Stock Market Movements Research Articles

Tweets analytics for directional prediction of stock market movement: a short window event study

Tweets analytics for directional prediction of stock market movement: a short window event study

The Impact of Big Data Analytics on Stock Price Prediction in the Bangladesh Stock Market: A Machine Learning Approach

The stock market is a volatile and complex environment impacted by various unpredictable factors, making accurate stock price prediction challenging. This research paper explored the potential and capability of big data analytics and machine learning techniques in terms of enhancing stock price prediction accuracy in the setting of the Bangladesh stock market. The methodology adopted in the study entailed a data gathering process, which comprised collecting financial data from the Bangladesh stock market, such as news articles, financial statements, macroeconomic indicators, and historical stock prices. Based on a literature review, various fundamental and technical indicators are chosen as predictive features. The research paper employed a combined methodology that consolidates technical calculations and sentimental analysis to predict and forecast stock market patterns. By adopting machine learning and sentiment analysis techniques, this technique provides future predictions for the stock market while considering the impact of political events, economic factors, and dynamics in social media. The consolidation of big data analytics enables real-time predictions of stock market movements. The sentiment analysis algorithm facilitates prompt and extensive evaluations of tweets and news articles. As a result, the integration of technical and sentiment analyses greatly enhances the accuracy of stock market predictions.

Stock Price Prediction Using Twitter Dataset

In this paper, we apply sentiment analysis and machine learning principles to find the correlation between ”public sentiment” and ”market sentiment”. We use twitter data to predict public mood and use the predicted mood and previous days’ DJIA values to predict the stock market movements. In order to test our results, we propose a new cross validation method for financial data and obtain 75.56% accuracy using Self Organizing Fuzzy Neural Networks (SOFNN) on the Twitter feeds and DJIA values from the period June 2009 to December 2009. We also implement a naive protfolio management strategy based on our predicted values. Our work is based on Bollen et al’s famous paper which predicted the same with 87% accuracy.

Tweets analytics for directional prediction of stock market movement: a short window event study

Tweets analytics for directional prediction of stock market movement: a short window event study

Household willingness to take financial risk: Stockmarket movements and life‐cycle effects

Using panel data on Australian households, the relationship between risk tolerance and past stock returns is investigated across economic and financial cycles, as well as over the life-cycle and across generations. Risk tolerance is found to be procyclical with stock returns over an eight year horizon. The empirical results also reveal an inverted J-curve age risk profile, and the presence of a longer cycle across generations. Results are robust to controlling for financial crises, return volatility, real estate returns and home bias.

Improving the Process of Early-Warning Detection and Identifying the Most Affected Markets: Evidence from Subprime Mortgage Crisis and COVID-19 Outbreak-Application to American Stock Markets.

Stock-market-crash predictability is of particular interest in the field of financial time-series analysis. Famous examples of major stock-market crashes are the real-estate bubble in 2008 and COVID-19 in 2020. Several studies have studied the prediction process without taking into consideration which markets might be falling into a crisis. To this end, a combination analysis is utilized in this manuscript. Firstly, the auto-regressive estimation (ARE) algorithm is successfully applied to electroencephalography (EEG) brain data for detecting diseases. The ARE algorithm is employed based on state-space modelling, which applies the expectation-maximization algorithm and Kalman filter. This manuscript introduces its application, for the first time, to stock-market data. For this purpose, a time-evolving interaction surface is constructed to observe the change in the surface topology. This enables tracking of the stock market's behavior over time and differentiates between different states. This provides a deep understanding of the underlying system behavior before, during, and after a crisis. Different patterns of the stock-market movements are recognized, providing novel information regarding detecting an early-warning sign. Secondly, a Granger-causality time-domain technique, called directed partial correlation, is employed to infer the underlying interconnectivity structure among markets. This information is crucial for investors and market players, enabling them to differentiate between those markets which will fall in a catastrophic loss, and those which will not. Consequently, they can make successful decisions towards selecting less risky portfolios, which guarantees lower losses. The results showed the effectiveness of the use of this methodology in the framework of the process of early-warning detection.

A sentiment analysis approach to the prediction of market volatility.

Prediction and quantification of future volatility and returns play an important role in financial modeling, both in portfolio optimisation and risk management. Natural language processing today allows one to process news and social media comments to detect signals of investors' confidence. We have explored the relationship between sentiment extracted from financial news and tweets and FTSE100 movements. We investigated the strength of the correlation between sentiment measures on a given day and market volatility and returns observed the next day. We found that there is evidence of correlation between sentiment and stock market movements. Moreover, the sentiment captured from news headlines could be used as a signal to predict market returns; we also found that the same does not apply for volatility. However, for the sentiment found in Twitter comments we obtained, in a surprising finding, a correlation coefficient of -0.7 (p < 0.05), which indicates a strong negative correlation between negative sentiment captured from the tweets on a given day and the volatility observed the next day. It is important to keep in mind that stock volatility rises greatly when the market collapses but not symmetrically so when it goes up (the so-called leverage effect). We developed an accurate classifier for the prediction of market volatility in response to the arrival of new information by deploying topic modeling, based on Latent Dirichlet Allocation, in order to extract feature vectors from a collection of tweets and financial news. The obtained features were used as additional input to the classifier. Thanks to the combination of sentiment and topic modeling even on modest (essentially personal) architecture our classifier achieved a directional prediction accuracy for volatility of 63%.

A trans-national comparison of stock market movements and related social media chatter during the COVID-19 pandemic

ABSTRACT The outbreak of the SARS-CoV-2 (COVID-19) pandemic first identified in 2019 has had long-term ramifications across global financial markets. We have seen stock markets across countries falling to historical lows and then recovering back during the pandemic. Prior research has established that human emotions can significantly influence financial markets. In particular, social media discussions or online Word-of-mouth (OWoM) minutely reflect public emotions and opinions associated with global market volatility. In this study, we use a quantitative approach to explore the relationship between discussions in twitter, a popular micro-blogging online platform and stock market performance across different countries, in order to understand the disaster-triggered behavioural responses of common investors across the globe. We analyse the association of national stock-indices, sentiment polarity and discussion subjectivity in Covid-19-related tweets originating in India, US, Italy, UK, Australia, Nigeria and South Africa during February 2020– January 2021 period. Using a combination of multiple analytics methods, our study examines: (i) linear and lagged association between OWoM and market performance; and (ii) heterogeneity in the OWoM-market relationship across the seven countries. Our results show weak but statistically significant correlation between OWoM subjectivity and polarity and stock market returns across countries. Our findings also show differential temporal association of OWoM and market returns across countries. Our study shows stock market connectedness between pairs of countries, some simultaneously varying while others varying with a time lag, and the strength of such connectedness increases during global disasters such as the COVID-19 pandemic.

A Bibliometric Analysis of Artificial Intelligence-Based Stock Market Prediction

The primary purpose of this study is to conduct a scientometrics analysis of stock market forecasts based on artificial intelligence. This research examined 1,301 publications that were published between January 2002 and June 2022. We investigated 183 journal articles among 1,329 papers. In addition to entering the keywords into Scopus, a comprehensive dataset of relevant research papers was compiled. These papers discussed the optimization of investment portfolios, artificial intelligence-based stock market forecasts, investor emotions, and market monitoring. We found the most prolific documents by affiliation, the most prolific author, the most cited papers, nations, institutions, co-authorship maps, inter-country co-authorship maps, and keywords occurrences in this study. Co-authorship analysis network maps and keyword occurrence linkages are generated using the VOS-viewer software. According to our findings, it is evident from the review that the body of literature is becoming more specific and extensive. Primarily, neural networks, support vector machines, and neuro-fuzzy systems are employed to predict the future price of a stock market index based on the composite index's historical prices. Artificial intelligence techniques are able to consider challenges facing financial systems when forecasting time series. Our findings provide actionable guidance on how artificial intelligence can be used to predict stock market movements for market participants, including traders, investors, and financial institutions.

Are Twitter sentiments during COVID-19 pandemic a critical determinant to predict stock market movements? A machine learning approach

The problem of stock market prediction is a challenging task owing to its complex nature and the numerous indirect factors at play. The sentiments regarding socio-political issues such as wars and pandemics can affect stock prices. The spread of the COVID-19 pandemic continues to take a toll on the economy and fluctuations in sentiment of the concerns about the health impacts of the disease can be captured from the microblogging platform, Twitter. We examined how these sentiments during the Covid-19 pandemic and the health impacts arising from the disease along with other macroeconomic indicators provide useful information to predict the stock indices in a more accurate manner. We developed a machine learning model namely, long-short term memory (LSTM) networks to predict the impact of the Covid-19 induced sentiments on the stock values of different sectors in the United States and India. We did the same predictions using the timeseries statistical models such as autoregressive moving average model and the linear regression model. We then compared the performance of the LSTM and the timeseries statistical models to find that the machine learning model has produced more accurate predictions of the stock indices. The performance of the models across the sectors and between the United States and India are compared to draw economic inferences.

Effect Of Inflation, Exchange Rates, And Trading Volume Activity On Stock Price Indices During The Covid-19 Pandemic On Companies In The Basic Industry And Chemical Sectors

Covid-19 has an impact on the economy, where ADB decreased with estimates in Asian Developing Countries by 3.0 ppts to 2.2%, and for ASEAN by 3.7 ppts to 1.0% (ASEAN, 2020). In addition, one of the indicators that shows that the occurrence of stock market movements, can be seen through the country's stock price index. The Composite Stock Price Index (JCI), which is one of the benchmarks for the Indonesian stock market, on March 5, 2020 was at 5,638.13 and experienced a low on March 24, 2020 at 3,937.63. This study aims to determine the effect of inflation, exchange rate, and TVA on the stock price index in the basic and chemical industry sectors, which in this case uses data in the period January 2020 -June 2022, namely the period where the stock price index of the basic industry and chemical sectors shows a downward trend in April 2020 and November 2020. The sampling technique used in this study was purposive sampling samples so that 64 Companies in the Basic and Chemical Industries Sector were obtained listed on the IDX. The data analysis technique used in this study uses descriptive statistical analysis to describe the data that has been collected. The results of the study for the F test showed that inflation, exchange rates and TVA had a positive and significant effect on the stock price index. While the results of the t-test show that inflation has a positive and insignificant effect, the exchange rate has a positive and significant effect on the stock price index, and TVA has a negative and insignificant effect on the stock price index.

Nonlinear relationship between monetary policy and stock returns: Evidence from the U.S.

This paper studies the relationship between monetary policy and stock market return in the U.S. using nonlinear econometric models. It first employs a univariate Markov-switching model on each of the three stock indices and three monetary policy variables, displaying significant regime-switching patterns and common movements. This paper then uses a Markov-switching dynamic bi-factor model to simultaneously extract two latent common factors from stock indices and monetary policy variables to represent monetary policy changes and stock market movements separately. The smoothed probabilities of regimes demonstrate that expansionary monetary policy regimes follow economic recessions, but bear stock markets usually occur before economic recessions. The maximum likelihood estimation results show that expansionary monetary policy such as a decrease in the federal funds rate raises stock returns, but stock returns don't directly influence monetary policy decision.

Discovering the drivers of stock market volatility in a data-rich world

This study comprehensively examines the economic and financial drivers of volatility changes in terms of a cross-country perspective. We review a wide range of studies related to financial volatility forecasting and collect a diverse set of prediction variables. By analyzing them within a unified framework, we find that only a small number of variables contain significant predictive information. Most of all, we discover that among various global market indicators, Chinese stock market movements significantly predict U.S. stock market volatility. Further analyses provide evidence of the effect of Chinese stock market movements on the U.S. stock market.

On the Impact of News for Reliable Stock Market Predictions: An LSTM-based Ensemble using FinBERT Word-Embeddings

Stock market (SM) prediction methods can be divided into two categories based on the number of information sources used: single-source methods and dual-source approaches. To estimate the price of a stock, single-source approaches rely solely on numerical data. The Efficient Market Hypothesis (EMH), [1]. States that the stock price will represent all important information. Different sources of information might complement one another and influence the stock price. Machine learning and deep learning techniques have long been used to anticipate stock market movements, [2], [3]. The researcher gathered the dataset, [4], [5], [6], [7]. The dataset contains the date of the reading, the opening price, the high and low value of the stock, news about the stock, and the volume. The researcher uses a variety of machine Learning and deep learning approaches to compare performance and prediction error rates, in addition, the researcher also compared the effect of adding the news text as a feature and as a label model. and using a dedicated model for news sentiment analysis by applying the FinBERT word embedding and using them to construct a Long Short-Term Memory (LSTM). From our observation, it is evident that Deep learning-based models performed better than their Machine learning counterparts. The author shows that information extracted from news sources is better at predicting rather than its direction of price movement. And the best-performing model without news is the LSTM with an RMSE of 0.0259 while the best-performing model with news is the LSTM with a stand-alone and LSTM model for news yields RMSE of 0.0220.

Design Analysis and Implementation of Stock Market Forecasting System using Improved Soft Computing Technique

In this paper, a stock market prediction model was created utilizing artificial neural networks. Many people nowadays are attempting to predict future trends in bonds, currencies, equities, and stock markets. It is quite challenging for a capitalist and an industry to forecast changes in stock market prices. Due to the numerous economic, political, and psychological aspects at play, forecasting future value changes on the stock markets is quite challenging. In addition, stock market forecasting is a difficult endeavor because it relies on a wide range of known and unknown variables. Many approaches, including technical analysis, fundamental analysis, time series analysis, and statistical analysis are used to attempt to predict the share price; however, none of these methods has been demonstrated to be a consistently effective prediction tool. Artificial neural networks (ANNs), a subfield of artificial intelligence, are one of the most modern and promising methods for resolving financial issues, such as categorizing corporate bonds and anticipating stock market indexes and bankruptcy (AI). Artificial neural networks (ANN) are a prominent technology used to forecast the future of the stock market. In order to understand financial time series, it is often essential to extract relevant information from enormous data sets using artificial neural networks. An outcome prediction neural network with three layers is trained using the back propagation method. Analysis shows that ANN outperforms every other prediction technique now available to academics in terms of stock market price predictions. It is concluded that ANN is a useful technique for predicting stock market movements globally.

TRADING BEHAVIOUR OF FOREIGN INSTITUTIONAL INVESTORS IN INDIA: AN EMPIRICAL STUDY

The study is about the investment behaviour of “Foreign Institutional Investors” (FII) in the Indian stock market w.r.t their trading behaviour and its impact on stock market movements. We have collected the daily data of investment of FII net equity investments and NIFTY 50 index in Indian stock markets for a long time period from the year 2000 to 2022. The paper used trend analysis and the relationship between FII net equity investments and NIFTY 50 index. The paper found a significant relationship and causality in the direction of NIFTY to FII investments. The FII are found to invest with consistency in the Indian stock market and are also responsible to contribute significantly to the development of the Indian stock market.

Empirical Analysis of the Relationship of Stock Market, Exchange Rate, CDS Spreads and VIX Index in Turkey

Küresel entegrasyon süreçlerinin hız kazanmasıyla yaşanan krizlerin yapısındaki ortak noktanın genel olarak ülke risk primindeki artışlar veya büyük açık ekonomilerde ortaya çıkan oynaklıkların olduğu görülmektedir. Bu çalışmanın amacı Türkiye’de borsa endeksi, döviz kuru, risk primi (CDS) ve korku endeksi (VIX) arasındaki ilişkileri incelemektir. Bunun için ARDL sınır testinden yararlanılmıştır. Analiz dönemi olarak hem veri bulunabilirliği açısından hem de Türkiye ekonomisi için yapısal bir dönüm noktası olan Şubat 2001 sonrası dönem kullanılmıştır. Literatürden farklı olarak hem ülke risk primini temsil eden CDS primi, hem de yurtdışı risk alma iştahını ve dolayısıyla yurtdışı konjonktürü yansıtan VIX endeksi aynı modelde kullanılmıştır. Bu şekilde CDS ve VIX göstergelerinin aynı modelde kullanılması sonucunda borsa endeksi üzerindeki etkilerinin aynı düzeyde olup olmadığı sorusuna ışık tutulmaya çalışılmıştır. Elde edilen ampirik bulgulara göre Türkiye’de borsa endeksini döviz kuru, CDS primi ve VIX endeksi etkilemektedir. Küresel piyasalara entegre bir ülke olan Türkiye’de bu sonucun beklentiler dahilinde düşünülmektedir. Yani döviz kuru, ülke risk primi ve yurtdışı risk alma iştahında meydana gelen değişimlerin borsa hareketleri üzerinde etkisi bulunmaktadır. Sonuçlarımız, küresel risk alma iştahını temsilen VIX endeksine kıyasla ülke riskini temsil eden CDS priminin BİST 100 için önemli bir gösterge olduğunu göstermektedir. Bu durumda hisse senedi piyasalarında incelenen değişkenlerin önemini öne çıkarmaktadır.

Text representation for direction prediction of share market

Financial news articles are textual sources that report on economic events which affect the stock market. News articles published when the stock market is open, influence the movement of the stock market indices. An implicit relationship exists between different economic events that eventually influence the stock market movement. This paper studies the relationship between news articles and the direction of close price movement of the stock market. It explores the effectiveness of different statistical and deep learning-based classifiers that use price features or text features as input to predict the direction of close price movement. Further, this paper proposes a parallel CNN model which combines text representation and price representation to predict the direction of close price movement. The proposed model gives high accuracy, and the normalized cross-correlation scores show that the predicted and actual time series are strongly correlated. These metrics indicate that economic events in news articles were effectively harnessed to predict the close price movement.

A STUDY ON THE STOCK MARKET INVESTMENT DECISIONS OF CORPORATE EMPLOYEES WITH RESPECT TO BENGALURU

The following study aims to examine the influencing factors which are affecting corporate investor behaviour in the stock market and it is trying to find out perception of corporate investors regarding various considerations kept in mind while investing in the stock market .Analysis of stock market movements is very important for investor; therefore it attracts many scholars to conduct research. The investment behaviour seems very challenging; this behaviour is due to different factors like condition of financial statement, current economic indicator, history and futuristic data, the result of technical analysis, internal and external influence. It is important for the corporate investors to keep themselves up to date and financially literate about the stock market and it’s affecting factors. This study used primary data which is collected from 150 corporate investors through structured questionnaire to measure the behaviour of investment decision. Through convenient sampling the data was collected from respondents. The Annova and chi square tools were used to examine the corporate investor’s behavioural intentions with financial considerations in the stock market investment. The result of this study shows that investor simply react to the available information and act accordingly. Lot of consideration is required to deal with before, after and while investing in the stock market. Investor should try to make financial analysis and influencing factor analysis before investing on any shares and they must look into all avenues while investing into different shares. Consideration of influencing factors is sector specific and it helps in understanding the investment behaviour. Technical and financial analysis about the company and fundamental analysis of the economy is taken into account while investing in the stock market. Investment in stock market has high risk compared to other financial instruments. Therefore this study has significant implication on policymakers, Stock market regulators and financial service providers. KEYWORDS: Stock Market, Shareholder, Stocks or shares, Portfolio, dividend.

Generalized durative event detection on social media.

Given the recent availability of large volumes of social media discussions, finding temporal unusual phenomena, which can be called events, from such data is of great interest. Previous works on social media event detection either assume a specific type of event, or assume certain behavior of observed variables. In this paper, we propose a general method for event detection on social media that makes few assumptions. The main assumption we make is that when an event occurs, affected semantic aspects will behave differently from their usual behavior, for a sustained period. We generalize the representation of time units based on word embeddings of social media text, and propose an algorithm to detect durative events in time series in a general sense. In addition, we also provide an incremental version of the algorithm for the purpose of real-time detection. We test our approaches on synthetic data and two real-world tasks. With the synthetic dataset, we compare the performance of retrospective and incremental versions of the algorithm. In the first real-world task, we use a novel setting to test if our method and baseline methods can exhaustively catch all real-world news in the test period. The evaluation results show that when the event is quite unusual with regard to the base social media discussion, it can be captured more effectively with our method. In the second real-world task, we use the event captured to help improve the accuracy of stock market movement prediction. We show that our event-based approach has a clear advantage compared to other ways of adding social media information.