scholarly journals Event Study: Advanced Machine Learning and Statistical Technique for Analyzing Sustainability in Banking Stocks

Mathematics ◽  
2021 ◽  
Vol 9 (24) ◽  
pp. 3319
Author(s):  
Varun Dogra ◽  
Aman Singh ◽  
Sahil Verma ◽  
Abdullah Alharbi ◽  
Wael Alosaimi
Keyword(s):  
Machine Learning ◽  
Stock Prices ◽  
Research Work ◽  
Abnormal Returns ◽  
Second Phase ◽  
Financial News ◽  
News Events ◽  
News Event ◽  
The Impact

Machine learning has grown in popularity in recent years as a method for evaluating financial text data, with promising results in stock price projection from financial news. Various research has looked at the relationship between news events and stock prices, but there is little evidence on how different sentiments (negative, neutral, and positive) of such events impact the performance of stocks or indices in comparison to benchmark indices. The goal of this paper is to analyze how a specific banking news event (such as a fraud or a bank merger) and other co-related news events (such as government policies or national elections), as well as the framing of both the news event and news-event sentiment, impair the formation of the respective bank’s stock and the banking index, i.e., Bank Nifty, in Indian stock markets over time. The task is achieved through three phases. In the first phase, we extract the banking and other co-related news events from the pool of financial news. The news events are further categorized into negative, positive, and neutral sentiments in the second phase. This study covers the third phase of our research work, where we analyze the impact of news events concerning sentiments or linguistics in the price movement of the respective bank’s stock, identified or recognized from these news events, against benchmark index Bank Nifty and the banking index against benchmark index Nifty50 for the short to long term. For the short term, we analyzed the movement of banking stock or index to benchmark index in terms of CARs (cumulative abnormal returns) surrounding the publication day (termed as D) of the news event in the event windows of (−1,D), (D,1), (−1,1), (D,5), (−5,−1), and (−5,5). For the long term, we analyzed the movement of banking stock or index to benchmark index in the event windows of (D,30), (−30,−1), (−30,30), (D,60), (−60,−1), and (−60,60). We explore the deep learning model, bidirectional encoder representations from transformers, and statistical method CAPM for this research.

scholarly journals The Impact of COVID-19 on the Stock Price of Socially Responsible Enterprises: An Empirical Study in Taiwan Stock Market

2021 ◽  
Vol 18 (4) ◽  
pp. 1398
Author(s):  
Kuo-Jung Lee ◽  
Su-Lien Lu
Keyword(s):  
Stock Market ◽  
Stock Prices ◽  
Stock Price ◽  
Abnormal Returns ◽  
Recovery Phase ◽  
Socially Responsible ◽  
Cumulative Impact ◽  
Study Approach ◽  
Price Performance ◽  
The Impact

This study examines the impact of the COVID-19 outbreak on the Taiwan stock market and investigates whether companies with a commitment to corporate social responsibility (CSR) were less affected. This study uses a selection of companies provided by CommonWealth magazine to classify the listed companies in Taiwan as CSR and non-CSR companies. The event study approach is applied to examine the change in the stock prices of CSR companies after the first COVID-19 outbreak in Taiwan. The empirical results indicate that the stock prices of all companies generated significantly negative abnormal returns and negative cumulative abnormal returns after the outbreak. Compared with all companies and with non-CSR companies, CSR companies were less affected by the outbreak; their stock prices were relatively resistant to the fall and they recovered faster. In addition, the cumulative impact of the COVID-19 on the stock prices of CSR companies is smaller than that of non-CSR companies on both short- and long-term bases. However, the stock price performance of non-CSR companies was not weaker than that of CSR companies during times when the impact of the pandemic was lower or during the price recovery phase.

Market reactions to the inclusion of people with disabilities

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Claudia Araceli Hernández González
Keyword(s):  
Event Study ◽  
Stock Prices ◽  
Stock Price ◽  
Abnormal Returns ◽  
People With Disabilities ◽  
Market Reactions ◽  
Content Type ◽  
Study Methodology ◽  
Research Advance ◽  
The Impact

PurposeThis study aims to provide evidence of market reactions to organizations' inclusion of people with disabilities. Cases from financial journals in 1989–2014 were used to analyze the impact of actions taken by organizations to include or discriminate people with disabilities in terms of the companies' stock prices.Design/methodology/approachThis research is conducted as an event study where the disclosure of information on an organization's actions toward people with disabilities is expected to impact the organization's stock price. The window of the event was set as (−1, +1) days. Stock prices were analyzed to detect abnormal returns during this period.FindingsResults support the hypotheses that investors value inclusion and reject discrimination. Furthermore, the impact of negative actions is immediate, whereas the impact of positive actions requires at least an additional day to influence the firm's stock price. Some differences among the categories were found; for instance, employment and customer events were significantly more important to a firm's stock price than philanthropic actions. It was observed that philanthropic events produce negative abnormal returns on average.Originality/valueThe event study methodology provides a different perspective to practices in organizations regarding people with disabilities. Moreover, the findings in this research advance the literature by highlighting that organizations should consider policies and practices that include people with disabilities.

scholarly journals Stock Price Prediction Using Convolutional Neural Networks on a Multivariate Time Series

2021 ◽  
Author(s):  
Sidra Mehtab ◽  
Jaydip Sen
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Stock Prices ◽  
Stock Price ◽  
Regression Models ◽  
Research Work ◽  
Hybrid Approach ◽  
Forecast Horizon ◽  
Stock Price Prediction ◽  
Price Prediction

Prediction of future movement of stock prices has been a subject matter of many research work. On one hand, we have proponents of the Efficient Market Hypothesis who claim that stock prices cannot be predicted, on the other hand, there are propositions illustrating that, if appropriately modelled, stock prices can be predicted with a high level of accuracy. There is also a gamut of literature on technical analysis of stock prices where the objective is to identify patterns in stock price movements and profit from it. In this work, we propose a hybrid approach for stock price prediction using machine learning and deep learning-based methods. We select the NIFTY 50 index values of the National Stock Exchange (NSE) of India, over a period of four years: 2015 – 2018. Based on the NIFTY data during 2015 – 2018, we build various predictive models using machine learning approaches, and then use those models to predict the “Close” value of NIFTY 50 for the year 2019, with a forecast horizon of one week, i.e., five days. For predicting the NIFTY index movement patterns, we use a number of classification methods, while for forecasting the actual “Close” values of NIFTY index, various regression models are built. We, then, augment our predictive power of the models by building a deep learning-based regression model using Convolutional Neural Network (CNN) with a walk-forward validation. The CNN model is fine-tuned for its parameters so that the validation loss stabilizes with increasing number of iterations, and the training and validation accuracies converge. We exploit the power of CNN in forecasting the future NIFTY index values using three approaches which differ in number of variables used in forecasting, number of sub-models used in the overall models and, size of the input data for training the models. Extensive results are presented on various metrics for all classification and regression models. The results clearly indicate that CNN-based multivariate forecasting model is the most effective and accurate in predicting the movement of NIFTY index values with a weekly forecast horizon.

scholarly journals Impacto dos Ratings de crédito nas ações de empresas de capital aberto no Brasil

2017 ◽  
Vol 16 (2) ◽  
pp. 573-602
Author(s):  
Rafaela Augusta Cunha Silveira ◽  
Renata Turola Takamatsu ◽  
Bruna Camargos Avelino
Keyword(s):  
Stock Prices ◽  
Credit Rating ◽  
Stock Exchange ◽  
Abnormal Returns ◽  
Final Analysis ◽  
Share Prices ◽  
New Information ◽  
Agency Issues ◽  
Study Methodology ◽  
The Impact

Resumo O rating de crédito expressa uma opinião, por intermédio de escalas, sobre a qualidade do crédito de empresas, utilizado-a como medida de avaliação de risco no mercado. Agências de classificação de risco de crédito, como a Moody’s, divulgam os ratings que atribuem às empresas. Primeiramente, essas agências emitem o new rating, que representa o primeiro rating da companhia, e, posteriormente, essa emissão pode apresentar variações, denominadas upgrades e downgrades, relativas a boas e más notícias, respectivamente. Além disso, os ratings podem ser colocados em uma Watchlist quando, em breve, pode haver uma mudança do rating para downgrade ou para upgrade. O objetivo com este estudo consistiu, diante do que foi tratado, em abordar o impacto do rating de crédito sobre os preços das ações de empresas listadas na bolsa de valores brasileira. Para alcançar o objetivo proposto, foi analisada uma amostra de 44 empresas comercializadas na BM&FBovespa e 65 ratings nacionais de longo prazo emitidos pela Moody’s entre 2000 e 2015. Utilizou-se a metodologia de estudo de eventos, com os retornos normais calculados pelo modelo de retornos ajustados ao risco e ao mercado, e o Teste-F e o Teste-T para verificar a significância dos resultados. As análises finais evidenciaram que os preços das ações não são afetados de forma significativa pelas divulgações dos new ratings, downgrades, upgrades, on watch – possible downgrades e on watch – possible upgrades em nenhuma janela do evento, indicando que os ratings, para a amostra analisada, não trazem novas informações ao mercado.Palavras-chave: Ações. Rating. Estudo de eventos. Retornos anormais. Abstract Credit ratings are used as a mean to investors get new information on the companies by reducing the information asymmetry in the market. Thus, the rating is an important mean of business information with investors, enabling share prices relating to companies react to it. Branches of credit rating as Moody's, disclose the ratings they assign to companies. First, the agency issues the new rating, which represents the company's first rating, then this issue may vary, upgrades and downgrades calls relating to good and bad news respectively. In addition, the ratings could be placed in a Watchlist when, soon there may be a change to the rating downgrade or upgrade. The purpose of this study was to discuss the impact that the credit rating has on stock prices of companies listed on the Brazilian stock exchange. For a sample of 44 companies traded on BM&FBovespa and 65 long-term national ratings issued by Moody's between 2000 and 2015, we used the event study methodology, with normal returns calculated by the model of returns adjusted for risk and market the F-Test and T-Test to test the significance of the results. The final analysis showed that stock prices are not significantly affected by the disclosures of new ratings, downgrades, upgrades, on watch – possible downgrades and on watch – possible upgrades in any event window, indicating that the ratings do not bring new information to the market.Keywords: Stocks. Rating. Event studies. Abnormal returns.

scholarly journals Analyzing the Impact of Climate Factors on GNSS-Derived Displacements by Combining the Extended Helmert Transformation and XGboost Machine Learning Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Hanlin Liu ◽  
Linqiang Yang ◽  
Linchao Li
Keyword(s):  
Machine Learning ◽  
Puerto Rico ◽  
Reference Frame ◽  
Learning Algorithm ◽  
Virgin Islands ◽  
Machine Learning Algorithm ◽  
Climate Factors ◽  
Helmert Transformation ◽  
The Impact

A variety of climate factors influence the precision of the long-term Global Navigation Satellite System (GNSS) monitoring data. To precisely analyze the effect of different climate factors on long-term GNSS monitoring records, this study combines the extended seven-parameter Helmert transformation and a machine learning algorithm named Extreme Gradient boosting (XGboost) to establish a hybrid model. We established a local-scale reference frame called stable Puerto Rico and Virgin Islands reference frame of 2019 (PRVI19) using ten continuously operating long-term GNSS sites located in the rigid portion of the Puerto Rico and Virgin Islands (PRVI) microplate. The stability of PRVI19 is approximately 0.4 mm/year and 0.5 mm/year in the horizontal and vertical directions, respectively. The stable reference frame PRVI19 can avoid the risk of bias due to long-term plate motions when studying localized ground deformation. Furthermore, we applied the XGBoost algorithm to the postprocessed long-term GNSS records and daily climate data to train the model. We quantitatively evaluated the importance of various daily climate factors on the GNSS time series. The results show that wind is the most influential factor with a unit-less index of 0.013. Notably, we used the model with climate and GNSS records to predict the GNSS-derived displacements. The results show that the predicted displacements have a slightly lower root mean square error compared to the fitted results using spline method (prediction: 0.22 versus fitted: 0.31). It indicates that the proposed model considering the climate records has the appropriate predict results for long-term GNSS monitoring.

Testing Market Reaction On Stock Market Delisting In Russia

2021 ◽  
Vol 15 (3) ◽  
pp. 14-27
Author(s):  
Елена Моисеевна Рогова ◽  
Maria Belousova
Keyword(s):  
Stock Market ◽  
Stock Prices ◽  
Statistical Significance ◽  
Abnormal Returns ◽  
Global Market ◽  
Public Companies ◽  
Market Participants ◽  
Study Methodology ◽  
Available Information ◽  
The Impact

This paper expands the available information on the effects of delisting in Russia, and represents a rare empirical analysis of the impact of external events on securities prices in this major global market. We seek to evaluate how stock prices of competing companies fluctuate around the dates of stock market delisting announcements and completion. We analyse stock prices as correlated with company delisting events from 2004 to 2019 on 552 companies on the Russian MOEX Exchange. The event study methodology is used to evaluate the abnormal returns of rival companies close to relevant delisting dates. These data were checked for statistical significance using the standardised Patell residual test. The results indicate a significant competitive effect on stock prices both on the dates of delisting announcement and on completion, with more significant returns close to announcement dates. These effects were found to influence the prospects not just of individual groups of companies, but of all market participants. We may conclude from our results that delisting is not an event limited in effect to only one company, but impacts the industry as a whole, temporarily changing its value. As such, it will interest both shareholders and managers of public companies, and any participants of industries in which delisting occurs.

scholarly journals The Dynamic Effects of Terrorism on Tourism: A Bound Testing Co-integration Approach

2020 ◽  
Vol 16 (1) ◽  
pp. 44-57
Author(s):  
Jamil Shah ◽  
Keyword(s):  
Research Work ◽  
Tourism Industry ◽  
Mountainous Area ◽  
Short Term ◽  
Khyber Pakhtunkhwa ◽  
Domestic Tourism ◽  
Swat Valley ◽  
The Impact ◽  
Bound Test

Tourism industry is considered a key driver promoting socioeconomic development in under development economy, but there are several factors which hindering this development. The terror incidence in swat valley have severely affected tourism industry of the area. Terrorism is a growing hazard across the globe with severs socio-economic consequences. Pakistan is also playing it’s was against terrorism that it has affected its various economic activities including tourism. During the first decade of the ongoing century, northern mountainous area of Khyber Pakhtunkhwa, which was famous for tourism, was badly affected by incidences of terror2. The objective of this research work is to estimate the impact of terror incidents on domestic tourism in Pakistan, Khyber Pakhtunkhwa, Swat Valley (TA –domestic visitors’ arrivals).The current research is an effort to evaluate the short-term and long-term association between events of terror and domestic visitation. Primary data was collected using stratified random sampling techniques and interview method and secondary data was taken from various sources to evaluate the model. Auto Regressive Distributive Lag (ARDL) model is used to evaluate the data. The ARDL bound test confirms the co-integration between terror incidents and tourism. Additionally, the examined findings undoubtedly ensure the negative short-term and long-term impact of events of terror on domestic tourism in the study area.

scholarly journals The impact of Indonesian oil price (CPI) and macroeconomics on investments in the manufacturing sector in Indonesia

F1000Research ◽  
2021 ◽  
Vol 10 ◽  
pp. 338
Author(s):  
Handri Handri ◽  
Hendrati Dwi Mulyaningsih ◽  
Achmad Kemal Hidayat ◽  
Rudi Kurniawan ◽  
Ani Wahyu Rachmawati
Keyword(s):  
Energy Source ◽  
Stock Prices ◽  
Manufacturing Sector ◽  
Granger Causality Test ◽  
Oil Price ◽  
Causality Test ◽  
Long Run ◽  
Short Run ◽  
The Impact

Background: Indonesia consumes oil as the main energy source in the production process and as a result of the development of the manufacturing industry. Thus, investment in manufacturing stocks will be affected by oil price fluctuations and macroeconomic conditions. Changes in oil prices will affect the performance of the manufacturing sector which in turn affects manufacturing stock prices. This paper aims to examine the impact of Indonesia's oil price shocks and macroeconomic factors on stock price movements in the manufacturing sector. Methods: This study uses monthly data for the 2009-2016 period in the manufacturing sector, and 67 stocks were selected on the basis consistently available in the period of the research. The cointegration and causality technique was used in this paper; firstly we applied a unit-panel root test, Secondly, we performed a residual test to indicate whether there was cointegration among variables in the long run equilibrium, and short the short run, we used a Granger causality test. Results: The panel unit root test (both Shin and Fisher) and the Pedroni cointegration residual test show that the data is stationary at 1%  level of significance, thus all variables simultaneously achieve long-run equilibrium, and in the short run, the Granger causality test shows that there is one way direction causality Conclusions: For long-term investment in manufacturing stocks, investors must consider the exchange rate, as it is also as a determining factor in influencing the movement of manufacturing stock prices, inflation, and the production index. Meanwhile, weakening of the rupiah in the short run will also determine investment conditions due to the dependency on raw materials for production from foreign sources. The price of oil as an energy source in the manufacturing sector does not have a long-term relationship with other variables.

Empirical Analysis of Dependence on Capital Structure with Respect to Its Impact on the Financial Performance of Domestic Non Financial Listed Stock Exchange Companies Operating in the Public Sector of Pakistan

2016 ◽  
Vol 3 (2) ◽  
pp. 58-76
Author(s):  
Syed Jawad Hussain Shahzad ◽  
Memoona Kanwal
Keyword(s):  
Capital Structure ◽  
Financial Performance ◽  
Stock Exchange ◽  
Random Effect ◽  
Random Effect Model ◽  
Research Work ◽  
Debt Financing ◽  
The Impact ◽  
The Relationship

This research work is based on the relationship that exists between the capital structure and performance of different sector's firms currently operating in the Pakistan. Capital structure decisions can be considered as the most important financial performance and risk management tools which are available to the companies' management. Capital structure can also play an important role in performance assessment, in performance management and in effective handling of ownership claims. The extensive use and heavy dependence on debt has exposed many companies to potential risk of declined performance and also to the risk of insolvency. This study analyzes the relationship between various capital structure indicators and dependence of financial performance of companies on these indicators using a broad sample covering 202 non-financial firms listed on Karachi Stock Exchange (KSE) over the period of 1999-2012. The sample firms are divided into five sectors i.e. Textile, Chemical, Cement, Food and Fuel & Energy. Financial performance of firms is quantified by Return on Assets (ROE), Return on Equity (ROE), Price-Earnings ratio (PE) and Tobin's Q (TQ). The relationship between financial performance measures and capital structure measures i.e. total debt, short term debt and long term debt is estimated using GLS fixed and random effect model. Sector wise comparison shows that majority of the sectors have similar capital structure. The impact of capital structure on the financial performance is also similar across sectors with few variations. Overall the relationship is found to be negative among capital structure and firm performance measured by ROA, ROE and PE except TQ which is positively related to Long Term Debt to total Assets (LTDA). The result of industry wise comparison contributes significantly to the existing stream of knowledge. The results indicate that lower reliance on the debt financing improves the performance of the firm whereas dependence and exposure of debt financing reduce performance. The research can be useful for the management of companies in different sectors that want to improve their performance.

STUDY OF THE IMPACT OF INTERNATIONAL FINANCIAL CRISIS ON TAIWAN’S GAME INDUSTRY AND INVESTORS

2018 ◽  
Vol 4 (2) ◽  
pp. 13-18
Author(s):  
Bi-Huei Tsai
Keyword(s):  
Financial Crisis ◽  
Stock Returns ◽  
Video Game ◽  
Stock Prices ◽  
Abnormal Returns ◽  
Efficient Market Hypothesis ◽  
Economic Recovery ◽  
Market Reactions ◽  
Game Industry ◽  
The Impact

Purpose of study: This study investigates the change of stock returns during the Lehman Brother’s announcement of bankruptcy in 2008 for the Taiwanese listed video game companies. We further explore the change of stock returns for the Taiwanese listed video game companies after Taiwan’s economy recovers from Lehman Brother’s bankruptcy. Methodology: This study utilizes the event study method to statistically test abnormal returns so as to understand whether the Lehman Brother’s bankruptcy-related event affects stock prices and whether securities prices reflect Lehman Brother’s bankruptcy-related information. Main Findings: The results show a significant negative abnormal rate during Lehman Brother’s declaration of bankruptcy on Sep. 15, 2008. Investors were affected by the financial crisis caused by Lehman Brother’s bankruptcy and fully reflected on the stock prices of that day. In addition, our results show that video game companies have significantly positive returns when most Taiwanese electronics firms stop no-pay leave on March 31, 2009. It represents investors were encouraged by this information and fully reflected on the stock prices. Implications: The results support the efficient market hypothesis. The pattern of CARs experiences a constant increase and displays the apparent price rise during the announcement of no-pay leave stop. The positive abnormal returns are accompanied by the economic recovery. Originality/Novelty: This investigation for the first time chooses the stop of no-pay leave as the indicator of economic recovery from financial crisis. Our analysis novel explores the impact of the financial crisis and the economic recovery on the game industry simultaneously and the results show significantly different market reactions between the occurrence of the financial crisis and economic recovery.

Sign in / Sign up

Export Citation Format

Share Document