Stock Market Analysis Research Articles

Prediction of stock return by LSTM neural network

ABSTRACT The role of the stock market in the whole financial market is indispensable. How to obtain the actual trading income and maximize the interests in the trading process has been a problem studied by scholars and financial practitioners for a long time. Deep learning network can extract features from a large number of original data, which has potential advantages for stock market prediction. Based on the Shanghai and Shenzhen stock markets from 2019 to 2021, we use LSTM models, optimized on in-sample period and tested on out-of-sample period, using rolling window approach. We select the right hyperparameters at the beginning of our tests, use RBM preprocessing data, then use LSTM model to obtain expected stock return, to effectively predict future stock market analysis and predictive behavior. Finally, we perform a sensitivity analysis of the main parameters and hyperparameters of the model.

What drives stock market participation? The role of institutional, traditional, and behavioral factors

We analyze stock market participation in 19 European countries, providing a composite view of the interplay and relative importance of established participation drivers. We jointly control for nearly all relevant drivers found in prior studies, which tend to introduce one novel variable at a time and often omit risk-aversion. Excellent full model predictive power decomposes into institutional (country) fixed effects (about 30% of total), traditional individual-level variables (50%), and more recently identified behavioral variables (20%). We sketch a hierarchical framework where factors’ effects vary by agents’ proneness to participate. We also challenge and complement existing interpretations given to sociability, IQ, trust, and life experiences.

A Review on Sentiment Analysis in Reinforcement Learning Model for Stock Market Analysis

Sentiment analysis is a natural language processing approach that is widely implemented for many natural language processing applications such as translation, chatbots, and more. In this paper, news sentiment analysis in the stock market was reviewed. Stock market sentiment fluctuates because of events such as the reporting of quarterly financial report, macroeconomic data, government policy, etc. Traders use sentiment analysis to predict stock prices and trends. In recent years, sentiment analysis has been embedded into reinforcement learning for building an algorithmic trading system. This paper is a review paper to analyze and summarize sentiment analysis in reinforcement learning models. Specifically, the paper reviews the data, features, and approaches used in sentiment analysis. To identify the relevant journals and articles, a methodology is applied to review the sentiment analysis in the stock market. These studies are categorized according to their general similarities, differences, limitations, and field to be investigated further. Finally, the last section is the conclusion, which provides the direction for future study.

Institutional Market Analysis in Stock Market

Abstract: A stock market, equity market, or share market is the aggregation of buyers and sellers of stocks (also called shares), which represent ownership claims on businesses. In stock market analysis we are trying to predict the price of given share or stock The result was achieved at the end of this project was quite impressive as model was able to predict the trend successfully, it was not 100% accurate but considering that model it predicted only on the basis of past data is quite impressive. All these things we are able to do with help of machine learning.

Competitiveness of Human and Business in Terms of Stock Market Analysis

The competitiveness of modern human and business are inextricably linked with the work of the stock market. In some cases, easily could be detected a correlation between trends or tendencies of the stock market and the directions of transformation of human behavior. What should people and businesses be like to maintain this competitiveness at the proper level? According to the authors, it is the developed stock market as instrument of modern society that provides the answer to this question. Through the analysis of stock markets tendencies, this research aims to find evidence that confirm the new characteristics of human life in the fields of education, healthcare, communication, commerce, and interaction with virtuality. Most researchers focus separately on the study of human behavior and the functioning of the stock market. We analyze the relation between both dimensions, assuming that the stock market can be considered, for developed countries, through the small investors voting as public preferences and goals reflection. Evidence from statistical analysis of the stock market confirmed the following characteristics of modern human: faster dissemination of knowledge, e-commerce acceleration, influencing interpenetration of the Internet communications, in depth virtualization, and accelerated circulation of information flows. Operating within such flows of change allows people and businesses to remain competitive at the appropriate level.

Time Series Analysis and Some Applications in Medical Research

Time series have applications in many fields. Time Series Analysis is used for many applications, such as economic forecasting, sales forecasting, budgetary analysis, stock market analysis, yield projections, process and quality control, etc. In this study, we examined the applications of time series in the field of health. We gave some examples of applications in the field of health. We mentioned that many more studies could be done in the field of health with time series analysis. In this paper, we reviewed recent works and present a summary and a brief theoretical introduction to time series ARIMA modeling. We have seen that this model is the most widely used method in research in the field of health. As a result, time series analysis, a statistical technique that may be appropriate when data are measured repeatedly and at nearly equal intervals of time, has potential research applications in the study of chronic diseases such as diabetes, hypertension, and herpes simplex. We believe that this study will guide researchers working in this field in their research.

Reaksi pasar saham atas peristiwa disahkannya Omnibus Law RUU Cipta Kerja

This research aims to analyze stock market reaction on the legalization of Omnibus Law the Job Creation Act on October 5, 2020. The market reaction is measured using abnormal return, average abnormal return and trading volume activity which happens in manufacturing company consumer goods sector food and beverage sub sector listed on the Indonesia Stock Exchange. The research sample is determined by using non probability sampling method with purposive sampling technique. Hypothesis testing used one sample t-test and wilcoxon signed rank test in which the observation period is 15 days using SPSS tools. The results of the hypothesis testing show that there is a significant abnormal return on the 3rd day dan 7th day after the Job Creation Act legalization. There is no significant difference in the average abnormal return between the period before and after the Job Creation Act legalization. There is no significant difference in the trading volume activity between the period before and after the Job Creation Act legalization.

DEEP LEARNING AND MACHINE LEARNING MODELS TO FORECAST BSE AND NIFTY SENSEX IT INDEX

The primary objective of this work is to build an appropriate mathematical model that helps predict the direction of stock market indices. The stock market is volatile and dynamic, and prediction of its movement will help investors make more optimal strategies and boost their profit. In this context, the data was collected from two major IT indices of India, the BSE IT Index and the NIFTY IT Index. In modeling the time series, autoregressive integrated moving average (ARIMA) was used initially, followed by various machine learning models, like artificial neural network (ANN), recurrent neural network (RNN), and convolutional neural network (CNN). The data analysis exhibited superior performance of ANN models compared to other models for performance criteria such as root mean squared error (RMSE) and mean absolute percentage error (MAPE). This exploratory analysis concluded that ANN models outperform other predicting models to greater accuracy, augmenting previous literature on stock market analysis. This machine learning approach would help investors design optimal strategies and boost their profits in the world of stock market.

DeeBERT-S3WD: Three-Way Multigranularity Decision for Interactive Information Sentiment Analysis Research

Interactive information between listed companies and investors is an emerging form of information disclosure in the stock market and has a crucial impact on stock market analysis. Interactive information interferes with investors’ decision-making by influencing their sentiments, significantly affecting the stock market’s health. Due to the unique nature of interactive information, the existing approaches to dynamic interactive information sentiment analysis rarely consider a multistep study under the tradeoff of cost and accuracy. To address this problem, we propose a novel unified framework combining DeeBERT with the sequential three-way decision based on the early exiting mechanism and continually mining uncertain regions for interactive information sentiment analysis. Specifically, we treat the question-answer pair interaction information as an entire sample and leverage DeeBERT to allow the samples to exit early without traversing through all the Transformer layers. Subsequently, the uncertain samples are selected at each Transformer layer to be reinvestigated at the next granularity of time-evolving data. Besides, we utilize a manual modification method to assign the determined samples to training sets to update the model. Lastly, a series of comparative experiments demonstrate that our proposed model has outstanding performance in terms of time efficiency and interactive information sentiment index.

Impact of Brexit news on the stock prices of european insurance companies: an event study approach based on indexation and sub-indexation

The Brexit referendum in June 2016 led to different publications analysing stock market reactions. This study addresses a research gap, regarding the consideration of other Brexit events and the focus on stock prices of European insurance companies, by using a further refined event study approach based on indexation and sub-indexation. In scope are 17 listed insurance companies based in the European Union or the United Kingdom represented by the Insurance Index. To analyse potential dependencies between abnormal returns and the location of the company (European Union or United Kingdom) or the share of insurance business written in the United Kingdom, the Insurance Index is divided into four sub-indices. The results show significant positive or negative abnormal returns of the Insurance Index. In addition, the sub-indices react differently to the events under consideration. Trends are suggesting that significant abnormal returns may depend on the location and the share of insurance business written in the United Kingdom.

ANALYSIS OF STOCK MARKET REACTION TO LARGESCALE SOCIAL RESTRICTIONS POLICY ANNOUNCEMENT

This study aims to analyze stock market reactions to large-scalesocial restrictions policy implementation announcements. Themethod used is event study. This study used 7, 5, and 3 daysevent window and 120 days estimation window for calculatingabnormal return. The samples of this study are 32 companies inthe tourism, hotel, and restaurant sub-sector listed in IndonesiaStock Market which were determined by purposive samplingmethod. The results of this study indicate that 1) there was nosignificant negative market reaction indicated by negative andinsignificant average abnormal return and accumulation averageabnormal return around the announcement date of the Large-ScaleSocial Restrictions (PSBB) policy implementation which meansthat the market does not react to the event and 2) there was nosignificant difference in average abnormal return before and afterthe announcement of the Large-Scale Social Restrictions (PSBB)policy implementation.

Investor attention and reaction in COVID-19 crisis: sentiment analysis in the Indian stock market

PurposeThis paper aims to investigate the influence of attention and sentiment in the Indian stock market during the unusual COVID-19 crisis in the first and second waves of the pandemic.Design/methodology/approachIn this study, the capital asset pricing model (CAPM) is used to estimate the expected return. The autoregressive distributed lag (ARDL) model with optimal lag value selection and Granger causality using the vector autoregressive (VAR) estimation model were applied to find out whether there is a causal relationship between investors' attention and sentiment that influence stock returns across 14 sectors.FindingsThe results show that increased attention to COVID-19 substantially varied in the first wave and second wave market reactions. The upsurge attention of COVID-19 shows a negative influence with lower expected returns in the second wave. The sentiment of investors contrasts from the lower expected return in the first wave to the higher expected return in the second wave of the pandemic. Moreover, investors’ sentiment in a state of fear is associated with lower returns.Originality/valueThe authors capture sentiment based on attention and investors mood using novel data set during the COVID-19 pandemic shock. The study is among a few which take a comprehensive stock market response during initial and subsequent waves across sector returns.

The Impact of Leverage and Marginal Expected Shortfall on Systematic Risk -- Based on the Analysis of China's Stock Market

In recent years, the systemic risks of China's stock market has broken out frequently. Many scholars believe that leverage is an important factor that affects systemic risk. Based on Acharya(2010)，this paper studies the relationship between leverage, Marginal Expected Shortfall and Systemic Expected Shortfall of stocks in China under the background of the global financial crisis in 2008, the COVID-19 epidemic in 2020 and the Federal Reserve's interest rate hike as well as the Russia-Ukraine conflict in 2022 respectively. The results show that: in the global financial crisis in 2008, and under the Russia-Ukraine conflict as well as Federal Reserve's interest rate hike in 2022, stocks with higher leverage and higher Marginal Expectation Shortfall will have greater Systemic Expected Shortfall; However, due to "supply-side reform" and "deleveraging", the effect was not significant under the COVID-19 epidemic in 2020. In addition, the manufacturing industry has performed significant heterogeneity under the two shocks in 2020 and 2022.

A Random-Matrix-Theory-Based Analysis of the Brazilian Stock Market During the 2008 Financial Crisis and Asian Crisis and Temporal Neighborhoods

Several approaches and concepts of physics, such as Random Matrix Theory, have been used to investigate the complexity of financial time series. This study aims to analyze the spectrum of stock correlation in the Brazilian stock market by applying Random Matrix Theory to the subprime and Asian financial crisis periods and their temporal neighborhoods. Results show evident synchronized market behavior during both crises. The results also show that the period preceding a crisis presents symptoms which may predict future crises. Thereby, the methodology presented here could be used by the market as a tool that helps to anticipate possible market fluctuations.

Predicting Stock Market Volatility from Candlestick Charts: A Multiple Attention Mechanism Graph Neural Network Approach

As an important part of financial market, stock market price volatility analysis has been the focus of academic and industry attention. Candlestick chart, as the most widely used indicator for evaluating stock market price volatility, has been intensively studied and explored. With the continuous development of computer technology, the stock market analysis method based on candlestick chart is gradually changed from manual to intelligent algorithm. However, how to effectively use stock market graphical indicators to analyze stock market price fluctuations has been pending solution, and deep learning algorithms based on structured data such as deep neural networks (DNN) and recurrent neural networks (RNNs) always have the problems of making it difficult to capture the laws and low generalization ability for stock market graphical indicators data processing. Therefore, this paper proposes a quantification method of stock market candlestick chart based on Hough variation, using the graph structure embedding method to represent candlestick chart features and multiple attention graph neural network for stock market price fluctuation prediction. The experimental results show that the proposed method can interpret the candlestick chart features more accurately and has superiority performance over state-of-the-art deep learning methods, including SVM, CNN, LSTM, and CNN-LSTM. Relative to these algorithms, the proposed method achieves an average performance improvement of 20.51% in terms of accuracy and further achieves at least 26.98% improvement in strategy returns in quantitative investment experiments.

Sparrow Search Algorithm-Optimized Long Short-Term Memory Model for Stock Trend Prediction.

The long short-term memory (LSTM) network is especially suitable for dealing with time series-related problems, which has led to a wide range of applications in analyzing stock market quotations and predicting future price trends. However, the selection of hyperparameters in LSTM networks was often based on subjective experience and existing research. The inability to determine the optimal values of the parameters results in a reduced generalization capability of the model. Therefore, we proposed a sparrow search algorithm-optimized LSTM (SSA-LSTM) model for stock trend prediction. The SSA was used to find the optimal hyperparameters of the LSTM model to adapt the features of the data to the structure of the model, so as to construct a highly accurate stock trend prediction model. With the Shanghai Composite Index stock data in the last decade, the mean absolute percentage error, root mean square error, mean absolute error, and coefficient of determination between stock prices predicted by the SSA-LSTM method and actual prices are 0.0093, 41.9505, 30.5300, and 0.9754. The result indicates that the proposed model possesses higher forecasting precision than other traditional stock forecasting methods and enhances the interpretability of the network model structure and parameters.

Algorithmic Trading Stock Price Model

Abstract: Stock market price prediction is a difficult undertaking that generally requires a lot of human-computer interaction. Traditional batch processing methods cannot be used effectively for stock market analysis due to the linked nature of stock prices. This project presents an online learning technique that employs a recurrent neural network of some sort (RNN) called Long Short-Term Memory (LSTM), which uses stochastic gradient descent to update the weights for individual data points. When compared to existing stock price prediction systems, this will yield more accurate results. With varying sizes of data, the network is trained and evaluated for accuracy, and the results are tallied. A comparison with respect to accuracy is then performed against an Artificial Neural Network. Traditional approaches to securities market analysis and stock value prediction embrace basic analysis, that appearance at a stock's past performance and therefore the general believability of the corporate itself, and applied mathematics analysis, that is exclusively involved with computation and distinguishing patterns available value variation.

Stock Market Analysis and Prediction using Machine Learning

The stock market is a field which has spurred the interest of not only researchers, but, ordinary people as well over the years. It has encouraged scientists to develop better predictive models. The stock market is not as simple as it might seem initially. It is a transformative, non-straight dynamical and complex system. The main objectives of the project are to analyze the advantages and disadvantages of using Machine Learning techniques for the purpose of predicting values and comparing different algorithms, along with integrating the best model in a Web Application which will help users to be able to improve their decision making strategies by trying to give them an insight on what could possibly happen in the short term of things. Machine learning can be described as a technology that enables a system to learn on its own through real-world interactions with the help of data and hence be able to recognize similar interactions which the machine initially learned. Machine Learning over the past decade has quite subtly become to become a part of one’s everyday life due to its key role in numerous vital applications.

The reaction of G20+ stock markets to the Russia–Ukraine conflict “black-swan” event: Evidence from event study approach

In this paper we examine the impact of the breakout of the conflict between Russia and Ukraine on the G20 and other selected stock markets using the event study approach. The analysis of the abnormal returns (AR) before and after the launch of the ‘special military operation’ by Russian military forces on the 24th of February 2022 revealed a strong negative impact of this military action on a majority of the stock markets, especially on the Russian market. The aggregate stock market analysis indicates a significant and negative impact of the Russia–Ukraine conflict on the event day and post event days. The country-wise analysis demonstrated that the stock markets of Hungary, Russia, Poland, and Slovakia were first to react in anticipation of the military actions in Ukraine, showing negative returns in pre- event days already, whereas the stock markets of Australia, France, Germany, India, Italy, Japan, Romania, South Africa, Spain, and Turkey were adversely affected in the post-invasion days. Finally, the regional analysis indicates that the European and Asian regions are significantly and adversely affected by this event.

Historical analysis and forecasting of stock market using fbprophet


 
 
 Forecasting can be used in many fields such as crypto currency prediction, financial entities, supermarkets etc. We get the time series date which we use to feed the data into the algorithm is given by Y finance with this we get refreshed data every day. The stock market prediction or forecasting helps customers and brokers get a brief view of how the market behaves for the coming years. Many models are currently in use Like Regression techniques, Long Short-Term Memory algorithm etc. FB Prophet is proven to perform better than most other Algorithms with better accuracy. From the proposed research and references we have determined Facebook's Prophet algorithm as our forecasting algorithm because it is predicting at better accuracy, low error rate, handles messy data, doesn’t bother for null values and better fitting.