Stock Price Movements Research Articles

Multivariate Bayesian Time-Series Model with Multi-temporal Convolution Network for Forecasting Stock Market During COVID-19 Pandemic

The paper proposes a hybrid algorithm for forecasting multiple correlated time-series data, which consists of two main steps. First, it employs a multivariate Bayesian structural time series (MBSTS) approach as a base step. This method allows for the incorporation of potentially high-dimensional regression components, and it utilizes spike and slab priors to identify a parsimonious model. Second, the algorithm includes a post-model fitting diagnostic step where the residuals from the MBSTS step are processed through a multi-input/output temporal convolutional network (M-TCN) with multiple time scale feature learning. This step serves as an alternative to traditional subjective residual-based diagnostic procedures in time-series analysis, with the aim of improving forecasting accuracy. The key advantage of the M-TCN is its ability to capture sequential information efficiently. The M-TCN expands the field of convolution kernel without increasing the number of parameters, thus enhancing the capacity of model to capture complex sequential patterns. The paper presents two applications showcasing the effectiveness of the proposed hybrid algorithm. First, it utilizes pre-lockdown data from eleven Nifty stock sectoral indices to predict stock price movements, including the initial post-lockdown upturn. In the second application, it focuses on stock market data from pharmaceutical companies involved in manufacturing COVID-19 vaccines. In both cases, sentiment data sourced from newspapers and social media serve as the regression component. Through rigorous analysis, the paper demonstrates that the hybrid model outperforms various benchmark models, including LSTM, Bidirectional Encoder Representations from Transformers (BERT)-based LSTM, Deep Transformer Model, and GRU, among others, in terms of forecasting accuracy. This underscores the utility of the hybrid algorithm, particularly in predicting stock market trends during the COVID-19 pandemic period and its associated market dynamics.

Exploring the Association Between Bilibili's Post-IPO Quarterly Stock Price and Multivariate Factors: A Multiple Linear Regression Analysis

This research delves into the intricate dynamics of stock price movements for Bilibili, a prominent digital platform, post its Initial Public Offering (IPO). Emphasis is placed on evaluating the correlation and predictive power of three main factors, Gross Profit, Advertising Revenue, and Additional Services Revenue, in determining stock prices. Furthermore, the study examines the often-assumed positive relationship between Average Monthly Interactions (AMI) and Gross Profit, questioning the depth and directionality of this relationship. Preliminary findings suggest that while Gross Profit and Advertising Revenue may historically be substantial revenue streams impacting stock prices, revenues from additional services are emerging as significant predictors in the contemporary digital platform valuation landscape. Contrary to conventional belief, high AMI does not always translate to proportional Gross Profit gains. The research presents valuable insights for investors, stakeholders, and digital platform operators, elucidating the multifaceted drivers of stock price movements in the digital age.

Ntegrating Quantum-Inspired Principles into Financial Data Science: Optimizing Reservoir Computing Models

This research explores the integration of quantum-inspired principles into financial data science with a focus on optimizing Reservoir Computing (RC) models. This approach aims to achieve a more nuanced representation of market states, improving accuracy in predicting stock price movements and capturing complex interdependencies among financial assets. Utilizing historical data from Yahoo Finance, implement and optimize RC models enhanced by Quantum State Model (QSM) and Entangled Asset Model (EAM) techniques. The results demonstrate the potential benefits and challenges of applying these quantum-inspired methods to financial data analysis. Keywords: Computational Intelligence, Financial Data Science, Quantum Computing, Quantum Machine Learning (QML), Reservoir Computing

Analisis Peramalan Harga Saham Dengan Metode Arima Terhadap Keputusan Investasi Pada Perusahaan Perbankan Dalam Indeks LQ45

Every trader or investor in buying shares will always confused with the highly volatile stock price movements, this is causes traders or investors to be careful in choosing prices on when entering to buy shares. ARIMA price forecasting method is a forecasting method that traders and investors can use to help make decisions.This study is a descriptive study with a quantitative approach with the aim of analyzing, explaining, and concluding the analysis of price forecasting using the ARIMA (Autoregressive Integrated Moving Average) method on investment decisions in banking companies listed in the LQ45 index on the Indonesia Stock Exchange. The data collection technique in this study is documentation of the LQ45 Banking Index Stock Price on the Indonesian Stock Exchange.The results obtained in this study are that the model used in forecasting banking stock prices is the best model, the models include BBCA ARIMA (5.2.0), BBRI ARIMA (5.2.0), BMRI ARIMA (5.2, 0), BBNI ARIMA (2,2,0), and BBTN ARIMA (5,2,0). BBCA's share price decreased by -14.9%. BBRI's share price decreased by -5.8%. BMRI's share price decreased by -6.8%. BBNI's share price decreased by -58.5%. BBTN's share price decreased by -18.8%.106. Investors should not buy shares in banking stocks listed in the LQ45 index. This is because prices tend to fall and make investors suffer losses. However, if trading or investing in the near future, investors will buy shares of BBRI and BBTN companies, because within 1 month the shares will increase and investors or traders can get capital gains.

The dynamics of financial performance and market performance in the context of Indian banking industry

Background This study aims to gain insight into the effect of banks’ financial performance on their market performance. We conceptualized the research subject on the assumption that the financial performance of an organization is the most important criterion for triggering movement in its stock price. We explored various models and parameters to evaluate financial performance of banks and found CAMELS being one of the most comprehensive and appropriate model. We considered share price growth of banks to measure their stock market performance Methods We collected financial and stock market data pertaining to 32 listed Indian banks for the period 2018 to 2022. The study has employed multiple linear regression analysis of panel data for evaluating the relationship between independent and dependent variables. We adopted panel regression for data analysis and used the Prais- Winsten regression with panel corrected standard errors, as the data suffers from contemporaneous cross-sectional correlation. Results The results show that net non-performing assets, net interest margins, and return on capital have a significant negative impact on share price growth. The capital adequacy ratio and the current and savings account deposit ratios have a positive insignificant impact. The liquid asset-to-total asset ratio has a negative, insignificant impact. The coefficient of determination indicates that the share price growth of banks is more dependent on other factors which are not included in the regression analysis of this study. Conclusion This study helps investors and bankers understand the limited impact of financial parameters on banks’stock prices and to look for other parameters which explain the stock price movement better.

Amazon’s Stock Trends Prediction based on ARIMA Model

The rapid development of e-commerce in recent years has made stock market prediction a challenging yet important task for investors and traders. The ARIMA model has been extensively applied for forecasting in financial time series data. This study applied the ARIMA model to predict the Amazon stock price, utilizing historical stock price data from a period of a decade. The results of the analysis indicated that the ARIMA model can effectively predict short-term stock price movements with a certain level of accuracy. The model managed to encapsulate the predominant trend in the variations of Amazon’s stock prices, providing insights into potential future price movements. The predicted stock prices closely matched the actual prices, with a reasonable level of precision. Furthermore, the ARIMA model can be useful for investors and traders in making informed decisions. By utilizing the model’s predictions, investors can better assess the potential risks and returns associated with their investment strategies. It should be noted that the ARIMA model is not without its limitations. The model may not perform well during periods of structural changes or when there are significant events affecting the stock price. Besides, it can also be influenced by other factors such as policies, market sentiment and corporate fundamentals. In conclusion, the ARIMA model can assist in predicting short-term Amazon stock price movements, serving as a valuable tool for investors and traders. However, it is essential to integrate the model's forecasts with other pertinent information and analysis to form comprehensive investment decisions.

Improving Cryptocurrency Price Prediction Accuracy with Multi-Kernel Support Vector Regression Approach

Cryptocurrencies are digital assets that have attracted a lot of investment and attention. It is challenging and essential for investors and traders to predict their stock price movements. Making accurate predictions about cryptocurrency prices is crucial for avoiding losses and gaining profits. Our research proposes a novel method for predicting the stock closed prices of three popular cryptocurrencies: Bitcoin, Ethereum and Polkadot. The SVR (Support vector regression) machine learning method can provide robust and accurate predictions for nonlinear and nonstationary data. This paper compares SVR radial basis functions (RBFs) and hybrid kernels based on cryptocurrency data characteristics. SVR parameters such as regularization, gamma, and epsilon can also be tuned using grid search. Our approach is tested on real-world cryptocurrency stock prices collected from Yahoo Finance. Prediction performance is measured using regression metrics like MAPE (Mean absolute percentage error) and R2 score. In our work, a MAPE value of 0.07772 and an R2 score of 0.9999 have been obtained. The results of our experiments indicate that our approach is significantly more accurate and reliable than existing methods.

Prediksi Pergerakan Harga Saham Menggunakan Support Vector Machines Di Indonesia

Predicting stock movements is challenging due to their dynamic nature and influence from various factors. One of these factors is the lack of research considering the use of fundamental analysis regarding currency exchange rates and the use of foreign stock index movements related to technical analysis. This research aims to predict stock price movements in Indonesia based on sentiment analysis, technical analysis, and fundamental analysis using Support Vector Machine. The results obtained have an average prediction accuracy rate of 65.33%. The inclusion of currency exchange rates and foreign stock index movements as predictors in this study can increase the average prediction accuracy rate by 11.78% compared to predictions without using these two variables, which only result in an average prediction accuracy rate of 53.55%. Keywords: Fundamental Analysis, Sentiment Analysis, Stock Prediction, Support Vector Machines, Technical Analysis.

The Influence of Capital Structure, Company Growth and Company Value on Share Prices in Coal Sub-Sector Companies Listed on the Indonesian Stock Exchange 2018-2023

This study aims to empirically investigate the impact of Capital Structure, Company Growth, and Company Value on stock prices. Employing a quantitative descriptive research method with a verificative approach, the study utilizes panel data regression analysis to examine these relationships. The research focuses on Coal Sub-Sector Companies listed on the Indonesia Stock Exchange from 2018 to 2023, encompassing a sample of 12 companies. The findings reveal that Capital Structure negatively influences stock prices, indicating that higher debt levels may detract from stock value. Conversely, Company Growth is found to have no significant effect on stock prices, suggesting that growth metrics do not necessarily translate to market valuation in this sector. In contrast, Company Value exerts a positive impact on stock prices, demonstrating that higher valuation metrics are associated with increased stock prices. These results provide valuable insights for investors and stakeholders in the coal sub-sector, highlighting the critical factors that drive stock price movements and offering a basis for more informed investment decisions.

Pendekatan Metode Monte Carlo untuk Simulasi Pergerakan Harga Saham

This research applies the Monte Carlo simulation method to predict the movement of Apple Inc.'s stock price over a long period of time. Using historical data of Apple's stock price from 12 December 1980 to 24 March 2022, this study aims to generate a probability distribution of the future stock price. The method involves several steps, including data collection, log return calculation, parameter estimation, and simulation of the stock price path through random iterations based on the log return distribution. The simulation results show that the closing price of Apple stock can be predicted by following the historical trend, although there are differences with the real data due to the stochastic nature of the Monte Carlo technique. This research also applies a variance reduction method to improve simulation efficiency. The findings provide a valuable perspective for investors and financial analysts in identifying investment risks and opportunities through an in-depth understanding of the dynamics of stock price movements using Monte Carlo simulation. Suggestions for future research include the use of VaR methods with historical variance and covariance approaches, as well as considering longer data periods and more stock indices for more comprehensive results.

Cross-Sectional Variation of Option-Implied Volatility Skew

The stock option-implied volatility skew reflects both the structural risk characteristics of the underlying company and the short-term information flow about the stock price movement. This paper builds a semistructural, cross-sectional option pricing model to separate the structural risk contributions from the information flow. The model identifies two structural risk sources that contribute to the cross-sectional variation of the skew: the company’s business cyclicality and its default risk. The model can explain as much as 44% of the cross-sectional variation in implied volatility skew and is particularly informative during and after recessions. The remaining skew variation reflects mainly short-term information flow and can be used to construct stock portfolios with much better investment performance and without hidden structural risk exposures. This paper was accepted by Agostino Capponi, finance. Funding: L. Wu gratefully acknowledges support by a grant from the City University of New York PSC-CUNY Research Award Program. Supplemental Material: The online appendix and data are available at https://doi.org/10.1287/mnsc.2023.4872 .

Peran Profitabilitas, Likuiditas, Aktivitas, dan Leverage dalam Harga Saham

This research stems from the need to investigate the influence of financial factors, such as profitability, liquidity, activity, and leverage, on the share price of a company. The growing complexity of financial markets drives the need for a deeper understanding of the contribution of each factor to stock price dynamics. This research aims to identify and analyze the role of each financial factor of profitability, liquidity, activity and leverage in determining stock price movements. The research method used involves multivariable statistical analysis using historical financial data of companies listed on the stock market. This quantitative approach will help in dissecting the complex relationship between profitability, liquidity, activity, leverage, and stock price. This research produces significant findings regarding the impact of each financial factor on stock prices. An in-depth analysis will show to what extent profitability, liquidity, activity, and leverage influence a company's stock valuation. These results can be the basis for developing investment strategies that are smarter and responsive to market dynamics.

Macroeconomic shocks, market uncertainty and speculative bubbles: a decomposition-based predictive model of Indian stock markets

PurposeStock markets are essential for households for wealth creation and for firms for raising financial resources for capacity expansion and growth. Market participants, therefore, need an understanding of stock price movements. Stock market indices and individual stock prices reflect the macroeconomic environment and are subject to external and internal shocks. It is important to disentangle the impact of macroeconomic shocks, market uncertainty and speculative elements and examine them separately for prediction. To aid households, firms and policymakers, the paper proposes a granular decomposition-based prediction framework for different time periods in India, characterized by different market states with varying degrees of uncertainty.Design/methodology/approachEnsemble empirical mode decomposition (EEMD) and fuzzy-C-means (FCM) clustering algorithms are used to decompose stock prices into short, medium and long-run components. Multiverse optimization (MVO) is used to combine extreme gradient boosting regression (XGBR), Facebook Prophet and support vector regression (SVR) for forecasting. Application of explainable artificial intelligence (XAI) helps identify feature contributions.FindingsWe find that historic volatility, expected market uncertainty, oscillators and macroeconomic variables explain different components of stock prices and their impact varies with the industry and the market state. The proposed framework yields efficient predictions even during the COVID-19 pandemic and the Russia–Ukraine war period. Efficiency measures indicate the robustness of the approach. Findings suggest that large-cap stocks are relatively more predictable.Research limitations/implicationsThe paper is on Indian stock markets. Future work will extend it to other stock markets and other financial products.Practical implicationsThe proposed methodology will be of practical use for traders, fund managers and financial advisors. Policymakers may find it useful for assessing the impact of macroeconomic shocks and reducing market volatility.Originality/valueDevelopment of a granular decomposition-based forecasting framework and separating the effects of explanatory variables in different time scales and macroeconomic periods.

Long Short Term Memory Method and Social Media Sentiment Analysis for Stock Price Prediction

The stock market is a complex arena of interest yet uncertainty. Trading stocks, binaries, gold, and bitcoin is growing in popularity, but is prone to price fluctuations influenced by economic and political factors. Social media, particularly Twitter, is where views on companies are shared. Social media sentiment analysis can provide additional insights to evaluate potential future stock price movements, preventing unwanted speculation. The purpose of this research is to develop a Tesla stock price prediction model by integrating the Long Short-Term Memory (LSTM) method and social media sentiment analysis from Twitter to improve prediction accuracy. Stock price data is obtained from Kaggle and Twitter sentiment data is processed through pre-processing. Evaluation values such as Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) are lower in the model with sentiment indicating the ability of the model to more accurately model the dynamics of stock price movements. Lower MSE and RMSE indicate that the model's predictions are closer to the true values, and therefore, the model can be considered more reliable in projecting future stock price changes. These results provide support for the use of Twitter sentiment analysis as a useful source of additional information in improving the prediction accuracy of LSTM regression models in the context of stock market analysis

A Probabilistic Model for Predicting Stock Price Movements Using Bayesian Inference

A Probabilistic Model for Predicting Stock Price Movements Using Bayesian Inference

Heteroscedasticity effects as component to future stock market predictions using RNN-based models.

Heteroscedasticity effects are useful for forecasting future stock return volatility. Stock volatility forecasting provides business insight into the stock market, making it valuable information for investors and traders. Predicting stock volatility is a crucial task and challenging. This study proposes a hybrid model that predicts future stock volatility values by considering the heteroscedasticity element of the stock price. The proposed model is a combination of Generalized Autoregressive Conditional Heteroskedasticity (GARCH) and a well-known Recurrent Neural Network (RNN) algorithm Long Short-Term Memory (LSTM). This proposed model is referred to as GARCH-LSTM model. The proposed model is expected to improve prediction accuracy by considering heteroscedasticity elements. First, the GARCH model is employed to estimate the model parameters. After that, the ARCH effect test is used to test the residuals obtained from the model. Any untrained heteroscedasticity element must be found using this step. The hypothesis of the ARCH test yielded a p-value less than 0.05 indicating there is valuable information remaining in the residual, known as heteroscedasticity element. Next, the dataset with heteroscedasticity is then modelled using an LSTM-based RNN algorithm. Experimental results revealed that hybrid GARCH-LSTM had the lowest MAE (7.961), RMSE (10.466), MAPE (0.516) and HMAE (0.005) values compared with a single LSTM. The accuracy of forecasting was also significantly improved by 15% and 13% with hybrid GARCH-LSTM in comparison to single LSTMs. Furthermore, the results reveal that hybrid GARCH-LSTM fully exploits the heteroscedasticity element, which is not captured by the GARCH model estimation, outperforming GARCH models on their own. This finding from this study confirmed that hybrid GARCH-LSTM models are effective forecasting tools for predicting stock price movements. In addition, the proposed model can assist investors in making informed decisions regarding stock prices since it is capable of closely predicting and imitating the observed pattern and trend of KLSE stock prices.

Machine learning methods for financial forecasting and trading profitability: Evidence during the Russia–Ukraine war

PurposeThis study aims to evaluate the effectiveness of machine learning models to yield profitability over the market benchmark, notably in periods of systemic instability, such as the ongoing war between Russia and Ukraine.Design/methodology/approachThis study made computational experiments using support vector machine (SVM) classifiers to predict stock price movements for three financial markets and construct profitable trading strategies to subsidize investors’ decision-making.FindingsOn average, machine learning models outperformed the market benchmarks during the more volatile period of the Russia–Ukraine war, but not during the period before the conflict. Moreover, the hyperparameter combinations for which the profitability is superior were found to be highly sensitive to small variations during the model training process.Practical implicationsInvestors should proceed with caution when applying machine learning models for stock price forecasting and trading recommendations, as their superior performance for volatile periods – in terms of generating abnormal gains over the market – was not observed for a period of relative stability in the economy.Originality/valueThis paper’s approach to search for financial strategies that succeed in outperforming the market provides empirical evidence about the effectiveness of state-of-the-art machine learning techniques before and after the conflict deflagration, which is of potential value for researchers in quantitative finance and market professionals who operate in the financial segment.

Correlation Between News and Stock Price Based on Stock Market Indices: Can News Classification Be Used as a Tool to Make Better Decisions?

The stock market is influenced by various factors, including news events, economic indicators, and investor sentiment. Understanding the correlation between news and stock price movements interests market participants and researchers. In this paper, we explore the relationship between news sentiment and stock market trends using stock market indices. We employ natural language processing (NLP) techniques to classify news articles and analyze their impact on stock market indices, focusing on the S&P 500 and the Dow Jones Industrial Average. We utilize sentiment analysis and machine learning algorithms, including Random Forest, Loughran-McDonald (2014) Financial Sentiment Word Lists (Extended), and AFINN Lexicon, to predict stock market trends based on news sentiment. Our findings demonstrate that positive news sentiment has a more significant impact on stock prices than negative sentiment. The Random Forest model achieves the highest accuracy, while domain-specific lexicons provide valuable insights into financial news sentiment. However, predicting negative trends remains a challenge across all methods. Our research contributes to the growing knowledge of the relationship between news and stock prices and provides valuable insights for market participants and researchers.

Factors affecting Stock Price Behaviour of Commercial Banks in Nepal Stock Exchange

This research investigates how factors such as Dividends Per Share (DPS), Earnings Per Share (EPS), Price-Earnings Ratio (PER), and Net Worth Per Share influence the Market Price Per Share of commercial banks in Nepal. The study analyzed the panel data from four commercial banks, consisting of 40 observations, to evaluate the correlation and influence of factors affecting stock price movements. In this study, secondary panel data covering ten years (2070/2071-2079/2080) has been used. Based on the results of this investigation, there is a significant positive correlation between the Market Price Per Share and the Dividends Per Share, Price-Earnings Ratio, and Net Worth Per Share but a negligible effect of Market Price Per Share and Earnings Per Share of commercial banks.

An adaptive dual-level reinforcement learning approach for optimal trade execution

The purpose of this research is to devise a tactic that can closely track the daily cumulative volume-weighted average price (VWAP) using reinforcement learning while minimizing the deviation from the VWAP. Previous studies often choose a relatively short trading horizon to implement their models, making it difficult to accurately track the daily cumulative VWAP since the stock price movement is often insignificant within the short trading horizon. On the other hand, training reinforcement learning models directly over a longer, daily horizon is burdensome due to extensive sequence length. Hence, there is a need for a method that can divide the long daily horizon into smaller, more manageable segments. We propose a method that leverages the U-shaped pattern of intraday stock trade volumes and uses Proximal Policy Optimization (PPO) as the learning algorithm. Our method follows a dual-level approach: a Transformer model that captures the overall (global) distribution of daily volumes in a U-shape, and a LSTM model that handles the distribution of orders within smaller (local) time intervals. The results from our experiments suggest that this dual-level architecture improves cumulative VWAP tracking accuracy compared to previous reinforcement learning approaches. The key finding is that explicitly accounting for the U-shaped intraday volume pattern leads to better performance in approximating the cumulative daily VWAP. This has implications for developing trading strategies that need to efficiently track VWAP over a full trading day.