk. However, the profitable firms are dissimilar from the value firms (high book-to-market ratio firms); therefore, an alternative factor model including gross profitability may help us understand the economic implications of the well-known anomalies such as value premium, momentum, and low volatility. We reserve these topics for future research.

• Journal of Convergence for Information Technology
• /
• v.11 no.9
• /
• pp.84-93
• /
• 2021

The purpose of this study is to analyze whether the spread of COVID-19 infectious diseases acts as a fear to investors and affects the direction and volatility of stock returns. The investor fear index was proposed using the domestic confirmed patient information of COVID-19, and the influence on stock prices was empirically analyzed. The direction and volatility models of stock prices used the Granger causality and GARCH models, respectively. The results of empirical analysis using the KOSPI index from February 20, 2020 to June 30, 2021 are as follows: First, the COVID-19 fear index showed causality to future stock prices. Second, the COVID-19 fear index has a negative effect on the volatility of KOSPI index returns. In future studies, it is necessary to document the cause by using individual business performance and stock price instead of the stock index.