Showing papers on "Stock exchange published in 2019"

Stock Market Analysis: A Review and Taxonomy of Prediction Techniques

Abstract: Stock market prediction has always caught the attention of many analysts and researchers. Popular theories suggest that stock markets are essentially a random walk and it is a fool’s game to try and predict them. Predicting stock prices is a challenging problem in itself because of the number of variables which are involved. In the short term, the market behaves like a voting machine but in the longer term, it acts like a weighing machine and hence there is scope for predicting the market movements for a longer timeframe. Application of machine learning techniques and other algorithms for stock price analysis and forecasting is an area that shows great promise. In this paper, we first provide a concise review of stock markets and taxonomy of stock market prediction methods. We then focus on some of the research achievements in stock analysis and prediction. We discuss technical, fundamental, short- and long-term approaches used for stock analysis. Finally, we present some challenges and research opportunities in this field.

Decision-making for financial trading: A fusion approach of machine learning and portfolio selection

Abstract: Forecasting stock returns is an exacting prospect in the context of financial time series. This study proposes a unique decision-making model for day trading investments on the stock market. In this regard, the model was developed using a fusion approach of a classifier based on machine learning, with the support vector machine (SVM) method, and the mean-variance (MV) method for portfolio selection. The model's experimental evaluation was based on assets from the Sao Paulo Stock Exchange Index (Ibovespa). Monthly rolling windows were used to choose the best-performing parameter sets (the in-sample phase) and testing (the out-of-sample phase). The monthly windows were composed of daily rolling windows, with new training of the classifying algorithm and portfolio optimization. A total of 81 parameter arrangements were formulated. To compare the proposed model's performance, two other models were suggested: (i) SVM + 1/N, which maintained the process of classifying the trends of the assets that reached a certain target of gain and which invested equally in all assets that had positive signals in their classifications, and (ii) Random + MV, which also maintained the selection of those assets with a tendency to reach a certain target of gain, but where the selection was randomly defined. Then, the portfolio's composition was determined using the MV method. Together, the alternative models registered 36 parameter variations. In addition to these two models, the results were also compared with the Ibovespa's performance. The experiments were formulated using historical data for 3716 trading days for the out-of-sample analysis. Simulations were conducted without including transaction costs and also with the inclusion of a proportion of such costs. We specifically analyzed the effect of brokerage costs on buying and selling stocks on the Brazilian market. This study also evaluated the classifier's performance, portfolios’ cardinality, and models’ returns and risks. The proposed main model showed significant results, although demand for trading value can be a limiting factor for its implementation. Nonetheless, this study extends the theoretical application of machine learning and offers a potentially practical approach to anticipating stock prices.

EMD2FNN: A strategy combining empirical mode decomposition and factorization machine based neural network for stock market trend prediction

Abstract: Stock market forecasting is a vital component of financial systems. However, the stock prices are highly noisy and non-stationary due to the fact that stock markets are affected by a variety of factors. Predicting stock market trend is usually subject to big challenges. The goal of this paper is to introduce a new hybrid, end-to-end approach containing two stages, the Empirical Mode Decomposition and Factorization Machine based Neural Network (EMD2FNN), to predict the stock market trend. To illustrate the method, we apply EMD2FNN to predict the daily closing prices from the Shanghai Stock Exchange Composite (SSEC) index, the National Association of Securities Dealers Automated Quotations (NASDAQ) index and the Standard & Poor’s 500 Composite Stock Price Index (S&P 500), which respectively exhibit oscillatory, upward and downward patterns. The results are compared with predictions obtained by other methods, including the neural network (NN) model, the factorization machine based neural network (FNN) model, the empirical mode decomposition based neural network (EMD2NN) model and the wavelet de-noising-based back propagation (WDBP) neural network model. Under the same conditions, the experiments indicate that the proposed methods perform better than the other ones according to the metrics of Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Furthermore, we compute the profitability with a simple long-short trading strategy to examine the trading performance of our models in the metrics of Average Annual Return (AAR), Maximum Drawdown (MD), Sharpe Ratio (SR) and AAR/MD. The performances in two different scenarios, when taking or not taking the transaction cost into consideration, are found economically significant.

Towards a more ethical market: the impact of ESG rating on corporate financial performance

Abstract: This paper fits in a research field dealing with the impact of Corporate Ethics Assessment on Financial Performance. The authors argue how environmental, social and governance (ESG) paradigm, meant to measure corporate social performance by rating issuance, can impact on abnormal returns of Italian firms listed on Financial Times Stock Exchange Milano Indice di Borsa (FTSE MIB) Index, developing a panel data analysis which runs from 2007 to 2015.,This study aims at exploring whether socially responsible investors outperform an excess market return on Italian Stock Exchange because of their investment behavior, testing statistically the relationship between the yearly ESG assessment issued by Standard Ethics Agency on FTSE MIB’s companies and their abnormal returns. To verify the impact of an ESG Rating on a company’s abnormal return, the authors developed a panel data analysis through a Fixed Effects Model. They measured abnormal returns via Fama–French approach, running a yearly Jensen’s Performance Index for each company under investigation.,The empirical results denote in Italy both a growing interest to corporate social responsibility (CSR) and sustainability by managers over the past decade, as well as an improving quality in ESG assessments because of a reliable corporate disclosure. Thus, despite investors have been applying ESG criteria in their stock – picking operations, the authors found a not positive and statistically significant impact in terms of market premium, when they have been undertaking a socially responsible investment (SRI).,The findings described above show that ethics is not yet a reliable fundraising tool for Italian-listed companies, despite SRIs having a positive growth rate over past decade. Investors seem to be not pricing CSR on Stock Exchange Market; therefore, listed companies cannot be rewarded with a premium price because of their highly stakeholder oriented behavior.,This paper explores, for the first time in Italy, when market extra-returns (if any) are related to corporate social performance and how managers leverage ethics to build capital added value.

An Analysis of Corporate Social Responsibility and Firm Performance with Moderating Effects of CEO Power and Ownership Structure: A Case Study of the Manufacturing Sector of Pakistan

Abstract: Corporate social responsibility (CSR) are the activities of firms that are not only considered for economic profit but also include the social welfare returns. To find the key drivers that affect the relationship between corporate social responsibility (CSR) and firm performance, we investigated the moderating effects of CEO power and ownership structure. Ownership structure is classified into two parts: managerial ownership and ownership concentration. We selected a sample of firms from eight manufacturing sectors of the Pakistani economy for the analysis. We collected data from the State Bank of Pakistan (SBP), Securities and Exchange Commission of Pakistan (SECP), Pakistan Stock Exchange (PSX), and companies’ annual reports over the period 2008 to 2017. We employed the Fixed Effects model and Generalized Method of Moment (GMM) to investigate the association between CSR and firm performance. The empirical analysis of this study highlights the following conclusions: First, CSR has a significant positive association with firm performance. Second, the relationship between CSR and firm performance shows the same results with the interaction of CEO power. Thirdly, interaction of the managerial ownership with CSR has a significant positive relationship with firm performance. Fourth, the interaction of the ownership concentration with CSR has a positive effect on firm performance.

The impact of intellectual capital on SMEs’ performance in China: Empirical evidence from non-high-tech vs. high-tech SMEs

Abstract: The purpose of this paper is to explore and compare the extent of intellectual capital (IC) and its four components in high-tech and non-high-tech small and medium-sized enterprises (SMEs) operating in China’s manufacturing sector, and to examine the relationship between IC and the performance of high-tech and non-high-tech SMEs.,The study uses the data of 116 high-tech SMEs and 380 non-high-tech SMEs listed on the Shenzhen stock exchanges during 2012–2016. The modified value added intellectual coefficient (MVAIC) model is used incorporating four components, namely, capital employed, human capital, structural capital and relational capital. Finally, multiple regression analysis is utilized to test the proposed research hypotheses.,The findings of this paper reveal that there is significant difference in MVAIC between high-tech and non-high-tech SMEs. The results further indicate a positive relationship between IC and financial performance of high-tech and non-high-tech SMEs. Specifically, IC is positively associated with firms’ earnings, profitability and operating efficiency. Additionally, capital employed efficiency, human capital efficiency and structural capital efficiency are found to be the most influential value drivers for the performance of two types of SMEs while relational capital efficiency possesses less importance.,This paper will provide a valuable framework for executives, managers and policy makers in managing IC within the Chinese context.,To the best knowledge of the authors, this is the first empirical study that has been conducted on high-tech and non-high-tech SMEs in the manufacturing sector in China.

Corporate governance and corporate social responsibility (CSR) disclosure in an emerging economy: evidence from commercial banks of Kazakhstan

Abstract: This paper aims to explore the extent and nature of corporate social responsibility (CSR) reporting practices in the banking sector of Kazakhstan and investigates the effects of board characteristics on CSR disclosures in the given emerging economy.,Data on CSR disclosures were manually collected from annual reports of all commercial banks listed in the Kazakhstan Stock Exchange (KASE) for the period 2010-2016. Financial data were obtained from audited financial statements available on bank websites and the Web page of the National Bank of Kazakhstan.,The empirical results reveal that board gender diversity has a positive influence on CSR reposting, while board size and board independence have no impact on the level of CSR disclosures. Furthermore, the results show that bank size and bank age are significant factors in the dissemination of CSR disclosures. Additionally, the findings suggest that banks with a share of foreign ownership disclose more extensive and transparent information on CSR activities than banks owned by local investors and state-owned banks.,The study provides evidence on the relationship between corporate governance and the level of CSR in the context of an emerging economy such as Kazakhstan, representing the Central Asian region. The study contributes to the current literature by focusing on the banking sector of Kazakhstan as a research context due to its substantial representation in the capital market of the given emerging economy.

Board, audit committee, ownership and financial performance – emerging trends from Thailand

Abstract: This study aims to investigate the effects of corporate board and audit committee characteristics and ownership structures on market-based financial performance of listed firms in Thailand.,It applies system GMM (generalized method of moments) as the baseline estimator approach, and ordinary least squares and fixed effects for robustness checks on a sample of 452 firms listed on the Thai Stock Exchange for the period 2000-2016.,Relying mainly on the system GMM estimator, the empirical results indicate some emerging trends in the Thai economy. Contrary to expectations for an emerging market and prior research findings, ownership structures, particularly ownership concentration and family ownership, appear to have no significant influence on market-based firm performance, while managerial ownership exerts a positive effect on performance. Moreover, as expected, board structure variables such as board independence; size; meeting and dual role; and audit committee meeting show significant explanatory power on market-based firm performance in Thai firms.,These findings are important for policymakers in constructing an appropriate set of governance mechanisms in an emerging market context, and for corporate entities and investors in shaping their understanding of corporate governance in the Thai institutional context.,Unlike previous literature on the Thai market, this study is the first to use the more advanced econometric method known as system GMM estimator for addressing causality/endogeneity issues in governance–performance relationships. The findings indicate new trends in the explanatory power of ownership structure variables on market-based firm performance in Thai-listed firms.

Factors influencing the level of environmental disclosures in sustainability reports: Case of climate risk disclosure by Brazilian companies

Abstract: In addition to sustainability issues, companies are being asked to disclose information on climate change risks in order to inform investors and stakeholders. However, despite the growing number of studies on corporate environmental disclosure, there are few studies on risks and opportunities in relation to climate change. This study investigated the extent and content of climate risks information disclosure provided in the sustainability reports of firms listed on the Brazilian Stock Exchange (BM&FBovespa) and tested whether there were any relationships between the amount of climate risks disclosure and some corporation characteristics. The sample was composed of companies that were simultaneously listed on the stock exchange and disclosed the Global Reporting Initiative sustainability reports from 2009 to 2014. The final sample of the study was 67 companies totaling 402 observations. Preliminary results from the content analysis revealed that, although Brazilian companies tend to disclose information on climate risks, the level of this type of disclosure still remains relatively low. Findings suggest that corporate climate risk disclosures have significant and positive relationships with firm size, financial performance, and country origin. Nevertheless, findings indicate that corporate climate risk disclosures have negative associations with level of indebtedness.

The Impacts of Interest Rate on Stock Market: Empirical Evidence from Dhaka Stock Exchange

Abstract: Stock exchange and interest rate are two crucial factor of economic growth of a country. The impacts of interest rate on stock exchange provide important implications for monitory policy, risk management practices, financial securities valuation and government policy towards financial markets. This study seeks evidence supporting the existence of market efficiency on the Dhaka Stock Exchange (DSE) based on the daily general price index 1994 to 2005 and also shows empirical relationship between stock index and interest rate in Bangladesh based on monthly data from May 1992 to June 2004. Stationary of market return is tested and found DSE Index does not follow random walk model indicate DSE is not efficient in week form. The linear relationship between share price and interest rate, share price and growth of interest rate, growth of share price and interest rate, and growth of share price and growth of interest rate were determined through ordinary least-square (OLS) regression. For all of the cases, included and excluded outlier, it is found that Interest Rate has significant negative relationship with Share Price and Growth of Interest Rate also has significant negative relationship with Growth of Share Price. So if the interest rate is considerably controlled in Bangladesh than it will be the great benefit of Dhaka Stock Exchange through demand pull way of more investor in share market and supply pull way of more extensional investment of companies.

Stock return and financial performance as moderation variable in influence of good corporate governance towards corporate value

Abstract: Purpose The purpose of this paper is to evaluate how much influence good corporate governance (GCG) has on corporate value, as well as moderating effect of stock return and financial performance on the influence of GCG on corporate value. Design/methodology/approach This study was an explanatory study. The unit of analysis was the companies listed in LQ45 in Indonesian Stock Exchange and the sources of data were ICMD, annual report and financial reports of the companies. Indonesian Stock Exchange was selected as the setting of the study since Indonesian Stock Exchange is one of trading places for various types of companies in Indonesia, and it provides complete information on company’s financial data and stock price. The population was 84 companies listed in LQ45 in Indonesian Stock Exchange between 2010 and 2016. Findings The higher GCG, independent commissioners proportion, institutional managerial and public ownerships resulted in higher corporate value. MBE and PER stock return is a moderating variable in the influence of GCG on corporate value. Financial performance is moderating variable in the influence of GCG on corporate value. Originality/value Based on the previous studies, it may be concluded that there is a gap between the influence of GCG on corporate value and the influence of stock return on financial performance, and moderating variable is needed to evaluate the influence of GCG on company performance, more particularly stock return and financial performance. This discrepancy creates opportunity for conducting an in-depth study on those variables. Its novelty is correlation between stock return and financial performance as moderation. Previous studies used these as mediating variables. This study is going to generate different finding as it is conducted in different setting (country where this study is conducted), type of industry, research period and using different method of analysis.

Cascading logistic regression onto gradient boosted decision trees for forecasting and trading stock indices

Abstract: Forecasting the direction of the daily changes of stock indices is an important yet difficult task for market participants. Advances on data mining and machine learning make it possible to develop more accurate predictions to assist investment decision making. This paper attempts to develop a learning architecture LR2GBDT for forecasting and trading stock indices, mainly by cascading the logistic regression (LR) model onto the gradient boosted decision trees (GBDT) model. Without any assumption on the underlying data generating process, raw price data and twelve technical indicators are employed for extracting the information contained in the stock indices. The proposed architecture is evaluated by comparing the experimental results with the LR, GBDT, SVM (support vector machine), NN (neural network) and TPOT (tree-based pipeline optimization tool) models on three stock indices data of two different stock markets, which are an emerging market (Shanghai Stock Exchange Composite Index) and a mature stock market (Nasdaq Composite Index and S&P 500 Composite Stock Price Index). Given the same test conditions, the cascaded model not only outperforms the other models, but also shows statistically and economically significant improvements for exploiting simple trading strategies, even when transaction cost is taken into account.

The Impact of Board Gender Diversity and Foreign Institutional Investors on the Corporate Social Responsibility (CSR) Engagement of Chinese Listed Companies

Abstract: The main purpose of this research is to examine the impact of board gender diversity and foreign institutional investors on the corporate social responsibility engagement of Chinese listed companies by considering a sample from the China Stock Market and Accounting Research (CSMAR) database of all non-financial firms listed on the Shanghai stock exchange and the Shenzhen stock exchange during the period from 2008–2015. The CSR is engaged by using the data from the CSMAR database at the firm level, and ranks the CSR disclosures of Chinese companies separately. The recent CSR promotion in China produced a visible increase in attracting female members on the board and members as foreign institutional investors by Chinese listed companies. The findings also showed that the greater the presence of female directors on the board, the stronger the CSR engagement would be. According to critical mass theory and team dynamics, these findings further broaden the accounts that emphasize social networks based on gender. Hence, female members on the board of directors emerged to be significant as a gender mix with extending CSR change. Therefore, our results added a new aspect to the emerging literature on CSR-engagement and gender especially in China. Due to intense political forces and networks in the Chinese listed entities, foreign institutional investors (FIIS) have less incentive to enhance CSR engagement further. Thus, the impact of foreign institutional investors on CSR engagement is as yet unknown, but we improved our knowledge about how the international aspects affect CSR in China. Furthermore, our results are robust, which concern control variables under consideration.

The effect of carbon dissemination on cost of equity

Abstract: This study examines whether firms can influence their cost of equity (COE) by broadly disseminating their carbon information over Twitter. We study firms' dissemination decisions of carbon information by developing a comprehensive measure of carbon information that a firm makes on Twitter, referred to as iCarbon. Using a sample of 1,737 firm‐year observations for 584 nonfinancial firms with a Twitter account and listed on the U.S. NASDAQ stock exchange over the period 2009–2015, we find that iCarbon is significantly and negatively associated with COE. Our results are consistent after determining the effect of Bloomberg's environmental and environmental, social, and governance disclosure. The findings also hold when using alternative measures of COE and iCarbon.

Deep LSTM with Reinforcement Learning Layer for Financial Trend Prediction in FX High Frequency Trading Systems

Abstract: High-frequency trading is a method of intervention on the financial markets that uses sophisticated software tools, and sometimes also hardware, with which to implement high-frequency negotiations, guided by mathematical algorithms, that act on markets for shares, options, bonds, derivative instruments, commodities, and so on. HFT strategies have reached considerable volumes of commercial traffic, so much so that it is estimated that they are responsible for most of the transaction traffic of some stock exchanges, with percentages that, in some cases, exceed 70% of the total. One of the main issues of the HFT systems is the prediction of the medium-short term trend. For this reason, many algorithms have been proposed in literature. The author proposes in this work the use of an algorithm based both on supervised Deep Learning and on a Reinforcement Learning algorithm for forecasting the short-term trend in the currency FOREX (FOReign EXchange) market to maximize the return on investment in an HFT algorithm. With an average accuracy of about 85%, the proposed algorithm is able to predict the medium-short term trend of a currency cross based on the historical trend of this and by means of correlation data with other currency crosses using techniques known in the financial field with the term arbitrage. The final part of the proposed pipeline includes a grid trading engine which, based on the aforementioned trend predictions, will perform high frequency operations in order to maximize profit and minimize drawdown. The trading system has been validated over several financial years and on the EUR/USD cross confirming the high performance in terms of Return of Investment (98.23%) in addition to a reduced drawdown (15.97 %) which confirms its financial sustainability.

Does Green Credit Policy Work in China? The Correlation between Green Credit and Corporate Environmental Information Disclosure Quality

Abstract: Roughly a decade ago, the Chinese government implemented a green credit policy aimed at lowering emissions from highly polluting corporations through improving information disclosure quality during the loan process. According to policy guidelines, banks may provide financial support only for new projects that passed an environmental assessment or were explicitly designed to decrease pollution. This paper used panel data from 320 companies in heavy polluting industries listed on the Shanghai Stock Exchange from 2008 to 2016 and adopted a fixed effects regression model to examine whether collusion between local governments and Chinese listed companies has prevented the green credit policy from achieving its target. The results show that there is no significant positive correlation between CEID and corporate green financing, which means that the environmental information disclosure system does not send valuable signals to the market and has failed to become a decision-making tool for bank-risk management.

CEO characteristics and firm performance: focus on origin, education and ownership

Abstract: This study examines the impact of the chief executive officer’s (CEO) ownership, education and origin on firm performance. The study uses balanced panel data for 6 years from 2011 to 2016 to run ordinary least square regression. Three variables that include the CEO origin, education and ownership are investigated in relation to firm performance. These characteristics are some of the basic CEO characteristics that are rarely considered by prior studies. The study uses a sample from firms in the financial sector listed on the Nigerian Stock Exchange from 2011 to 2016. The findings indicate that CEO education improves profitability. Similarly, stock performance gets improved when the CEO has prior experience of the firm before being appointed as the chief executive officer. The findings will be useful to shareholders in making an informed decision in selecting the right CEO to manage the firm. Further studies need to consider not only the CEO ownership, but also whether the interest in ownership makes them more powerful.

Investor sentiment and stock return volatility: Evidence from the Johannesburg Stock Exchange

Abstract: Volatility is an important component of asset pricing; an increase in volatility on markets can trigger changes in the risk distribution of financial assets. In conventional financial theory, inves...

Earnings management, audit quality, and cost of debt: evidence from a Central Asian economy

Abstract: This study aims to examine the effects of earnings management and audit quality on cost of debt of listed companies in Kazakhstan. The study also investigates the effects of audit quality on earnings management and whether the relationship between earnings management and cost of debt is affected by audit quality in the context of a given emerging economy.,The study sample consists of public companies listed in the Kazakhstan Stock Exchange (KASE) from 2011 to 2016, and all data were obtained from audited financial statements and annual reports downloaded from the webpage of KASE. The study uses the cross-sectional ordinary least squares technique to test the impact of audit quality and earnings management on cost of debt.,The collected empirical evidence shows that earnings management is negatively related to cost of debt. The findings also indicate that higher audit quality leads to a lower cost of debt. However, the results suggest that audit quality has no impact on earnings management and that the effect of earnings management on cost of debt is not different for the companies audited by the Big Four and for the companies audited by other audit firms.,The findings of the study can be of interest to policy-makers, regulators, investors and practitioners in emerging markets with an institutional environment similar to that of Kazakhstan.,The study throws more light on the impact of earnings management and audit quality on cost of debt in Kazakhstan, representing the Central Asian region. This study also extends the current literature by providing empirical evidence that the relationship between earnings management and cost of debt is not affected by audit quality.

Women on corporate boards and firm's financial performance

Abstract: The European Commission has proposed that member countries develop their national self-regulation and governance initiatives to increase the number of women on corporate boards with the aim of promoting gender equality in the processes of decision-making. This has provoked some controversial opinions, which in turn has led to the search for factual data which may support the legal initiatives. In order to shed more light on this topic, this study investigates the influence of a higher percentage of women on the board of directors of companies (excluding financial companies) included in the index of the Spanish Stock Exchange IBEX35 for a fifteen-year period: 2003–2017. To do this, we use a two-stage instrumental variables (IV) regression to address endogeneity and reverse causality problems. Moreover, we study the influence of a mandatory law on female presence on company boards by using a panel data methodology. The findings of this study show that the increasing number of women on boards is positively related to higher financial performance. Moreover, as expected, the gender mandatory law boosts the female proportion on boards of directors. Consequently, there are valid business as well as ethical arguments to support mandatory gender legislation.

A Robust Predictive Model for Stock Price Prediction Using Deep Learning and Natural Language Processing

Abstract: Prediction of future movement of stock prices has been a subject matter of many research work. There is a gamut of literature of technical analysis of stock prices where the objective is to identify patterns in stock price movements and derive profit from it. Improving the prediction accuracy remains the single most challenge in this area of research. We propose a hybrid approach for stock price movement prediction using machine learning, deep learning, and natural language processing. We select the NIFTY 50 index values of the National Stock Exchange of India, and collect its daily price movement over a period of three years (2015 to 2017). Based on the data of 2015 to 2017, we build various predictive models using machine learning, and then use those models to predict the closing value of NIFTY 50 for the period January 2018 till June 2019 with a prediction horizon of one week. For predicting the price movement patterns, we use a number of classification techniques, while for predicting the actual closing price of the stock, various regression models have been used. We also build a Long and Short-Term Memory - based deep learning network for predicting the closing price of the stocks and compare the prediction accuracies of the machine learning models with the LSTM model. We further augment the predictive model by integrating a sentiment analysis module on twitter data to correlate the public sentiment of stock prices with the market sentiment. This has been done using twitter sentiment and previous week closing values to predict stock price movement for the next week. We tested our proposed scheme using a cross validation method based on Self Organizing Fuzzy Neural Networks and found extremely interesting results.