Actual Stock Market Research Articles

The Impact of the COVID-19 Pandemic on Stock Market Performance in G20 Countries: Evidence from Long Short-Term Memory with a Recurrent Neural Network Approach.

In light of developing and industrialized nations, the G20 economies account for a whopping two-thirds of the world's population and are the largest economies globally. Public emergencies have occasionally arisen due to the rapid spread of COVID-19 globally, impacting many people's lives, especially in G20 countries. Thus, this study is written to investigate the impact of the COVID-19 pandemic on stock market performance in G20 countries. This study uses daily stock market data of G20 countries from January 1, 2019 to June 30, 2020. The stock market data were divided into G7 countries and non-G7 countries. The data were analyzed using Long Short-Term Memory with a Recurrent Neural Network (LSTM-RNN) approach. The result indicated a gap between the actual stock market index and a forecasted time series that would have happened without COVID-19. Owing to movement restrictions, this study found that stock markets in six countries, including Argentina, China, South Africa, Turkey, Saudi Arabia, and the United States, are affected negatively. Besides that, movement restrictions in the G7 countries, excluding the United States, and the non-G20 countries, excluding Argentina, China, South Africa, Turkey, and Saudi, significantly impact the stock market performance. Generally, LSTM prediction estimates relative terms, except for stock market performance in the United Kingdom, the Republic of Korea, South Africa, and Spain. The stock market performance in the United Kingdom and Spain countries has significantly reduced during and after the occurrence of COVID-19. It indicates that the COVID-19 pandemic considerably influenced the stock markets of 14 G20 countries, whereas less severely impacting 6 remaining countries. In conclusion, our empirical evidence showed that the pandemic had restricted effects on the stock market performance in G20 countries.

Effect of covid 19 on it business and stock market

During a pandemic, the most affected aspects are the business economy and other sectors and areas globally. This research analyses the IT sector’s condition during COVID-19 by taking a sample of four companies, analyzing the stock market and financial records of the previous few months, and predicting future stock market value to see the stock market graph. Random function and MS excel used for prediction of future stock market and records of the previous financial year to conclude status of the company with graphs. After analyzing a four-sample company, a conclusion for the sector is provided. Research analysis found most companies are stable even though they are going through certain losses because of their existing assets, fluctuating financial records, and stock market graphs. Sample companies can easily recover losses and still showing a bullish graph successfully. Even though suffering a percentage of error with the actual stock market price, it successfully portrayed the IT industry scenario in this uncertain situation. However, the magnitude of the impact has never been precisely calculated. This thesis suggests a COVID-19 impact calculation model. Assets gains in the COVID-19 timeframe are weighted means of prior COVID-19 standard yields and COVID-19-induced returns in the proposed model. The COVID-19-generated gains are negatively auto-correlated and extremely unpredictable, and they substitute the prior COVID-19 standard gains. During the COVID-19 era, the COVID-19-generated gains are unique natural gains.

Financial Market Correlation Analysis and Stock Selection Application Based on TCN-Deep Clustering

It is meaningful to analyze the market correlations for stock selection in the field of financial investment. Since it is difficult for existing deep clustering methods to mine the complex and nonlinear features contained in financial time series, in order to deeply mine the features of financial time series and achieve clustering, a new end-to-end deep clustering method for financial time series is proposed. It contains two modules: an autoencoder feature extraction network based on TCN (temporal convolutional neural) networks and a temporal clustering optimization algorithm with a KL (Kullback–Leibler) divergence. The features of financial time series are represented by the causal convolution and the dilated convolution of TCN networks. Then, the pre-training results based on the KL divergence are fine-tuned to make the clustering results discriminative. The experimental results show that the proposed method outperforms existing deep clustering and general clustering algorithms in the CSI 300 and S&P 500 index markets. In addition, the clustering results combined with an inference strategy can be used to select stocks that perform well or poorly, thus guiding actual stock market trades.

Intelligent candlestick forecast system for financial time-series analysis using metaheuristics-optimized multi-output machine learning

The effective prediction of stock market prices and trends is a critical topic in financial research for investors and stakeholders who wish to increase their return on investment. Motivated by highly unstable stock market targets and the continuous trading system that has been launched by Taiwan’s stock market, this work develops an intelligent candlestick forecast system (ICFS), which combines the advantages of three forecasting techniques — single-point, interval value, and trend forecasting. The ICFS is simple and intuitive, using a sliding-window metaheuristic-optimized multi-output least squares support vector regression hybrid model scheme to forecast simultaneously four types of price information that are represented on a candlestick chart. Three parameter-free metaheuristic algorithms, namely teaching-learning-based optimization (TLBO), symbiotic organisms search (SOS), and forensic-based investigation (FBI), are in turn used to optimize the hyperparameters of the multi-output least squares support vector regression (MLSSVR) model, to increase its accuracy and stability in predicting stock prices. Benchmark data from relevant studies are used to compare the forecast performances of previously developed and the three proposed hybrid models. Among all tested models, the FBI-MLSSVR greatly outperforms the others in forecasting Standard & Poor’s (S&P) and National Association of Securities Dealers Automated Quotations (NASDAQ) indexes, Taiwan’s exchange-traded funds, and major listed construction companies. A floating dollar-cost averaging strategy for maximizing returns while minimizing investment risks is proposed and compared with traditional dollar-cost averaging and the buy-and-hold strategy. The profitability of the predictions made using the proposed system is verified against actual stock market operations. The ICFS is packaged as a visualized expert system and independent application program for the convenience of users, who can intuitively run it and interpret its forecasts. Therefore, this study is highly practical by providing stakeholders with an easy-to-use and accurate predictive tool.

Discussion on the Influence of Stock Market opening on Market Manipulation

The stock market is an emerging market formed after China's reform and opening up. It plays a very important role in the development of our social economy. As an information intensive market, the stock price is very sensitive to the change of information. In order to make the stock market in a more fair and true state, relevant information needs to be transmitted to investors in a timely and accurate manner. However, in the actual stock market, relevant stock information cannot be disclosed to investors in a timely and accurate manner, which leads to an unfair stock investment environment and is not conducive to the sustainable and healthy development of the stock market. However, the gradual opening of the stock market in recent years has had an important impact on the manipulation of the stock market. Based on this, this paper chooses the impact of the opening of the stock market on market manipulation to study, in order to provide some reference for the follow-up research.

Incorporating Transformers and Attention Networks for Stock Movement Prediction

Predicting stock movements is a valuable research field that can help investors earn more profits. As with time‐series data, the stock market is time‐dependent and the value of historical information may decrease over time. Accurate prediction can be achieved by mining valuable information with words on social platforms and further integrating it with actual stock market conditions. However, many methods still cannot effectively dig deep into hidden information, integrate text and stock prices, and ignore the temporal dependence. Therefore, to solve the above problems, we propose a transformer‐based attention network framework that uses historical text and stock prices to capture the temporal dependence of financial data. Among them, the transformer model and attention mechanism are used for feature extraction of financial data, which has fewer applications in the financial field, and effective analysis of key information to achieve an accurate prediction. A large number of experiments have proved the effectiveness of our proposed method. The actual simulation experiment verifies that our model has practical application value.

Combining expert weights for online portfolio selection based on the gradient descent algorithm

In this paper, we propose a new online portfolio selection strategy based on a weighted learning technique and an online gradient descent algorithm. Our strategy, named combination weights based on online gradient descent (CW-OGD), achieves improved robustness by integrating different expert strategies and overcomes the difficult problem of complex computational time. First, an expert system including many basic expert strategies, in which we choose the strategy that invests in a single stock as the basic expert strategy, is established. Second, we exploit the loss function to evaluate the performance of different basic expert strategies and use the OGD algorithm to update the weight vector for the experts based on their losses. In addition, we theoretically prove that the proposed strategy has a regret bound. Finally, extensive experiments conducted on four stock combinations and seven benchmark datasets show that our strategy can outperform some state-of-the-art strategies in terms of the return, risk and computational time metrics. Furthermore, our strategy can achieve higher returns even at certain transaction cost rates, which illustrates its effectiveness in the actual stock market.

Stock Market Prediction Using Twitter Sentiment Analysis

Stock market prediction is an important topic in ?nancial engineering especially since new techniques and approaches on this matter are gaining value constantly. In this project, we investigate the impact of sentiment expressed through Twitter tweets on stock price prediction. Twitter is the social media platform which provides a free platform for each individual to express their thoughts publicly. Specifically, we fetch the live twitter tweets of the particular company using the API. All the stop words, special characters are extracted from the dataset. The filtered data is used for sentiment analysis using Naïve bayes classifier. Thus, the tweets are classified into positive, negative and neutral tweets. To predict the stock price, the stock dataset is fetched from yahoo finance API. The stock data along with the tweets data are given as input to the machine learning model to obtain the result. XGBoost classifier is used as a model to predict the stock market price. The obtained prediction value is compared with the actual stock market value. The effectiveness of the proposed project on stock price prediction is demonstrated through experiments on several companies like Apple, Amazon, Microsoft using live twitter data and daily stock data. The goal of the project is to use historical stock data in conjunction with sentiment analysis of news headlines and Twitter posts, to predict the future price of a stock of interest. The headlines were obtained by scraping the website, FinViz, while tweets were taken using Tweepy. Both were analyzed using the Vader Sentiment Analyzer.

Aggregating exponential gradient expert advice for online portfolio selection

In recent years, online portfolio selection, one of the fundamental problems in computational finance, has attracted increasing interest from online learning. Although existing online portfolio strategies have been shown to achieve good performance, appropriate values of their parameters need to be set in advance. However, the optimal values can only be known in hindsight. To overcome this limitation, this paper proposes a new online portfolio strategy by aggregating exponential gradient (EG) expert advice using the weak aggregating algorithm (WAA). First, we consider a pool of EG strategies with different learning rates as experts, and compute the portfolio on the next period by aggregating all the expert advice using the WAA according to their previous performance. Second, we theoretically prove that the proposed strategy is universal, i.e. its average logarithmic growth rate is asymptotically the same as that of the best constant rebalanced portfolio (BCRP) in hindsight. Finally, we conduct extensive experiments to examine the performance of the proposed strategy on actual stock market. Numerical results show that the proposed strategy overcomes the drawbacks of existing online strategies and achieves significant performance.

CAPM verification using overnight and daytime returns

Purpose The capital asset pricing model has failed to explain the effect of systematic risk (referred to as beta) on actual stock market returns. Accordingly, this study analyzes daily returns by splitting it into overnight and daytime returns. The study analysis empirically confirms a positive relationship between overnight returns and beta and a negative relation between daytime returns and beta. Furthermore, this paper aims to determine that empirical results are mostly the same with three different beta calculations, namely, daily, overnight and daytime returns. The study concludes that beta on overnight returns has the strongest explanatory power and is statistically significant.

A Q-learning agent for automated trading in equity stock markets

Trading strategies play a vital role in Algorithmic trading, a computer program that takes and executes automated trading decisions in the stock market. The conventional wisdom is that the same trading strategy is not profitable for all stocks all the time. The selection of a trading strategy for the stock at a particular time instant is the major research problem in the stock market trading. An optimal dynamic trading strategy generated from the current pattern of the stock price trend can attempt to solve this problem. Reinforcement Learning can find this optimal dynamic trading strategy by interacting with the actual stock market as its environment. The representation of the state of the environment is crucial for performance. We have proposed two different ways to represent the discrete states of the environment. In this work, we trained the trading agent using the Q-learning algorithm of Reinforcement Learning to find optimal dynamic trading strategies. We experimented with the two proposed models on real stock market data from the Indian and American stock markets. The proposed models outperformed the Buy-and-Hold and Decision-Tree based trading strategy in terms of profitability.

Trend following deep Q‐Learning strategy for stock trading

AbstractComputers and algorithms are widely used to help in stock market decision making. A few questions with regards to the profitability of algorithms for stock trading are can computers be trained to beat the markets? Can an algorithm take decisions for optimal profits? And so forth. In this research work, our objective is to answer some of these questions. We propose an algorithm using deep Q‐Reinforcement Learning techniques to make trading decisions. Trading in stock markets involves potential risk because the price is affected by various uncertain events ranging from political influences to economic constraints. Models that trade using predictions may not always be profitable mainly due to the influence of various unknown factors in predicting the future stock price. Trend Following is a trading idea in which, trading decisions, like buying and selling, are taken purely according to the observed market trend. A stock trend can be up, down, or sideways. Trend Following does not predict the stock price but follows the reversals in the trend direction. A trend reversal can be used to trigger a buy or a sell of a certain stock. In this research paper, we describe a deep Q‐Reinforcement Learning agent able to learn the Trend Following trading by getting rewarded for its trading decisions. Our results are based on experiments performed on the actual stock market data of the American and the Indian stock markets. The results indicate that the proposed model outperforms forecasting‐based methods in terms of profitability. We also limit risk by confirming trading actions with the trend before actual trading.

Fluctuation entropy and complexity of financial percolation model with random jump on gasket fractal lattice

In an attempt to investigate the statistical complexity mechanics of stock markets, a novel stochastic interacting financial dynamics is proposed by Sierpinski gasket fractal lattice percolation with random jump. Sierpinski gasket is a famous example of fractals, and Sierpinski gasket lattice is a fractal-like graph which corresponds to that. Fuzzy entropy and multiscale composite complexity synchronization are applied to investigate the complexity and synchronization behaviors of security time series. Further, the similar statistical methods are used to analyze the actual stock market for comparison, which verifies the rationality and effectiveness of the financial model. The results suggest that the randomness of return series from the model increases with the increase of the parameter, which indicates the frequency of unexpected events affecting the stock market within the unit time and shows that the time series basically become more synchronous as the time scale increases. The empirical studies indicate that this stochastic price model is reasonable to a certain degree.

Fuzzy entropy complexity and multifractal behavior of statistical physics financial dynamics

The present paper introduces a novel stochastic statistical physics financial system by combining exclusion system with compound Poisson process. The financial system is a model concerning with price fluctuations derived from dissemination of trading attitudes of financial agents and random drastic jumps caused by exogenous economic factors, respectively. Multifractal detrended cross-correlation analysis and fuzzy entropy of simulation dataset are performed. Fractional fuzzy entropy based on fuzzy entropy method and fractional calculus, is also developed to explore nonlinear complexity of the proposed model in the paper. Empirical results display that there are significant multifractality and fractal asymmetry in the proposed model, and the complexity of return series increases when λ or γ increases, correspondingly. And same analyses for actual stock market dataset are comparatively investigated. The conclusions reveal that the novel compound dynamics can reproduce various nonlinear behaviors of actual stock markets to a certain extent.

Using the CCAPM with Stochastic Taxation and Money Supply to Examine U.S. REITs Pricing Bubbles

We examine three issues relating to U.S. real estate investment trust (REIT) pricing. First, using a modified capital consumption asset pricing model (CCAPM) with stochastic taxation and money supply, we compute the fundamental values for REITs for our sample period, 1972–2013. Second, for publicly traded equity REITs, we define a bubble to be the difference between the actual stock market price and the fundamental value derived from our theoretical model. U.S. REITs have, among other corporate structural features, special rules governing dividend distributions and corporate taxation that make them an especially attractive and preferred vehicle for testing for the presence of pricing bubbles. Our findings suggest that during our sample period, U.S. REITs experienced many price bubbles, some of which were quite large. Third, our results imply that monetary policy, in the short run, plays a role in the formation of these pricing bubbles.

Multiscale volatility duration characteristics on financial multi-continuum percolation dynamics

A random stock price model based on the multi-continuum percolation system is developed to investigate the nonlinear dynamics of stock price volatility duration, in an attempt to explain various statistical facts found in financial data, and have a deeper understanding of mechanisms in the financial market. The continuum percolation system is usually referred to be a random coverage process or a Boolean model, it is a member of a class of statistical physics systems. In this paper, the multi-continuum percolation (with different values of radius) is employed to model and reproduce the dispersal of information among the investors. To testify the rationality of the proposed model, the nonlinear analyses of return volatility duration series are preformed by multifractal detrending moving average analysis and Zipf analysis. The comparison empirical results indicate the similar nonlinear behaviors for the proposed model and the actual Chinese stock market.

GENERALIZED WEIERSTRASS–MANDELBROT FUNCTION MODEL FOR ACTUAL STOCKS MARKETS INDEXES WITH NONLINEAR CHARACTERISTICS

It is difficult to simulate the dynamical behavior of actual financial markets indexes effectively, especially when they have nonlinear characteristics. So it is significant to propose a mathematical model with these characteristics. In this paper, we investigate a generalized Weierstrass–Mandelbrot function (WMF) model with two nonlinear characteristics: fractal dimension D where 2 > D > 1.5 and Hurst exponent (H) where 1 > H > 0.5 firstly. And then we study the dynamical behavior of H for WMF as D and the spectrum of the time series γ change in three-dimensional space, respectively. Because WMF and the actual stock market indexes have two common features: fractal behavior using fractal dimension and long memory effect by Hurst exponent, we study the relationship between WMF and the actual stock market indexes. We choose a random value of γ and fixed value of D for WMF to simulate the S&P 500 indexes at different time ranges. As shown in the simulation results of three-dimensional space, we find that γ is important in WMF model and different γ may have the same effect for the nonlinearity of WMF. Then we calculate the skewness and kurtosis of actual Daily S&P 500 index in different time ranges which can be used to choose the value of γ. Based on these results, we choose appropriate γ, D and initial value into WMF to simulate Daily S&P 500 indexes. Using the fit line method in two-dimensional space for the simulated values, we find that the generalized WMF model is effective for simulating different actual stock market indexes in different time ranges. It may be useful for understanding the dynamical behavior of many different financial markets.

Is there any connection between the network morphology and the fluctuations of the stock market index?

Models which consider behavioral aspects of the investors have attracted increasing interest in the Finance and Econophysics literature in the last years. Different behavioral profiles (imitation, anti-imitation, indifference) were proposed for the investors, which take their decision based on their trust network (neighborhood). Results from agent-based models have shown that most of the features observed in actual stock market indices can be replicated in simulations. Here, we present a deeper investigation of an agent based model considering different network morphologies (regular, random, small-world) for the investors’ trust network, in an attempt to answer the question raised in the title. We study the model by considering four scenarios for the investors and different initial conditions to analyze their influence in the stock market fluctuations. We have characterized the stationary limit for each scenario tested, focusing on the changes introduced when complex networks were used, and calculated the Hurst exponent in some cases. Simulations showed interesting results suggesting that the fluctuations of the stock market index are strongly affected by the network morphology, a remarkable result which we believe was never reported or predicted before.

정보기준과 효율적 자료길이를 활용한 시계열자료 운동패턴 예측 연구

Is generated in real time in the real world, a large amount of time series data from a wide range of business areas. But it is not easy to determine the optimal model for the description and understanding of the time series data is represented as a dynamic feature. In this study, through the HMM suitable for estimating the short and long-term forecasting model of time-series data to estimate a model that can explain the characteristics of these time series data, it was estimated to predict future patterns of movement. The actual stock market through various materials, information criterion and optimal model estimation for the length of the most efficient data was found to accurately estimate the state of the model. Similar movement patterns predictive than the long-term prediction is more similar to the short-term prediction of the experimental result were found to be.

What Does Investor Sentiment Reflect: Animal Spirits or Risks?

The role of investor sentiment in the stock market has attracted attentions of many economists. Previous papers show that investor sentiment has return predictability and it is more pronounced among stocks that are more difficult to value and/or to arbitrage, and emphasize the behavioral role of investor sentiment. However, it still remains unclear whether this predictability is actually due to a causal effect of autonomous animal spirits or not. Alternatively, investor sentiment may simply reflect systematic risks, which would affect stock returns. In this alternative case, the predictability would be mere coincidence, not causation. In this paper, I try to understand the meaning of innovations in investor sentiment. I use the investor sentiment index constructed by Baker and Wurgler (2006). I set up a structural model in which sentiment innovations arise from both animal spirit shocks and several risk shocks, and animal spirit shocks could affect stock returns. By matching impulse response functions from data simulated by the theoretical model to those from the actual US data, I estimate parameters in the model. The estimated model moderately replicates the historical data in the actual stock market. The estimation results show that a substantial amount of variation in investor sentiment is explained by systematic risk shocks as well as by animal spirit shocks, and that animal spirit shocks can have significant effects on stock returns. The findings suggest that investor sentiment is a noisy proxy of animal spirits and autonomous animal spirits are at least in part responsible for the apparent return predictability of investor sentiment.