Stock Price Variations Research Articles

Explainable Machine Learning Exploiting News and Domain-Specific Lexicon for Stock Market Forecasting

In this manuscript, we propose a Machine Learning approach to tackle a binary classification problem whose goal is to predict the magnitude (high or low) of future stock price variations for individual companies of the S&P 500 index. Sets of lexicons are generated from globally published articles with the goal of identifying the most impactful words on the market in a specific time interval and within a certain business sector. A feature engineering process is then performed out of the generated lexicons, and the obtained features are fed to a Decision Tree classifier. The predicted label (high or low) represents the underlying company’s stock price variation on the next day, being either higher or lower than a certain threshold. The performance evaluation we have carried out through a walk-forward strategy, and against a set of solid baselines, shows that our approach clearly outperforms the competitors. Moreover, the devised Artificial Intelligence (AI) approach is explainable, in the sense that we analyze the white-box behind the classifier and provide a set of explanations on the obtained results.

The Cross-Sectional Variation of Stock Prices

In this paper, I decompose prices over a set of 21 variables across seven categories. I test a firm-specific version of the Campbell and Shiller (1988b) model against these categories and show expected returns and change in cash-flows explain 5% or less of modeled price variation while an often-ignored time-series constant explains over 70%. Approximately 50% to 70% of modeled cross-sectional variation is explained by efficient market variables, with the remainder explained by market frictions. I find institutional ownership and share repurchases show a significant ability in the cross-section to explain next-period prices, while transaction costs and some traditional market risk-factors fail to translate well to a price setting.

A study on the impact of macroeconomic indicators on the stock price by relaxing the assumptions of stationarity in time series data in a general linear model

A model has been evolved by keeping the stock index as dependable variable and gross domestic product, consumption and consumer price index as independent variables. The assumptions to arrive the model are tested. The behaviour of the model is studied by including and relaxing the important assumption of stationarity in the economic data. It was finally found that the model becomes significant if we violate the stationary assumption for both dependent variable stock price and independent variable consumer price index, consumption and gross domestic product. This is evidenced by demonstrating the model by using the data related to the macroeconomic variables of developed countries (USA, UK), emerging countries (India, Brazil), and frontier countries (Latvia, Estonia).

The Influence of Indonesian Interest Rates, Inflation, Debt to Asset Ratio and Return on Asset against the Property and Real Estate Sector Stock Prices on the Indonesia Stock Exchange in 2014-2018

The aim of this study is to see the effect of Indonesia's interest rates, inflation, DAR and ROA on stock prices. This type of research is quantitative research, uses a deductive approach and is descriptive in nature. The population of the property and real estate sector has 52 companies, within 5 years, so the data totaled 155. The results of this study show that simultaneously SBI, inflation, DAR and ROA have a significant effect on stock prices. Partially, only ROA has a positive / significant effect on the stock price. Other variables, namely SBI, inflation and DAR do not affect the stock price. The amount of stock price variation that can be explained by the independent variable used is 18.3%, the remaining 81.7% is influenced by other variables.

The Effect of Current Ratio (CR), Firm Size (FS), Return on Equity (ROE), and Earning Per Share (EPS) on the Stock Prices of Manufacturing Companies listed in Indonesia Stock Exchange in the 2014-2018 Period

This study aims to determine the effect of Current Ratio on stock prices, the effect of Firm Size on stock prices, the effect of Return On Equity on Stock Prices, the effect of Earning Per Share on Stock Prices, and the influence of Current Ratio, Firm Size, Return On Equity, and Earning Per Share simultaneously on stock prices in the 5 year period, 2014-2018. This study uses a quantitative approach with a descriptive statistical analysis type. The population in this study amounted to 150 companies. This study uses financial statement data with time series for the last 5 years published from www.idx.co.id. In this study, the sample selection used purposive sampling technique. The sample of this study contained 49 companies in the last 5 years with a total sample quantity of 245 manufacturing companies. The results of this study indicate that partially Current Ratio and Return On Equity have no and insignificant effect on stock prices of manufacturing companies. Partially Firm Size and Earning Per Share have a positive and significant effect on stock prices of manufacturing companies. Meanwhile, the independent variable Current Ratio, Firm Size, Return On Equity, and Earning Per Share simultaneously have a significant effect on the variable stock price of manufacturing companies.

Fear of the coronavirus and the stock markets

Since the outbreak of the COVID-19 pandemic, stock markets around the world have experienced unprecedented declines amid high uncertainty. In this paper, we use Google search volume activity as a gauge of panic and fear. The chosen search terms are specific to the coronavirus crisis and correspond to phrases related to nonpharmaceutical intervention policies to fight physical contagion. We show that during this period, fear of the coronavirus – manifested as excess search volume – represents a timely and valuable data source for forecasting stock price variation around the world.

Understanding the impact of investor sentiment on the price formation process: A review of the conduct of American stock markets

Applying both survey-based and market-based measures, we examined how investor sentiment affects the way with which prices reflect information and whether or not it manifests itself in the trading behavior of investors in the U.S. stock market. We also compared the effect of investor sentiment on several U.S. stock market indices. Our research improves our understanding of the price formation process when supporting the notion that sentiment-induced buying and selling is an important determinant of stock price variation. Our research design is novel as it suggests that sentiment-driven traders may not be as irrational as is presupposed in classical asset pricing and it provides more comprehensive statistical evidence on the impact of differing types of sentiment on the price formation process, especially in the various U.S. stock market indices. We consider that sentiment is linked to shifts in risk tolerance and this triggers contrarian-type behavior. Given this, using an EGARCH parameter estimation, we have shown the following concerning the behavior of sentiment driven investors; (i) They are more motivated to trade on survey-based indicators than market based indicators, (ii) They respond asymmetrically to shifts in sentiment and trade more aggressively during periods of declining sentiment, (iii) They respond asymmetrically to sentiment measures when incorporating the possible impact of market conditions and business cycles on trading behavior.

Pengaruh Earning Per Share (EPS). Return On Equity (ROE), dan Price Book Value (PBV) Terhadap Harga Saham pada perusahaan Perbankan Yang Terdaftar di Bursa Efek Indonesia Tahun 2015-2017

ABSTRACT
 
 This study is examined in order to explore how much influence Earning Per Share (EPS), Return On Equity (ROE), and Price Book Value (PBV) simultaneously and partially on stock prices on Banking Companies listed on the Indonesia Stock Exchange in 2015-2017 . This type of research used quantitative descriptive by nature sourced in the explanation stage where the research is more inclined to temperament cause or effect. The analytical method used is multiple linear regression method. The research approach used is a quantitative approach. The population quantity of 43 agencies over a total sample of 31 companies so that the total number of samples to be studied was 93 observations (31 x 3). The analysis value of the coefficient of determination is obtained from Adjusted R Square 0.942 with the intention that stock price variables can be explained in variations of EPS, ROE, and PBV variables of 94.2% while the remaining 5.8% is explained by other independent variables. The conclusions in the results of observations indicate partially EPS and PBV have a positive and significant effect on stock prices, partially ROE has a negative and significant effect on stock prices. Simultaneously, EPS, ROE and PBV have a significant effect on stock prices on Banking Companies listed on the Indonesia Stock Exchange in 2015-2017.
 Keywords: Earning Per Share (EPS), Return On Equity (ROE), Price Book Value (PBV), Stock Prices

The Existence of Profit Growth in Companies in The Jakarta Islamic Index (JII) (2016-2018)

This study aims to determine the partial profit growth of company stock prices (companies registered in the Jakarta Islamic Index - JII). The article is the result of stock analysis and annual financial statements of companies that enter the 2016-2018 Jakarta Islamic Index, by using a quantitative research. The sample used was obtained from 90 Jakarta Islamic Index companies using the simple regression analysis method. From the results of the hypothesis test, the variable earnings growth showed no significant effect on stock prices at companies listed on the Jakarta Islamic Index (JII). From the results of partial testing between earnings growth variables and stock price variables, the T count is smaller than the T table with a value of 0.436 <1.987 and a sig value of 0.664 is greater than 0.05. Therefore, it can be said that the profit growth variable does not have a significant effect on stock prices. According to the researchers, this occurs because there are other influences, one of which is the fluctuation of the rupiah exchange rate against foreign currencies.

Exchange Rates and Asset Prices in a Global Demand System

Using international holdings data, we estimate a demand system for financial assets across 36 countries. The demand system provides a unified framework for decomposing variation in exchange rates, long-term yields, and stock prices; interpreting major economic events such as the European sovereign debt crisis; and estimating the convenience yield on US assets. Macro variables and policy variables (i.e., short-term rates, debt quantities, and foreign exchange reserves) account for 55 percent of the variation in exchange rates, 57 percent of long-term yields, and 69 percent of stock prices. The average convenience yield is 2.15 percent on US long-term debt and 1.70 percent on US equity.

The Efficiency of Stock Exchange Self-Regulation: Evidence from Stock Market Liquidity and Transparency

This study examines whether and how stock exchange self-regulation affects stock market liquidity and corporate transparency. Using a large sample of firms from 46 stock exchanges from 2001 to 2015, we find significant and robust evidence that firms listed in self-regulated stock exchange are associated with fewer zero-return days, lower daily stock price variation, higher stock trading volume, smaller analyst forecast errors, lower discretionary accruals and less earnings management. These findings are more pronounced when the stock exchange has a strong self-regulation model rather than a limited self-regulation model. Also, our results are robust in different-in-difference tests based on the Australian Securities Exchange’s change from strong self-regulation model to a government regulation model. Further, when a firm from a country with a government-regulated stock exchange is cross-listed in a self-regulated stock exchange, the firm has higher liquidity and transparency than the matched firms. In addition, we find that self-regulated exchanges set more detailed insider trading and disclosure rules and are more transparent with their rules and rule enforcement. Overall, our study suggests that stock exchange self-regulation improves the efficiency of stock market regulation.

Value Relevance of R&D expenses in capital market: A study of brazilian IT sector companies

Although R&D expenses be relevant to any company, the IT sector stands out in this way, since these companies make constant investments in these intangibles in order to develop solutions and systems for their clients, so, this study aimed to verify the relevance of R&D expenses for companies in the IT sector listed in B3 between 2010 and 2018. Regressions were performed by least absolute deviations considering the stock price as response variable and R&D expenses as explanatory variable. In addition, complementary analyzes were made using logistic regressions. It was always considered a confidence level of 95%. Our results show that R&D expenses explain the variation in stock prices, as expected. The positive sign indicates that investments in these intangibles increase the market value of IT companies, however, there are limits to these benefits. An interesting comparative is that, for the electric sector, target of the study of Alves, Silva, Macedo, and Marques (2011), R&D expenses did not indicate predictive power against stock prices. This confirms the relevance of this measure to the IT sector given its importance to the activities of these companies. Although there is a common sense of the relevance of R&D expenses for the IT sector, there was no literature that would provide such evidence in an empirical way. This research fills this gap and denotes greater relevance of the accounting information regarding R&D expenses for investors of B3 IT companies.

STOCK SPLIT AND STOCK MARKET REACTION: THE EVIDENCE OF INDONESIAN PUBLIC COMPANY

Purpose of study: Go Public Company can raise funds for its operations through the sale of shares to investors. But if the stock price is too high, it can make the investors are not interested in buying stock. Stock market value can be reduced by the stock-split. This study aims to examine the effect of the stock split on abnormal return, stock price; trading volume and security return variability in the go public company on the Indonesia Stock Exchange.
 Methodology: Researchers use data from 41 companies that were taken by purposive sampling from 2013 to 2016. The hypotheses in this study were tested using a Paired sample t-test. 
 Result: The researcher found that the stock split event causes the difference between the stock price, trading volume and security return variability between before and after the stock split. But the results found that the stock split did not cause any differences between the abnormal return before and after the stock split. 
 Application: The results of this study can provide an overview of the relationship between stock split events with stock prices and stock trading volumes.
 Novelty/Originality of this study: This research using different methods compare with previous, namely multiple discriminant analysis. The multiple discriminant analysis methods are part of the discriminant analysis, which is a multivariate technique that includes the dependence method, namely the presence of variables.

EFFECT OF DIVIDEND POLICY (DPR), LIQUIDITY (CR) AND PROFITABILITY ON SHARE PRICE AT TRADE, SERVICE AND INVESTMENT SECTORS AT INDONESIA STOCK EXCHANGE IN PERIOD OF 2014-2018

Stock price is one indicator that shows investor interest in owning a company's stock. An investor always expects a stable stock price and has a pattern of movement that tends to rise from time to time, but in fact the stock price tends to fluctuate. Fluctuating stock prices become a risk for investors. Therefore, an investor must understand the issues that must be considered in determining investment decisions. The research variables are Dividend Payout Ratio (DPR), Liquidity (CR), and Profitability (NPM) and Share Prices. The research populations were Trade, Service and Investment Sector Companies listed on the Indonesia Stock Exchange in 2014-2018. The research samples were drawn by using a purposive sampling technique. The research samples were 17 company financial statements that met the criteria as a sample of the company. The datacollection was performed by documentation techniques and the research data were analyzed by using multiple linear analysis. Hypothesis testing shows that the Individual Payout Ratio (DPR) and Liquidity (CR) do not have a significant effect on stock prices. Profitability (NPM) has a significant effect on Stock Prices. The value of Adjusted R Square was 0.275 indicating that variations in the DPR, CR, and NPM can explain variations in the variable Stock Price up to 27.5% while the remaining 72.7% can be explained by other factors outside the variables that have not been examined.

O SETOR DE CONSUMO CÍCLICO SEGUNDO AÇÕES NEGOCIADAS NA B3: O SEGMENTO DE ELETRODOMÉSTICOS, PRODUTOS DIVERSOS,TECIDOS,VESTUÁRIOE CALÇADOS

By analyzing a portion of the Brazilian financial market, according to the daily value of its shares traded on the largest stock exchange in the country, the B3 stock exchange, offering possibilities to understand more clearly the behavior of the stock market according to growth, decrease, and even the stability of the values traded on the stock market in question. Thus, this research presents an analysis using Pearson's correlation coefficient and offers elements to affirm or refute the idea of proximity between companies in the same sector or not. By proposing the application of this methodology in the segment of home appliances, miscellaneous products, and fabrics, clothing and footwear, it is possible to point out how closely these companies are interconnected in terms of stock price variability. Thus, the objective was to observe not only the behavior of the stock price of the companies of the sector in question during a given period, as well as the intensity of variation between the same measures by the correlation coefficient, but also to evaluate the use of this coefficient as a proposal. methodological approach to assess the proximity between the companies. As a result, it was concluded that the largest proximityis between companies of the same segment.

ANALISIS PENGARUH RASIO PROFITABILITAS TERHADAP HARGA SAHAM PERUSAHAAN YANG TERCANTUM DALAM INDEKS LQ45

This study aimed to examine the effect of profitability ratio on stock price of companies listed in LQ45 index in Indonesia Stock Exchange (BEI). Profitability ratios here in include Net Profit Margin (NPM), Return on Assets (ROA), Return on Equity (ROE), and Eearning Per Share (EPS). This study was conducted to assess the financial performance of the company to generate earnings from an investment.This study uses secondary data. The population in this study is the companies included in the LQ45 index from 2010-2013 amounting to 78. The total sample is 16 companies belonging to and representing several sectors including the financial sector companies, automotive, property, plantation, infrastructure, mining, industrial cement, as well as the consumer goods industry are consistently incorporated in the four observation period 2010-2013 in LQ45 index that has been determined through purposive sampling method. Method of hypothesis testing using Classical Assumption Test, Regression, t test, F test, and the coefficient of determination by alpha (α) of 5%.Regression analysis showed that in partial Net Profit Margin (NPM), Return on Assets (ROA) and Return On Equity (ROE) significantly influence the stock price while the variable Eearning Per Share (EPS) has no significant effect on stock price. Simultaneously all variables Net Profit Margin (NPM), Return on Assets (ROA), Return on Equity (ROE), and Eearning Per Share (EPS) have a significant effect on stock price. The value of coefficient of determination (R2) of 0.899, which means that the independent variable Net Profit Margin (NPM), Return on Assets (ROA), Return on Equity (ROE), and Eearning Per Share (EPS) is able to explain the variation of the dependent variable stock price by 89,9%, while the remaining 10.1 % is explained by other variables outside of the variables used in the study.

Dividend Policy and Share Price Volatility Among Insurance Companies Listed at Nairobi Securities Exchange

The major objective of any firm is to maximize the shareholders wealth. This is evidence through dividend yield and payout ratio and this encapsulate into the dividend policy of a company. The research purpose aimed at examining the influence that dividend policy has on the volatility of share prices among the listed insurance corporations in Kenya. Research design, approach and method: Data was collected from listed insurance corporations over a 10-year period with a total of 49 data points. The Pearson correlation and ordinary regression analysis were employed. The results reveal the existence of a positive link among the study variables. The correlations were found to be substantial at ninety-five percent confidence level. It is worth noting that the model summary shows forty-three-point one percent of changes in the volatility of stock price are explicated by dividend yield and payout ratio. ANOVA statistics which examines whether the analytical model as set out in the study explains variations in the dependent variable concluded that the model is analytically substantial. The outcome revealed a statistically significant positive link between stock price variations and the ratio of dividend payout. Research also established a statistically substantial negative interrelation between volatility of stock prices and dividend return. Results therefore recommend that companies should have dividend policies which are mapped to shareholders wealth maximization objective. The study suggests further studies be undertaken to determine whether there exists an analytically substantial difference between the dividend policies of various sectors in the economy.

ANALISIS HARGA SAHAM DAN EARNING PER SHARE (EPS) TERHADAP BID ASK SPREAD PADA SAHAM SYARIAH PERUSAHAAN PROPERTY DAN REAL ESTATE YANG TERDAFTAR DI ISSI PERIODE 2014 - 2017

This study aims to analyze the effect of stock prices and earnings per share on bid ask spread on sharia shares of property and real estate companies listed in ISSI for the period 2014-2017 both partially and horizontally. This study uses a population of property and real estate companies registered at the ISSI. This study uses a sample of 26 samples of property and real estate companies registered with the ISSI where the sampling technique uses purposive sampling technique. The observation period in this study starts from the period 2014 - 2017. Based on the results of the study, the best estimation model used is the common effect model (CEM), this indicates that the variable share price and earnings per share (EPS) have a significant and simultaneous influence towards bid ask spread of sharia shares of property and real estate companies registered in ISSI for the period 2014 - 2017. The results of the research partially indicate that the stock price variable has a significant negative effect on the bid ask spread of sharia stock property and real estate companies registered in the ISSI period 2014-2017, while the earnings per share (EPS) variable has no influence and is significant towards bid ask spread of sharia shares of property and real estate companies registered in ISSI for the period 2014 - 2017.Keywords: Stock Price, Earning Per Share (EPS), property and real estate companies, ISSI

PENGARUH DIVIDEND YIELD, EARNING VOLATILITY DAN LEVERAGE TERHADAP STOCK PRICE VOLATILITY PADA SEKTOR PERTAMBANGAN YANG TERDAFTAR DI BURSA EFEK INDONESIA PERIODE 2015 - 2018

Penelitian ini bertujuan untuk mengetahui factor dominan yag mempengaruhi volatilitas harga saham pada sector pertambangan yang terdaftar di Bursa efek Indonesia. Selama periode 2015 hingga 2018. Jenis penelitian ini adalah studi kausalitas dengan menggunakan data kuantitatif. Data yang digunakan dalam penelitian ini adalah laporan keuangan yang telah diaudit dan dipublikasikan melalui situs web perusahaan. Teknik pengambilan sampel yang digunakan adalah judgemental sampling. Variable independen dalam penelitian ini adalah dividend yield (DY), earning volatility (EV) dan Leverage (LEV) sedangkan stock price volatility (SPV) adalah variable dependen. Jumlah sampel setiap tahun sebanyak 13 perusahaan. Hasil penelitian ini dividend yield (DY), earning volatility (EV) dan Leverage (LEV) secara simultan berpengaruh terhadap stock price volatility (SPV) pada level signifikasi 5%. Dividend yield (DY) berpengaruh signifikan terhadap stock price volatility (SPV), sedangkan Earning volatility (EV) dan Leverage (LEV) tidak berpengaruh signifikan terhadap stock price volatility (SPV) pada confidence level 95%. Adjusted R square menunjukkan 0,065(6,5%) artinya hanya 6,5% dari variable dependen yaitu stock price volatility (SPV) dapat dijelaskan oleh varibel independe dalam model regresi penelitian ini, sedangkan 93,5% dijelaskan oleh variable lain yang tidak termasuk dalam penelitian ini.

Does Weather Contribute to Stock Price Variation? A Cointegration Analysis

The objectives of this study are to investigate whether there is a long term relationship between stock returns and weather factors and to examine whether the weather factors have an outperforming effect over macroeconomic variables when explaining the stock price variation. This study is motivated by the emergence of behavioral branch of asset pricing which pays attention towards the irrationality of investors who are influenced by the mood and the sentiment. This study investigates this phenomenon taking evidence from an emerging market, Colombo Stock Exchange. The study uses Johansen Cointegration Test with VAR - Vector Error Correction Estimates and Variance Decomposition. The results confirm that weather factors are related with the stock prices in the long run and reveal that temperature has an outperforming contribution to the stock price variation whiles supporting the Temperature Anomaly which is widely tested in this background.