Daily Stock Research Articles

Prediction of Stock Price of GCC Islamic Banks Using Neural Network

Purpose: This study aims to evaluate the predicting ability of two machine learning models (ANN and KNN) to predict the stock prices of GCC Islamic banks. Methodology: The study analyzes the accuracy rates of two machine learning models to predict the stock prices of GCC Islamic banks by using the daily stock prices (open, close, high, and low) for a period of ten years (May 4th, 2012–May 31st, 2022). Findings: The predicting ability of the trained ANN and KNN models is evaluated using standard strategic indicators: root mean square error (RMSE), mean bias error (MBE), and accuracy rates. Originality: This study is distinctive in that it emphasizes the significance of machine learning models as an alternative to traditional methods for predicting stock prices. Research Limitations: The study has conducted a comparative analysis of the accuracy rates of only two machine learning models and determined the superior model among them. Practical Implication: The findings of this study have certain implications, as the results can be used to gain significant profits in the GCC region, as they help in predicting market fluctuations, discovering hidden relationships in the data sets, and making accurate investment decisions.

The effect of ownership concentration on firm risk and value: evidence from Germany

Aim: This paper aims to understand the effects of between ownership concentration on firm risk and value.
 Design / Research methods: The author focuses on the largest publicly listed 91 German corporations in the time period 2010 to 2021. The resulting sample contains between 928 and 1051 observations and is analysed through a pooled OLS regression analysis. Ownership concentration is measured in terms of the number of blockholders, the size of the largest shareholder, and the Herfindahl Index of the ten largest shareholders. Firm value is captured with Tobin’s Q and firm risk is computed as the annualised daily stock price volatility.
 Conclusions / Findings: It is found that ownership concentration affects firm risk significantly negatively. Moreover, results suggest an inverse U-shape relationship between ownership concentration and firm value. This relationship can be explained by combining the negative effects of rising ownership concentration on firm risk with its implications for the creation of firm value.
 Originality / Value of the article: The German market has used to have a network-like structure with a concentrated ownership structure. However, over the past two decades, it transformed towards a more Anglo-Saxon-like and market-based structure with a rather dispersed ownership structure. Furthermore, factors which govern the relationship between ownership concentration are used to explain parts of the relationship between firm value and ownership concentration in a new way, thereby adding value to understanding the latter, highly debated, relationship.

Navigating GPT-4 and BERT: A Dual Perspective on Financial and Political Sentiment Analysis

Abstract: This research delves into the dynamic capabilities of large language models (LLMs) by combining insights from two distinct studies. The first study, "Linking Microblogging Sentiments to Stock Price Movement: An Application of GPT-4," explores the efficacy of the GPT-4 Language Learning Model (LLM) compared to BERT in modeling same-day daily stock price movements for Apple and Tesla in 2017. The study leverages sentiment analysis of microblogging messages from the Stocktwits platform and employs a novel method for prompt engineering, emphasizing the contextual abilities of GPT-4. Logistic regression is utilized to evaluate the correspondence between extracted message contents and stock price movements, revealing GPT-4's substantial accuracy, outperforming BERT in five out of six months. However, practical considerations, including deployment costs and the need for fine-tuning prompts, are also acknowledged. The second study, "Do We Still Need BERT in the Age of GPT? Comparing the Benefits of Domain-Adaptation and In-Context-Learning Approaches to Using LLMs for Political Science Research," investigates the choices researchers face when employing LLMs in political science tasks. The study establishes benchmarks for various natural language processing (NLP) tasks within political science and compares two common approaches: domain-adapting smaller LLMs like BERT with unsupervised pre-training and supervised fine-tuning and querying larger LLMs like GPT-3 without additional training. Preliminary results suggest that, when labeled data is available, a finetuning-focused approach remains superior for text classification. By synthesizing these studies, this research contributes to the broader understanding of LLMs' capabilities and their applicability in diverse domains. It emphasizes the significance of prompt engineering in unlocking the contextual abilities of modern LLMs, providing insights into financial sentiment analysis and political text classification. The findings underscore the nuanced choices researchers must make in selecting appropriate LLMs, adapting them to specific domains, and designing effective prompts for optimal performance in different research contexts.

The Effects of Oil Price Volatility on South African Stock Market Returns

The aim of this study is to assess the response of the South African stock market returns to oil price volatility, based on the daily South African stock market index, using the GARCH-Copula modelling technique. The results of the analysis show evidence of an asymmetric impact of fluctuations in oil prices on South African stock market returns, using a copula model specification, particularly the bivariate symmetrized Joe-Clayton (SJC) copula. The results also revealed that the EGARCH process is the best univariate model to capture oil price volatility. Interestingly, this study also revealed that the tourism industry is most dependent on oil price fluctuations, due to its heavy reliance on transportation costs. The economic implications of this study also suggest that sectors affected by oil price fluctuations need specific long-term and short-term monetary policy strategies. It is recommended that in the short term, expansionary monetary policy could assist in mitigating the impact of higher oil prices, while in the long-term, policies aimed at reducing the volatility in oil prices would be of great help in alleviating its harmful effect on stock market returns.

Enhancing daily stock trading with a novel fuzzy indicator: Performance analysis using Z-number based fuzzy TOPSIS method

In the dynamic realm of financial markets, developing effective strategies for stock exchange transactions is paramount. This research addresses this critical need by introducing a pioneering indicator for daily stock trading, leveraging a robust fuzzy inference system (FIS). The indicator ingeniously integrates key technical indicators including Moving Average Convergence and Divergence (MACD), Relative Strength Index (RSI), Stochastic Oscillator (SO), and On-Balance-Volume (OBV). The FIS is meticulously constructed based on expert opinions and gleaned fuzzy rules. The fuzzified values then serve as inputs to the FIS, which in turn generates signals indicating optimal actions: buy, hold, or sell stocks. To validate the importance of the FIS, a carefully curated selection of stocks from the NASDAQ stock exchange is employed for experimentation. To prove the efficiency of the FIS, the technical indicators and the fuzzy risk-adjusted returns are considered as alternatives and criteria, respectively. A novel Z-number-based technique for order preference by similarity to the ideal solution (TOPSIS) method is used to rank the technical indicators and the FIS. The comparative results unequivocally demonstrate that the developed FIS surpasses existing indicators, yielding superior returns.

PRICING OF CALL OPTIONS USING THE QUASI MONTE CARLO METHOD

A call option is a type of option that grants the option holder the right to buy an asset at a specified price within a specified period of time. Determining the option price period of time within a certain period of time is the most important part of determining an investment strategy. Various methods can be employed to determine the prices of options, such as Quasi-Monte Carlo and Monte Carlo simulations. The purpose of this research is to determine the price of European-type call options using the Quasi-Monte Carlo method. The data used is daily stock closing price data on the Apple Inc. for the period October 1, 2021, to September 30, 2022. Apple Inc. stock options in this study were chosen because it is the largest technology company in the world in 2022. The steps taken in this study are to determine the parameters obtained from historical data such as the initial risk-free interest rate (r), stock price (, volatility , maturity time (T), and strike price (K). Next is to generate Halton’s quasi-randomized sequence and simulate the stock price by substituting the parameters by substituting the parameters. Then proceed to calculate the call option payoff and estimate the call option price by averaging the call option payoff values. The results showed that the call option price of the company Apple Inc. using the Quasi-Monte Carlo with Halton’s quasi-randomized sequence on the 1000000th simulation with a standard error of 0,045 is $90,163. The call option price obtained can be used as a reference for investors in purchasing options to minimize losses from call option investments in that period.

Dynamics of oil price shocks in Latin American stock markets during global turbulence: A nonlinear autoregressive distributed lag analysis

This paper investigates the impacts of oil price shocks on the stock markets of six Latin American countries – Argentina, Brazil, Chile, Colombia, Mexico, and Peru – by employing a Nonlinear Autoregressive Distributed Lag (NARDL) approach. This is during periods of global turbulence triggered by the COVID-19 pandemic and Russia’s war in Ukraine. The study used data gathered from January 2020 to July 2023, daily stock prices of the six countries, and West Texas Intermediate (WTI) as a proxy of the oil price index. The analysis revealed that the complex relationship between oil price shocks and stock markets in Latin America has changed significantly since the start of the pandemic and the Russian-Ukrainian War. The findings indicate that the relationship between oil price changes and stock markets is not a straightforward linear correlation, but rather is more complex, with non-linear and counteracting effects, likely due to the uncertainty created by the pandemic and the Russian-Ukrainian War, which has caused investors to be more cautious when responding to oil price shocks.

The impact of COVID-19 pandemic on financial performance: Comparison between Egyptian SMEs Tamayoz and EGX30 index

Most SMEs experience economic collapse and even insolvency due to a lack of sufficient governmental support, particularly those working in growing nations like Egypt with a heavy focus on SMEs’ growth and political and economic instability. As a result, this paper seeks first to measure the consequences of COVID-19 on financial performance (FP) by comparing small and medium enterprises (SMEs) with listed corporations in the Egyptian Stock Exchange (EGX). Second, we examine the impact of governmental interventions on this association. Our sample includes 26 SMEs in the Tamayoz EGX and the highest 30 firms listed in the EGX30. We applied pooled ordinary least square regression, paired sample test, and Barron and Kenny’s test. We used daily stock market returns from January 2020 to November 2020. The proliferation of COVID-19 has an influence on stock prices in both the EGX30 and Tamayoz stock indexes. We furthermore find a partial mediation of income support, facial-covering, school closures, and restrictions on international movements on the linkage between COVID-19 and FP for SMEs. The stock prices listed in EGX30 seem more sensitive to governmental interventions than Tamayoz EGX. The findings confirm governmental interventions would have a significant role in the firm’s FP during the COVID-19 pandemic.

Forecasting multistep daily stock prices for long-term investment decisions: A study of deep learning models on global indices

Deep machine learning algorithms play an important role in facilitating the development of predictive models for the stock market. However, most studies focus on predicting next-day stock prices or movements, limiting the usability of the predictive model for investors. This study extensively explores the ability of deep learning models to predict out-of-sample the daily prices of global stock indices over a long term, up to a year. The performance of six models, including Deep Neural Network (DNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (Bi-LSTM), Gated Recurrent Unit (GRU), and Convolutional Neural Network (CNN), are compared using Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). The models predict the long-term daily prices of five global stock indices, namely the Nifty, the Dow Jones Industrial Average (DJIA), the DAX performance index (DAX), the Nikkei 225 (NI225), and the Shanghai Stock Exchange composite Index (SSE). The results confirm the superiority of LSTM for predicting long-term daily prices. The Bi-LSTM does not improve the result of LSTM but performs better than other algorithms. CNN overfits the training data and poorly forecasts the long-term stock prices of global indices on the testing data. This research demonstrates the potential of deep learning models for long-term stock price forecasting, offering valuable insights for investors. Additionally, the patterns of predicted daily prices can be helpful in building trading and risk management decision systems.

Introducing NBEATSx to realized volatility forecasting

This paper investigates the application of neural basis expansion analysis with exogenous variables (NBEATSx) in the prediction of daily stock realized volatility for various time steps. It compares NBEATSx’s forecasting accuracy and robustness with several commonly used models, namely Long-Short Term Memory (LSTM) network, Temporal Neural Network (TCN), HAR, GARCH, and GJR-GARCH models. In this research, a total of six distinct stock indexes, three error measures, and four statistical tests are used, while three robustness tests are conducted to verify the outcomes of this paper. The findings of this research show that NBEATSx consistently yields statistically more accurate and robust forecasts than the other considered models. On average, NBEATSx generates forecasts that are respectively 13% and 8% more accurate for medium-term and long-term forecasting. Additionally, it produces forecasts that are respectively 43%, 60%, and 59% more robust for short-term, medium-term, and long-term forecasting. Yet, it should be noted that the superiority of NBEATSx in terms of forecast accuracy is not evident when applied to stock indexes from developing countries.

Stock Market Anomalies and Efficient Market Hypothesis: Empirical Analysis of Monday Effect of Selected Securities from Nigeria

This study was conducted to examine stock market anomalies and efficient market hypothesis with empirical analysis of Monday effect of selected securities from Nigeria. Daily stock prices of 20 quoted firms were sourced from www.cashcraft.com. The study used Friday 4/11/2022, and Friday 3/12/2022 to test against Monday Effect 7/11/2022 and Monday 5/12/2022. The prices of the stocks on Friday against Monday were used to test the market anomalies and the efficient market hypothesis. Findings of the study revealed a mix reaction of stock market anomalies and efficient market hypothesis among the studied securities. Evidence from table 1 and 2 proved that some stocks have return greater or less than zero which implies that investors in such stocks had abnormal return which contrary to the assumptions of efficient market hypothesis. However, some stocks have no return from the price of Friday and the price of Monday which implies that the investor have no return, this is in line with efficient market hypothesis. The study recommends that the regulatory authorities should develop the stock market such that the functioning of the market is in line with the stock market of the developed countries to reflect relevant assumptions and theories

Stock Price Prediction Based on Daily News Headlines: Logistic Regression Model and LSTM Model

The influence of daily news on the economy, especially stock market, cannot be underestimated with big data gaining its momentum. In this article, the author uses two years of daily news headlines to predict the stock market movements of the Dow Jones Industrial Average. The first treatments on the dataset are collecting news from Kaggle.com and stock data from Yahoo Finance. The two datasets are then combined into one CSV file and split into training and test sets. Two machine learning models, Logistic Regression and Long Short-Term Memory, are built to fit the combined dataset, and the test index is the accuracy of prediction. The test accuracy is 0.58 with the three-word phrase by Logistic Regression and 0.65 after ten times training with the LSTM model. The final result demonstrates that the two models are feasible and effective for seeking the relationship between daily news and stock market movements and, thus, valuable for stock prediction. The attempts to set parameters give reference to further study, especially the word count of phrases and the number of training circulation.

The Psychological Externalities of Investing: Evidence from Stock Returns and Crime

Abstract This paper investigates the psychological effects from stock market returns. Using an FBI database of over 55 million daily reported crime incidents across the United States, crime is proposed as a measure of psychological well-being. The evidence suggests that stock returns affect the well-being of not only investors but also noninvestors. Specifically, a contemporaneous negative (positive) relationship between daily stock market returns and violent crime rates is found for investors (noninvestors). A similar relationship is also found between local earnings surprises and violent crime. The contrasting relationships for investors and noninvestors suggests that relative wealth may influence well-being.

Predict Stock Price Trend by Using Classification Model

The stock market is changing daily and people are paying more and more attention to stocks. After the establishment of the stock market, the research on stocks has become more and more influential. The core of researching stock is the stock future price trend, bullish or bearish. In order to predict stock information in simple and efficient ways, this paper aims to predict stock rise or fall by using classification model with better performance index and strong operability. Firstly, the paper acquires Maotai Corporations daily stock data from tushare package. To define the label up and down, the paper compares the daily closing price with its yesterday price. If it is positive, it is recorded as up; if it is negative, it is recorded as down. The random forest, logistic regression and SVM models are established respectively. The best model was selected by comparing three models evaluation scores. The results show that logistic regression is better than the other two models in predicting the rise and fall of stocks. This study can promote the cross integration of financial field and technical level and provide new ideas for future stock investment.

A novel Deep Reinforcement Learning based automated stock trading system using cascaded LSTM networks

Deep Reinforcement Learning (DRL) algorithms have been increasingly used to construct stock trading strategies, but they often face performance challenges when applied to financial data with low signal-to-noise ratios and unevenness, as these methods were originally designed for the gaming community. To address this issue, we propose a DRL-based stock trading system that leverages Cascaded Long Short-Term Memory (CLSTM-PPO Model) to capture the hidden information in the daily stock data. Our model adopts a cascaded structure with two stages of carefully designed deep LSTM networks: it uses one LSTM to extract the time-series features from a sequence of daily stock data in the first stage, and then the features extracted are fed to the agent in the reinforcement learning algorithm for training, while the actor and the critic in the agent also use a LSTM network. We conduct experiments on stock market datasets from four major indices: the Dow Jones Industrial index (DJI) in the US, the Shanghai Stock Exchange 50 (SSE50) in China, S&P BSE Sensex Index (SENSEX) in India, and the Financial Times Stock Exchange 100 (FTSE100) in the UK. We compare our model with several benchmark models, including: (i) a model based on a buy-and-hold strategy; (ii) a Proximal Policy Optimization (PPO) model with Multilayer Perceptron (MLP) policy; (iii) some up-to-date models like the MLP model, LSTM model, Light Gradient Boosting Machine (LGBM) model, and histogram-based gradient boosting model; and (iv) an ensemble strategy model. The experimental results show that our model outperforms the baseline models in several key metrics, such as cumulative returns, maximum earning rate, and average profitability per trade. The improvements range from 5% to 52%, depending on the metric and the stock index. This indicates that our proposed method is a promising way to build an automated stock trading system.

Sensitivity Analysis Based on Portfolio Option Models Using Tesla and Nio as Examples

The electric vehicle (EV) industry is undergoing a significant transformation, driven by environmental concerns, advancements in battery technology, and changing consumer preferences. Companies like Tesla and China's NIO are at the forefront of this revolution, showcasing the global potential of EVs. This study undertook a sensitivity analysis of these two leading EV manufacturers, Tesla and NIO, to understand the dynamics of their stock prices and implications for investment strategies. Data was meticulously collected from various financial databases to capture daily stock prices, which were then used to compute monthly returns. The study also delved into options, focusing on the strike prices and volatility of Tesla and NIO options. Using a combination of stock prices, strike prices, and volatility, the intrinsic and time value of these options were analyzed. The research employed a composite option model to describe the price variation of an option, considering factors like asset price volatility, risk-free rate, and dividend yield. The findings revealed that stock prices and option prices exhibited certain sensitivities to market variables. For instance, Tesla's option prices showed an upward trend with rising stock prices, while NIO's option prices displayed varied responses to stock price changes. The study underscores the importance of understanding these sensitivities for informed investment decisions in the evolving EV market.

An effective approach for predicting daily stock trading decisions using fuzzy inference systems

An effective approach for predicting daily stock trading decisions using fuzzy inference systems

Impact of Price Indexes on Stock Market Prices of Banks in Financial Crises

During times of crises, stock markets often experience heightened volatility, and the banking sector is particularly susceptible. This study aims to investigate the impact of index values on the daily closing prices of five banks during five major financial crises in recent decades, using logistic regression analyses. The results show that in five crisis periods, different indexes have a significant impact on the daily stock price of banks. Although there is no pattern found for different crisis periods because each bank has different investment instruments, the index, ind38- CFMRC (VWI) Over $2, seems to have a highly significant impact on the crisis periods I-IV and ind37- CFMRC (DEWI) Over $2 plays a significant role in predicting the outcomes. The findings indicate that banks should give particular focus to their investment instruments, particularly value-weighted indexes (VWI) over $2 and equal-weighted indexes (DEWI) over $2 when any indications of a crisis arise. This is crucial because these index values influence the daily closing prices of banks and could potentially contribute to economic crises. Moreover, larger banks are more sensitive to changes in the index values than smaller banks, attributed to variations in their investment amounts.

Social media investors' sentiment as stock market performance predictor

PurposeThis study examines the impact of social media investor sentiment on the stock market performance through qualitative and quantitative proxies.Design/methodology/approachThe authors use a sample of daily stock performance related to S&P 500 Index for the period from December 18, 2017, to December 18, 2018. The social media investor sentiment was assessed through qualitative and quantitative proxies. For qualitative proxies, the study relies on three social media resources”: Twitter, Trump Twitter account and StockTwits. The authors proposed 3 methods to reflect investor sentiment. For quantitative proxies, the number of daily messages published from Trump Twitter account and StockTwits is considered as a signal of investor sentiment. For regression model, the study adopts the autoregressive distributed lagged to determine the relationships between the nonstationary series.Findings:Empirical findings provide evidence that quantitative measures of investor sentiment have significant effects on S&P’500 performances. The authors find that Trump's tweets should be interpreted with caution. The results also show that the number of Trump's tweets on t−1 day have a positive effect on performance on day t.Practical implicationsSocial media sentiment contains information for predicting stock returns and transaction activity. Since, the arrival of new information in capital markets triggers investor sentiment on social media.Originality/valueThis study investigates the investors’ sentiment through social media and explores quantitative and qualitative measures. The amount of information on social media reflects more the investor sentiment than content analysis measures.Peer reviewThe peer review history for this article is available at: https://publons.com/publon/10.1108/IJSE-12-2022-0818

Winners and Losers From Trade Agreements: Stock Market Reactions to TPP and TTIP

Which companies gain and which companies lose from trade agreements? In contrast to a view that sees the largest companies as the main beneficiaries of trade agreements, we argue that medium-sized companies gain the most from them. Moreover, we examine whether more capital-intensive and more diversified companies benefit more than other firms. Our empirical test relies on a dataset with daily firm-level stock price data for close to 4,000 US companies over the period 2009–2016. Concretely, we assess how the shares of different types of firms reacted to the news on the (lack of) progress of the negotiations aimed at concluding the TPP and TTIP. We find support for the view that medium-sized and diversified companies win the most from trade agreements. Besides speaking to the literature on the distributional effects of trade agreements, the article contributes to recent research on the role of firms in the international political economy and the stock market consequences of political events. It also presents a novel approach to measuring progress and stagnation in international trade negotiations using computational text analysis.