Stock Movement Research Articles

ECHO-GL: Earnings Calls-Driven Heterogeneous Graph Learning for Stock Movement Prediction

Stock movement prediction serves an important role in quantitative trading. Despite advances in existing models that enhance stock movement prediction by incorporating stock relations, these prediction models face two limitations, i.e., constructing either insufficient or static stock relations, which fail to effectively capture the complex dynamic stock relations because such complex dynamic stock relations are influenced by various factors in the ever-changing financial market. To tackle the above limitations, we propose a novel stock movement prediction model ECHO-GL based on stock relations derived from earnings calls. ECHO-GL not only constructs comprehensive stock relations by exploiting the rich semantic information in the earnings calls but also captures the movement signals between related stocks based on multimodal and heterogeneous graph learning. Moreover, ECHO-GL customizes learnable stock stochastic processes based on the post earnings announcement drift (PEAD) phenomenon to generate the temporal stock price trajectory, which can be easily plugged into any investment strategy with different time horizons to meet investment demands. Extensive experiments on two financial datasets demonstrate the effectiveness of ECHO-GL on stock price movement prediction tasks together with high prediction accuracy and trading profitability.

MDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment Prediction

The stock market is a crucial component of the financial system, but predicting the movement of stock prices is challenging due to the dynamic and intricate relations arising from various aspects such as economic indicators, financial reports, global news, and investor sentiment. Traditional sequential methods and graph-based models have been applied in stock movement prediction, but they have limitations in capturing the multifaceted and temporal influences in stock price movements. To address these challenges, the Multi-relational Dynamic Graph Neural Network (MDGNN) framework is proposed, which utilizes a discrete dynamic graph to comprehensively capture multifaceted relations among stocks and their evolution over time. The representation generated from the graph offers a complete perspective on the interrelationships among stocks and associated entities. Additionally, the power of the Transformer structure is leveraged to encode the temporal evolution of multiplex relations, providing a dynamic and effective approach to predicting stock investment. Further, our proposed MDGNN framework achieves the best performance in public datasets compared with the state-of-the-art stock investment methods.

Returns and Risks in Dynamic Stocks

In the current scenario of high volatility in the stock exchange, it's crucial for investors to make informed decisions. The surge of millennial investors into the market, aiming for substantial returns, highlights the importance of a solid grasp of statistical tools and measures for sound decision-making. This study delves into the risk and return analysis of various stocks alongside their benchmark indices to decode the stock movements in relation to the market. The primary goal for any investor is to amplify profits while minimizing risks. This research aids investors by offering insights into various statistical methods for analyzing stock risks and returns. The research concentrated on gathering daily data, including the closing prices of stocks from 2019 to 2023, from the stock market. It calculated the daily returns of these stocks and measured their standard deviations, focusing on key sectors such as Automobile, Banking, Finance, FMCG, and IT. These sectors are pivotal in reflecting the country's economic health. Further analysis was conducted using beta and regression analysis to assess the risk associated with the indices compared to market indices like NIFTY AUTOMOBILE, BANK NIFTY, NIFTY FINANCE, NIFTY FMCG, and NIFTY IT Service. This helped in understanding the indices' performance versus the benchmark indices and integrating various statistical tools to differentiate the risk and return profiles across sectors. The study aims to identify which sector presents a favorable investment opportunity in terms of risk and return.

A large-scale microblog dataset and stock movement prediction based on Supervised Contrastive Learning model

The integration of Deep Neural Networks (DNN) with Natural Language Processing (NLP) technologies has opened new avenues in financial market prediction, particularly through the utilization of textual information. This study represents a significant advancement, which offers two primary contributions to stock trend prediction: (i) the exploitation of textual data (news, comments, microblogs) using advanced DNN architectures, enhancing market information utilization; (ii) significant improvement of the accuracy of predicting the direction of stock volatility by integrating textual and neural network technologies. Meanwhile, we have crawled, filtered, and constructed a large-scale microblog dataset. This dataset includes approximately 114,992 microblog textual data from 40 Science and Technology Innovation Board (STIB) companies in China during 2021. We conducted a comprehensive analysis using various DNN techniques, including Feedback Neural Networks (FNN), Supervised Contrastive Learning (SCL), Cross Entropy (CE), and Dual Contrastive Learning (DualCL), in conjunction with bag of words models, BERT, and Roberta compilers. Our findings reveal that the SCL method, when combined with microblog data, significantly increases prediction accuracy, particularly during the COVID-19 period. Furthermore, we discovered that using a cross-stock dataset enhances the accuracy of all prediction methods, and random allocation of microblog data leads to better results than sequential allocation. Additionally, we compared the efficacy of traditional models like the CAPM, three-factor, and five-factor models against neural network-based methods. Our results suggest a notable superiority of the SCL method in increasing prediction accuracy. Finally, applying our findings to real-world trading strategies, we demonstrated the practical advantages of using the SCL method in trading, evidenced by significant improvements across all performance indicators.

A Comparative Analysis of Risk and Return Among chosen companies against the Benchmark Index in NSE.

In the current scenario of high volatility in the stock exchange, it's crucial for investors to make informed decisions. The surge of millennial investors into the market, aiming for substantial returns, highlights the importance of a solid grasp of statistical tools and measures for sound decision-making. This study delves into the risk and return analysis of various stocks alongside their benchmark indices to decode the stock movements in relation to the market. The primary goal for any investor is to amplify profits while minimizing risks. This research aids investors by offering insights into various statistical methods for analyzing stock risks and returns.

Modelling Stock Prices of Energy Sector using Supervised Machine Learning Techniques

This paper aims at comparing the performance of the different state-of-the-art machine learning techniques in anticipating the performance of stock prices of the energy sector. The data collected cover the period from January 2020 to February 2023 with a daily frequency for the three most imported refined petroleum products in Morocco and trained four regression machines learning (linear regression, lasso regression, ridge regression, and SVR) and four classifiers machine learning (logistic regression, decision tree, extra tree and Random Forest) so that anticipating one day ahead prices direction can take place no matter whether they are negative or positive prices. The performance of regression algorithm is then evaluated using different evaluation metrics, especially MSE, RMSE, MAE, MAPE and R2 to evaluate the performance of regression algorithm while precision, recall and F1 scores are used to evaluate the performance of classifiers algorithm. The outcomes propose that the performance of linear regression and ridge regression takes place equally and outperform other single regression that is lasso regression and SVR for-one-day predictions as a whole. In addition to that, we have come to find that in the classifiers, algorithms group all machine learning display similar predictive accuracy, this is on one hand. On the other hand, the best of them is the logistic regression. In brief, this study suggests that all performance metrics are significantly improved by ensemble learning. Therefore, this study proves that critical information affecting stock movement can be captured by utilizing historical transactions.

Artificial Intelligence in stock broking: A systematic review of strategies and outcomes

Artificial Intelligence (AI) has emerged as a transformative force in the field of stock broking, revolutionizing traditional trading strategies and reshaping financial markets. This systematic review delves into the diverse array of AI-driven strategies employed in stock broking and assesses their outcomes, shedding light on the evolving landscape of algorithmic trading. The study encompasses a comprehensive analysis of various AI models, including machine learning algorithms, deep neural networks, and natural language processing techniques, that have been harnessed to analyze market data, predict stock movements, and optimize trading decisions. By synthesizing existing literature, the review offers insights into the effectiveness and limitations of these strategies, providing a nuanced understanding of their impact on market dynamics. Key findings reveal that AI applications in stock broking exhibit a wide spectrum of approaches, ranging from predictive modeling for price forecasting to sentiment analysis for gauging market sentiment. The review also explores the integration of reinforcement learning in algorithmic trading, highlighting the adaptive nature of AI systems in responding to dynamic market conditions. Furthermore, the outcomes of AI-driven strategies are evaluated in terms of risk management, profitability, and overall market efficiency. The review identifies trends indicating increased efficiency and reduced human biases, but also acknowledges challenges related to model interpretability, ethical considerations, and the potential for algorithmic-driven market volatility. This systematic review contributes to the evolving discourse on the role of AI in stock broking, offering a holistic examination of strategies and outcomes. As financial markets continue to embrace technological advancements, understanding the nuances of AI applications becomes paramount for market participants, regulators, and researchers alike. This study serves as a valuable resource for stakeholders seeking to navigate the complex interplay between artificial intelligence and the stock broking landscape.

REVISITING WEAK-FORM EFFICIENCY OF MAJOR SECTORS OF MALAYSIA DURING THE COVID-19 PERIOD

There are plenty of literature on the efficient market hypothesis (EMH) especially for a stock market, but relatively fewer studies for across sectors. We look into the weak-form informational efficiency for twelve sectors in the Malaysia’s stock exchange, i.e. Consumer Products & Services (KLCSU), Construction (KLCON), Energy (KLENG), Financial Services (KLFIN), Health Care (KLHEAL), Industrial Products & Services (KLPRO), Property (KLPRP), Plantation (KLPLN), Transportation & Logistics (KLTRAN), Telecommunications & Media (KLTEL), Utilities (KLUTL), and Technology (KLTEC) during the outbreak of COVID-19 pandemic. We use QTEST (without trend) and TQTEST (with trend) which incorporate two structural breaks to carry out the analysis. Data are collected from 1/1/2020 through 31/3/2022. These indices show non-linearity and structural breaks in data. The findings of our study suggest mixed results in regard to informational efficiency when breaks are taken. Four indices, i.e. KLCON, KLFIN, KLPRP, and KLUTL are found to be inefficient while the remaining eight sectors are found to be efficient. Investors can predict the movements of stocks in the inefficient indices and are able to gain abnormal returns from these stocks. Policymakers may encourage investors to have more trades; so that to make the market more efficient by gradually eliminating the opportunities on earning abnormal returns.

Stock movement prediction: A multi‐input LSTM approach

AbstractGenerally, the nonlinear and non‐stationary financial time series becomes an obstacle in the process of stock movement prediction. But the recent theories of machine learning and deep learning have provided with some new solutions. Based on LSTM (long short‐term memory), we propose a hybrid model of wavelet transform (WT) and multi‐input LSTM to predict the trend of SSE composite index. It can mine valid data in time series and support different types of data as input. The whole model is divided into two stages. In the first stage, we adopt the level 1 decomposition with db4 mother wavelet to eliminate noise. In the second stage, combinative and qualitative analysis was made base on the data from Chinese stock market, US stock market, and technical indicators as input. According to the result, the proposed model, with the accuracy of 72.19%, performs better than single‐input LSTM, decision tree, random forest, Support Vector Machine (SVM), and XGBoost.

The Research of NVIDIA Stock Price Prediction Based on LSTM And ARIMA Model

The paper explores stock forecasting methods using NVIDIA as the research object. It contrasts how well LSTM and ARIMA models forecast NVIDIA's stock return. According to the study, LSTM surpasses ARIMA in terms of prediction accuracy. However, both models capture the overall trend of the stock. The results suggest that LSTM is better suited for forecasting stock movements due to its ability to handle time series data. The non-stationary nature of the stock market adds complexity to predictions. The significance of stock forecasting is that informed investment decisions can be made to maximise financial returns. Stock forecasting aims to predict the future performance of individual stocks, market sectors or the market as a whole based on various factors such as historical data, market trends, company fundamentals and economic indicators. By analysing and forecasting stock movements, investors can identify opportunities to buy low and sell high, optimise their portfolios and potentially outperform the broader market. Successful stock forecasting can help investors make more informed decisions, reduce risk and improve their chances of achieving their financial goals.

GAN-Enhanced Nonlinear Fusion Model for Stock Price Prediction

Stock price prediction is a significant field of finance research for both academics and practitioners. Numerous studies have proved that the stock movement can be fully reflect various internal features of stock price including non-stationary behavior, high persistence in the conditional variance. The fusion of time-series prediction model such as Auto-Regressive Integrated Moving Average (ARIMA) and neural network is an availability but difficult approach for stock price prediction. Although the orientation has been studied through some methods in different research, there are still difficulties with the poor capture ability of time-series features and insufficient effectiveness of integrating temporal feature and frequency domain information. In this paper, we propose a Generative Adversarial Network (GAN) framework with the Convolution Neural Networks (CNN) as the discriminator and a hybrid model as the generator for forecasting the stock price. The hybrid model includes Attention-based Convolution Neural Networks (ACNN), Long Short-Term Memory (LSTM), and ARIMA model. Moreover, this proposed framework uses the Generative Adversarial patten and Attention Mechanism to achieve effective analysis and feature extraction for stock price movement. The extensive experiments in different history periods of dataset demonstrate an improvement in forecasting of stock price using our model as compared to the baseline models.

WINTERS EXPONENTIAL SMOOTHING UNTUK FORECASTING HARGA SAHAM PT ASTRA INTERNATIONAL TBK

Investing in the stock market is one of the investment options that are in great demand by investors. Investors generally invest because want to gain profits which can be seen from the stock returns. On the other hand, there is a risk of loss if the investor makes the wrong decision. Investors need accurate information, predictions and a sense of security in stock transactions. Investors or shareholders need to know the development of stock prices in the future with forecasts to anticipate large losses. This study aims to predict the share price of PT. Astra International Tbk (ASII.JK) one year ahead using the winters exponential smoothing method. Forecasting results show that ASII's share price for the next year will increase every month. This can provide information on future stock movements for investors as a consideration for investing in these stocks.

Enhancing the Prediction of Stock Market Movement Using Neutrosophic-Logic-Based Sentiment Analysis

Social media platforms have allowed many people to publicly express and disseminate their opinions. A topic of considerable interest among researchers is the impact of social media on predicting the stock market. Positive or negative feedback about a company or service can potentially impact its stock price. Nevertheless, the prediction of stock market movement using sentiment analysis (SA) encounters hurdles stemming from the imprecisions observed in SA techniques demonstrated in prior studies, which overlook the uncertainty inherent in the data and consequently directly undermine the credibility of stock market indicators. In this paper, we proposed a novel model to enhance the prediction of stock market movements using SA by improving the process of SA using neutrosophic logic (NL), which accurately classifies tweets by handling uncertain and indeterminate data. For the prediction model, we use the result of sentiment analysis and historical stock market data as input for a deep learning algorithm called long short-term memory (LSTM) to predict the stock movement after a specific number of days. The results of this study demonstrated a predictive accuracy that surpasses the accuracy rate of previous studies in predicting stock price fluctuations when using the same dataset.

A comparative study of symbolic aggregate approximation and topological data analysis

<p>The movement of stocks is often perceived as random due to the complex interactions between different stocks and the inherently chaotic nature of the market. This study investigated the similarity in stock movements across multiple industry sectors in Europe. Specifically, we applied topological data analysis (TDA) to analyze stock time series data and compared the results with those obtained using an expanded form of a more classical time series analysis method, symbolic aggregate approximation (SAX). Our findings indicated that while TDA offered detailed insights into "local" stock movements, SAX was more effective in capturing broader trends in financial markets, where less detail was required, making it suitable for portfolio optimization. We also presented an extension of SAX that incorporated volatility measures, improving its performance in highly volatile markets.</p>

Exploring fluctuations and interconnected movements in stock, commodity, and cryptocurrency markets

Abstract This research employs a vector autoregression (VAR) analysis to explore the volatility and dynamic interactions between stock, commodity, and cryptocurrency markets. It focuses on the returns of the S&P 500, gold, crude oil, and Bitcoin to analyse their interconnections. Our results indicate that Bitcoin returns positively affect S&P 500 and crude oil, but negatively impact gold. Conversely, crude oil returns have a positive influence on gold but lead to decreased returns for Bitcoin and the S&P 500. Similarly, higher gold returns correspond to increased returns in crude oil and S&P 500 but decreased returns in Bitcoin. The rise of the S&P 500 negatively influences Bitcoin and crude oil returns, while gold returns remain unaffected. However, these relationships exhibit weak and limited strength. Including these assets in a portfolio can help risk mitigation, as Bitcoin diversifies crude oil, gold, and S&P 500, and crude oil diversifies S&P 500. These findings contribute to our understanding of global financial dynamics and inform decision-making in risk assessment, portfolio management, risk mitigation, and diversification strategies.

Multimethod computing technology for searching energy-optimal motion modes of electric rolling stock of railways

The article is devoted to the problem of finding energy-optimal modes of movement of electric rolling stock of railways, considered as a set of problems of finding a global extremum of a functional defined on a set of logical-dynamic system (LDS) movement trajectories that are acceptable under operating conditions, and a structural-parametric synthesis of the LDS control strategy and optimization of its parameters based on random search methods, swarm intelligence, evolutionary algorithms and multi-agent models. A multi-method technology for optimizing the modes of train movement according to the criterion of minimum energy consumption, and software and algorithmic support based on the original multi-agent evolutionary-swarm method for synthesizing the optimal-terminal control of multi-mode moving objects developed by the author are proposed. The specified computing technology includes the following stages: formation of a set of promising control strategies; their optimization and recombination based on the evolutionary genetic algorithm; finding the global extremum of the functional using parametric optimization of the solutions identified at the previous stages using the modified particle swarm method. The computational experiments performed with the simulation model of train movement showed that when a sufficiently large number of options for control strategies are generated at the first stage, the algorithm converges to the global extremum of the functional.

АНАЛИЗ ИНФОРМАЦИОННЫХ ТЕХНОЛОГИЙ УПРАВЛЕНИЯ ПРИ ПЕРЕВОЗКАХ ОПАСНЫХ ГРУЗОВ В РОССИИ И ЗА РУБЕЖОМ

The research work examines the issues of managing the transportation of dangerous goods using information technologies that can improve efficiency and reliability. Monitoring the movement of special rolling stock during the transportation of dangerous goods is a key element of effective management. The monitoring system provides a real-time mode or a specified frequency to obtain information about the location, status and condition of the vehicle, which allows you to make optimal management decisions.

Математическое моделирование адаптивного торможения высокоскоростного поезда с дисковым тормозом

Based on the analysis of the dependence of the brake pad pressure reserve coefficient on the speed of movement of the rolling stock, a simulation computer simulation of the adaptive braking control system of a high-speed train was performed. The dependence of the pressure in the brake cylinder on the set value of the coefficient is found. The simulation results showed that the use of the adaptive braking algorithm makes it possible to shorten the braking distance, reduce the likelihood of wheelsets jamming and ensure the comfort level of passengers when braking a train. The study was carried out within the framework of the state-sponsored project «Adaptive automatic control system with increased efficiency for passenger and high-speed trains» No. 121050600026-9 dated 06.05.2021.

Spatial-Temporal Stock Movement Prediction and Portfolio Selection based on the Semantic Company Relationship Graph

Spatial-Temporal Stock Movement Prediction and Portfolio Selection based on the Semantic Company Relationship Graph

Pengaruh Profitabilitas terhadap Harga Saham

The capital market plays a crucial role in supporting economic growth, enabling the trading of stocks and bonds. Investment in the capital market involves technical and fundamental analysis, with financial reports significantly influencing stock prices and investor returns. Macroeconomic factors and company performance also impact stock movements. Fundamental financial ratios play a central role in determining stock values. The aim of this research is to examine the effects of fundamental financial ratios such as GPM, PMR, ROA, ROE, and ROS on stock prices. The sampling method used is purposive sampling. In the analysis, this study applies multiple linear regression, including measures of determination coefficients, F-tests, and t-tests. Before hypothesis testing, initial steps involve descriptive statistical analysis and testing classical assumptions to ensure that data is free from assumptions such as normality, multicollinearity, heteroskedasticity, and autocorrelation. The population studied consists of industrial and manufacturing companies in Indonesia, with the sample comprising manufacturing companies in the mining sub-sector listed on the Indonesia Stock Exchange (IDX) during the period from 2018 to 2021. The research findings conclude that ROA has a significant negative impact on stock prices, while ROE has a positive but insignificant impact. GPM also has a positive but insignificant impact on stock prices, as does NPM. On the other hand, ROS has a significant negative impact on stock prices. For future research, other factors that may influence stock prices and their impact on the variables under study can be considered