Comparative Analysis of Machine Learning Models for Stock Price Prediction: Leveraging LSTM for Real-Time Forecasting

The research focuses on improving predictive accuracy in the financial sector through the exploration of machine learning algorithms for stock price prediction. The research follows an organized process combining Agile Scrum and the Obtain, Scrub, Explore, Model, and iNterpret (OSEMN) methodology. Six machine learning models, namely Linear Forecast, Naive Forecast, Simple Moving Average with weekly window (SMA 5), Simple Moving Average with monthly window (SMA 20), Autoregressive Integrated Moving Average (ARIMA), and Long Short-Term Memory (LSTM), are compared and evaluated through Mean Absolute Error (MAE), with the LSTM model performing the best, showcasing its potential for practical financial applications. A Django web application “Predict It” is developed to implement the LSTM model. Ethical concerns related to predictive modeling in finance are addressed. Data quality, algorithm choice, feature engineering, and preprocessing techniques are emphasized for better model performance. The research acknowledges limitations and suggests future research directions, aiming to equip investors and financial professionals with reliable predictive models for dynamic markets.

Stock Price Prediction Based on the Bi-GRU-Attention Model

The stock market, as one of the hotspots in the financial field, forms a data system with a huge volume of data and complex relationships between various factors, making stock price prediction an area of keen interest for further in-depth mining and research. Mathematical statistics methods struggle to deal with nonlinear relationships in practical applications, making it difficult to explore deep information about stocks. Meanwhile, machine learning methods, particularly neural network models and composite models, which have achieved outstanding results in other fields, are being applied to the stock market with significant results. However, researchers have found that these methods do not grasp the essential information of the data as well as expected. In response to these issues, researchers are exploring better neural network models and combining them with other methods to analyze stock data. Thus, this paper proposes the ABiGRU composite model, which combines the attention mechanism and bidirectional gated recurrent unit (GRU) that can effectively extract data features for stock price prediction research. Models such as LSTM, GRU, and Bi-LSTM are selected for comparative experiments. To ensure the credibility and representativeness of the research data, daily stock price indices of BYD are chosen for closing price prediction studies across different models. The results show that the ABiGRU model has a lower prediction error and better fitting effect on three index-based stock prices, enhancing the learning efficiency of the neural network model and demonstrating good prediction stability. This suggests that the ABiGRU model is highly adaptable for stock price prediction.

Deep Learning-Based Stock Price Prediction Using LSTM Model

The stock market is a vital component of the broader financial system,with its dynamics closely linked to economic growth.The challenges associated with analyzing and forecasting stock prices have persisted since the inception of financial markets.By examining historical transaction data,latent opportunities for profit can be uncovered,providing valuable insights for both institutional and individual investors to make more informed decisions.This study focuses on analyzing historical transaction data from four banks to predict closing price trends.Various models,including decision trees,random forests,and Long Short-Term Memory(LSTM)networks,are employed to forecast stock price movements.Historical stock transaction data serves as the input for training these models,which are then used to predict upward or downward stock price trends.The study’s empirical results indicate that these methods are effective to a degree in predicting stock price movements.The LSTM-based deep neural network model,in particular,demonstrates a commendable level of predictive accuracy.This conclusion is reached following a thorough evaluation of model performance,highlighting the potential of LSTM models in stock market forecasting.The findings offer significant implications for advancing financial forecasting approaches,thereby improving the decision-making capabilities of investors and financial institutions.

Carbon emission trading system and stock price crash risk of heavily polluting listed companies in China:based on analyst coverage mechanism

This study reveals the inconsistencies between the negative externalities of carbon emissions and the recognition condition of accounting statements.Hence,the study identifies that heavily polluting enterprises in China have severe off-balance sheet carbon reduction risks before implementing the carbon emission trading system(CETS).Through the staggered difference-in-difference(DID)model and the propen-sity score matching-DID model,the impact of CETS on reducing the risk of stock price crashes is examined using data from China’s A-share heavily polluting listed companies from 2007 to 2019.The results of this study are as follows:(1)CETS can significantly reduce the risk of stock price crashes for heavily polluting companies in the pilot areas.Specifically,CETS reduces the skewness(negative conditional skewness)and down-to-up volatility of the firm-specific weekly returns by 8.7%and 7.6%,respectively.(2)Heterogeneity analysis further shows that the impacts of CETS on the risk of stock price crashes are more significant for heavily polluting enterprises with the bear market condition,short-sighted management,and intensive air pollution.(3)Mechanism tests show that CETS can reduce analysts’coverage of heavy polluters,reducing the risk of stock price crashes.This study reveals the role of CETS from the stock price crash risk perspective and helps to clarify the relationship between climatic risk and corporate financial risk.

Impact of Environmental,Social,and Governance(ESG)Factors on Stock Prices and Investment Performance

This study examines the relationship between Environmental,Social,and Governance(ESG)factors and stock prices as well as investment performance.ESG factors have become increasingly relevant in investment decisions as investors prioritize companies with sustainable practices.Using a sample of publicly-traded companies,this research analyzes the impact of ESG factors on stock prices and investment returns.The findings suggest that companies with strong ESG performance tend to have higher stock prices and better investment performance than those with weak ESG performance.The study also highlights the significance of the individual components of ESG,such as environmental policies and corporate governance practices,on stock prices and investment returns.Overall,this research provides valuable insights for investors seeking to incorporate ESG factors into their investment decision-making processes.

Stock Price Forecasting with Artificial Neural Networks Long Short-Term Memory: A Bibliometric Analysis and Systematic Literature Review

This study maps the academic literature on Stock Price Forecasting with Long-Term Memory Artificial Neural Networks—RNA LSTM. The objective is to know if it is suitable for time series studies, especially for stock price projection. Through bibliometric analysis and systematic literature review, it is observed that 333 authors wrote on the topic between 2018 and March 2022, and the journals Expert Systems with Applications, IEEE Access, Big Data Journal and Neural Computing and Applications, published the most relevant articles. Of the 99 articles published in this period, 43 are associated with Chinese institutions, the most cited being that of Kim and Won, who studies the volatility of returns and the market capitalization of South Korean stocks. The basis of 65% of the studies is the comparison between the RNN LSTM and other artificial neural networks. The daily closing price of shares is the most analyzed type of data, and the American (21%) and Chinese (20%) stock exchanges are the most studied. 57% of the studies include improvements to existing neural network models and 42% new projection models.

Applications of nonferrous metal price volatility to prediction of China's stock market

The aim of the present work is to examine whether the price volatility of nonferrous metal futures can be used to predict the aggregate stock market returns in China. During a sample period from January of 2004 to December of 2011, empirical results show that the price volatility of basic nonferrous metals is a good predictor of value-weighted stock portfolio at various horizons in both in-sample and out-of-sample regressions. The predictive power of metal copper volatility is greater than that of aluminum. The results are robust to alternative measurements of variables and econometric approaches. After controlling several well-known macro pricing variables, the predictive power of copper volatility declines but remains statistically significant. Since the predictability exists only during our sample period, we conjecture that the stock market predictability by metal price volatility is partly driven by commodity financialization.

The chaotic behavior among the oil prices, expectation of investors and stock returns: TAR-TR-GARCH copula and TAR-TR-TGARCH copula

This paper has two aims. The first one is to investigate the existence of chaotic structures in the oil prices, expectations of investors and stock returns by combining the Lyapunov exponent and Kolmogorov entropy, and the second one is to analyze the dependence behavior of oil prices, expectations of investors and stock returns from January 02, 1990, to June06, 2017. Lyapunov exponents and Kolmogorov entropy determined that the oil price and the stock return series exhibited chaotic behavior. TAR-TR-GARCH and TAR-TR-TGARCH copula methods were applied to study the co-movement among the selected variables. The results showed significant evidence of nonlinear tail dependence between the volatility of the oil prices, the expectations of investors and the stock returns. Further, upper and lower tail dependence and comovement between the analyzed series could not be rejected. Moreover, the TAR-TR-GARCH and TAR-TR-TGARCH copula methods revealed that the volatility of oil price had crucial effects on the stock returns and on the expectations of investors in the long run.

Improving Stock Price Forecasting Using a Large Volume of News Headline Text

Previous research in the area of using deep learning algorithms to forecast stock prices was focused on news headlines,company reports,and a mix of daily stock fundamentals,but few studies achieved excellent results.This study uses a convolutional neural network(CNN)to predict stock prices by considering a great amount of data,consisting of financial news headlines.We call our model N-CNN to distinguish it from a CNN.The main concept is to narrow the diversity of specific stock prices as they are impacted by news headlines,then horizontally expand the news headline data to a higher level for increased reliability.This model solves the problem that the number of news stories produced by a single stock does not meet the standard of previous research.In addition,we then use the number of news headlines for every stock on the China stock exchange as input to predict the probability of the highest next day stock price fluctuations.In the second half of this paper,we compare a traditional Long Short-Term Memory(LSTM)model for daily technical indicators with an LSTM model compensated by the N-CNN model.Experiments show that the final result obtained by the compensation formula can further reduce the root-mean-square error of LSTM.

Using Data Mining with Time Series Data in Short-Term Stocks Prediction: A Literature Review

Data Mining (DM) methods are being increasingly used in prediction with time series data, in addition to traditional statistical approaches. This paper presents a literature review of the use of DM with time series data, focusing on shorttime stocks prediction. This is an area that has been attracting a great deal of attention from researchers in the field. The main contribution of this paper is to provide an outline of the use of DM with time series data, using mainly examples related with short-term stocks prediction. This is important to a better understanding of the field. Some of the main trends and open issues will also be introduced.

The interaction between stock prices and interest rates in Turkey:empirical evidence from ARDL bounds test cointegration

This paper demonstrates a significant,long-running relationship between stock prices and domestic interest rates in Turkey’s financial markets for the period of 2001 M1-2017 M4.Cointegration analysis is investigated using the autoregressivedistributed lag bounds(ARDL Bounds)test and vector autoregressive cointegration.Additionally,cointegrating equations such as the fully modified ordinary least square,dynamic ordinary least squares,and canonical cointegrating regression are applied to check the long-run elasticities in the concerned relationship.The ARDL Bounds and Johansen Cointegration test results show that,dynamically,both prices are significantly related to each other.The cointegrating equation outcomes demonstrate elasticities whereby both coefficients have negative signs.Additionally,the same results are corroborated by the impulse response where all variables respond negatively to each other.

Brent prices and oil stock behaviors: evidence from Nigerian listed oil stocks

Background:Given the shale oil glut that culminated in the most recent and continuing oil price drop from June 2014 and the global financial crisis of 2008 that triggered a cyclical downturn in oil prices and stock market activity,this study investigates the impact of Brent oil price shocks on oil related stocks in Nigeria.Methods:This study uses a vector autoregressive(VAR)model with the impulse response function and the forecast variance decomposition error.Findings:The empirical evidence reveals that oil price shocks have a negative impact on Nigerian oil and gas company stocks.In theory,this situation should apply to oil importing countries and is therefore uncharacteristic of an oil exporting country like Nigeria.Conclusions:The findings suggest that oil companies operating in Nigeria should diversify their investments to protect their business from single-sector market forces,and can also embrace the advantages of outsourcing some of their operations to specialist providers to increase flexibility and reduce operating costs.Finally,for vertically integrated oil and gas companies,oil price hedging and energy risk management will be beneficial because it will mean that these companies will take a position in the crude oil futures market.This will allow for better cash flow management and flexibility.Originality/value:This study extends the existing literature in two distinct ways.First,it provides,to the best of our knowledge,the first examination of the impact of oil price shocks on stock market activities with a focus on the market returns of oil and gas companies listed in the Nigerian Stock Exchange.Second,this study uses daily data because high frequency data contain more information than lower frequency data does,and lower frequency data average out too much important information.

The time‑varying effects of oil prices on oil-gas stock returns of the fragile five countries

This study analyzes oil price exposure of the oil–gas sector stock returns for the fragile five countries based on a multi-factor asset pricing model using daily data from 29 May 1996 to 27 January 2020.The endogenous structural break test suggests the presence of serious parameter instabilities due to fluctuations in the oil and stock markets over the period under study.Moreover,the time-varying estimates indicate that the oil–gas sectors of these countries are riskier than the overall stock market.The results further suggest that,except for Indonesia,oil prices have a positive impact on the sectoral returns of all markets,whereas the impact of the exchange rates on the oil–gas sector returns varies across time and countries.

The Prediction of Stock Price Based on Improved Wavelet Neural Network

To improve the accuracy of forecasting stock prices, a new method is proposed, which based on improved Wavelet Neural Network (WNN). Firstly, the Genetic Algorithm (GA) is used to optimize initial weights, stretching parameters and movement parameters. Then, comparing with traditional WNN, the momentum are added in parameters adjusting and learning of network, what’s more, learning rate and the factor of momentum are self-adaptive. The prediction system is tested using Shanghai Index data, simulation result shows that improved WNN performs very well.

Currency exposures of the oil and natural gas stock prices in the Hushen-300 stock market： A nonlinear model approach

The paper embarks to investigate the relationship between currency risk and stock prices of the oil and natural gas exploitation industry in the value-weighted Hushen-300 stock market, by applying the standard Capital Asset Pricing Model （CAPM） and nonlinear exchange rate exposure model to the Renminbi against US dollar. The results show that the currency exposure does vary in the oil-gas stock prices throughout the bull and bear market. The study suggests that the models of the equilibrium exchange rate exposure must be extended to considering the nonlinear exchange rate exposure, the regime periods of bull and bear market, and the industry types that is sensitive to the currency exposures. The nonlinear dynamic relationship between the exchange rate changes and the Chinese energy stock prices throughout the bull and bear market add to the recent empirical evidences that foreign exchange markets and stock markets are closely correlated.

Bankruptcy Probability and Stock Prices： The Effect of Altman Z-Score Information on Stock Prices Through Panel Data

There is an extensive branch of literature that examines the success of Altman＇s Z-score in predicting bankruptcy or financial distress. The goal of this research paper is to investigate the stock price performance of firms that exhibit a large probability of bankruptcy according to the model of Airman. Regardless of the validity of Airman＇s Z-score, we utilize a new empirical design that relates stock price movements to Altman＇s Z-score. We focus and examine, through the methodology of panel data, whether stocks that have a high probability of bankruptcy underperform stocks with a low probability of bankruptcy or if there are differences in the way the markets react to the financial health of the sample firms.

Exploring Patent Effects on Higher Stock Price and Stock Return Rate-A Study in China Stock Market

Based on the valid patent data and stock price data of China A-shares,the patent effects of four patent species including the invention publication,the invention grant,the utility model grant,and the design grant,on the stock price and the stock return rate were analyzed via analysis of variance(ANOVA).It was proved that the A-shares having new patents of any patent species shown the higher stock price mean and the higher stock return rate mean than those A-shares having no new patents did.The A-shares having new design grants were found to show the highest stock price mean among the A-shares having new patents of any patent species.The A-shares in the group of top 25%patent count of either the invention publication or the invention grant shown the highest stock return rates mean than those A-shares in other groups of less patent count did.The invention grant,following the general concept,showed its excellent patent effect.The design grant,beyond the expectation,also showed patent effects on the higher stock price and the higher stock return rate.The finding would improve the state of the art in the patent valuation and the listing company evaluation.

ARIMA and Facebook Prophet Model in Google Stock Price Prediction

We use the Autoregressive Integrated Moving Average(ARIMA)model and Facebook Prophet model to predict the closing stock price of Google during the COVID-19 pandemic as well as compare the accuracy of these two models’predictions.We first examine the stationary of the dataset and use ARIMA(0,1,1)to make predictions about the stock price during the pandemic,then we train the Prophet model using the stock price before January 1,2021,and predict the stock price after January 1,2021,to present.We also make a comparison of the prediction graphs of the two models.The empirical results show that the ARIMA model has a better performance in predicting Google’s stock price during the pandemic.

SIMPLEST DIFFERENTIAL EQUATION OF STOCK PRICE,ITS SOLUTION AND RELATION TO ASSUMPTION OF BLACK-SCHOLES MODEL

Two kinds of mathematical expressions of stock price, one of which based on certain description is the solution of the simplest differential equation (S.D.E.) obtained by method similar to that used in solid mechanics,the other based on uncertain description (i.e., the statistic theory)is the assumption of Black_Scholes's model (A.B_S.M.) in which the density function of stock price obeys logarithmic normal distribution, can be shown to be completely the same under certain equivalence relation of coefficients. The range of the solution of S.D.E. has been shown to be suited only for normal cases (no profit, or lost profit news, etc.) of stock market, so the same range is suited for A.B_ S.M. as well.

A Mathematical Model Reveals That Both Randomness and Periodicity Are Essential for Sustainable Fluctuations in Stock Prices

Is it true that there is an implicit understanding that Brownian motion or fractional Brownian motion is the driving force behind stock price fluctuations? An analysis of daily prices and volumes of a particular stock revealed the following findings: 1) the logarithms of the moving averages of stock prices and volumes have a strong positive correlation, even though price and volume appear to be fluctuating independently of each other, 2) price and volume fluctuations are messy, but these time series are not necessarily Brownian motion by replacing each daily value by 1 or –1 when it rises or falls compared to the previous day’s value, and 3) the difference between the volume on the previous day and that on the current day is periodic by the frequency analysis. Using these findings, we constructed differential equations for stock prices, the number of buy orders, and the number of sell orders. These equations include terms for both randomness and periodicity. It is apparent that both randomness and periodicity are essential for stock price fluctuations to be sustainable, and that stock prices show large hill-like or valley-like fluctuations stochastically without any increasing or decreasing trend, and repeat themselves over a certain range.