Stock Price Movements Research Articles

Harmonizing Macro-Financial Factors and Twitter Sentiment Analysis in Forecasting Stock Market Trends

The surge in generative artificial intelligence technologies, exemplified by systems such as ChatGPT, has sparked widespread interest and discourse prominently observed on social media platforms like Twitter. This paper delves into the inquiry of whether sentiment expressed in tweets discussing advancements in AI can forecast day-to-day fluctuations in stock prices of associated companies. Our investigation involves the analysis of tweets containing hashtags related to ChatGPT within the timeframe of December 2022 to March 2023. Leveraging natural language processing techniques, we extract features, including positive/negative sentiment scores, from the collected tweets. A range of classifier machine learning models, encompassing gradient boosting, decision trees and random forests, are employed to train on tweet sentiments and associated features for the prediction of stock price movements among key companies, such as Microsoft and OpenAI. These models undergo training and testing phases utilizing an empirical dataset gathered during the stipulated timeframe. Our preliminary findings reveal intriguing indications suggesting a plausible correlation between public sentiment reflected in Twitter discussions surrounding ChatGPT and generative AI and the subsequent impact on market valuation and trading activities concerning pertinent companies, gauged through stock prices. This study aims to forecast bullish or bearish trends in the stock market by leveraging sentiment analysis derived from an extensive dataset comprising 500,000 tweets. In conjunction with this sentiment analysis derived from Twitter, we incorporate control variables encompassing macroeconomic indicators, Twitter uncertainty index and stock market data for several prominent companies.

Mechanisms of Stock Selection and Its Capital Weighing in the Portfolio Design Based on the MACD-K-Means-Mean-VaR Model

When designing a stock portfolio, investors must select stocks with different characteristics and increasing price trends and weigh each capital. Both are fundamental to diversifying loss and profit. Therefore, the mechanisms that accommodate both are needed. Based on this, this research aims to design a stock selection and capital weighing mechanism using the MACD-K-means-Mean-VaR model. The moving average convergence–divergence (MACD) is used to analyze stock buying time, providing trend, momentum, and potential price reversal insights. Then, stocks with increasing price trends are clustered using K-means, a grouping simple pattern data method based on specific characteristics. The best stocks from each cluster are capital weighted using the mean value at risk (mean-VaR), a portfolio optimization model adjusting loss possibility to the investor’s acceptance tolerance. The mechanism is then applied to Indonesia’s 100 stock index data to analyze variable sensitivities and compare it with another model. The application reveals that all variables significantly impact portfolio return mean and VaR, suggesting the need for clustering and analyzing stock price movements in stock portfolio design. This research academically develops a portfolio design mechanism by clustering stocks and analyzing price movement trends. It enables investors to practically diversify and choose stocks with increasing price trends, reducing losses and increasing profit opportunities.

Technical Analysis of Stock Investment Decisions in Telecommunication Companies Listed on the Indonesian Stock Exchange

This research aims to examine stock investment decisions in telecommunications companies listed on the Indonesia Stock Exchange using a technical analysis approach. This research does not use hypotheses, so quantitative descriptive research is used. The purposive sampling method was used to obtain a representative sample in accordance with the sampling criteria, namely telecommunications companies listed on the Indonesia Stock Exchange. The object of the research is data in the form of graphs and trends in monthly stock price movements of three issuers in the fourth quartile of 2023 starting from October-December 2023. The research results show that the analysis of the three stocks above shows that MACD crossovers often give false signals if they are not confirmed by indicator movements momentum like RSI. In the case of TLKM and ISAT, even though the MACD has crossed over, the RSI actually moves in the opposite direction or at least does not provide a strong response, so there is potential for a reversal. Likewise with EXCL where even though a MACD crossover occurred, the RSI did not penetrate a significant level to validate the signal. Overall, MACD crossovers without the support of evidence of changes in momentum from the RSI tend to be weak and inaccurate. It takes confirmation from other indicators for a MACD crossover to truly indicate a long-term trend change instead of just a high-risk temporary move. Thus, it is important to carry out multi-factor validation so that the MACD crossover signal is stronger before being used as a reference for entry or exit positions.

Leveraging on Synthetic Data Generation Techniques to Train Machine Learning Models for Tenaga Nasional Berhad Stock Price Movement Prediction

This study employs machine learning models to explore stock price prediction for Tenaga Nasional Berhad (TNB), Malaysia’s primary electricity provider. It addresses the limitations of previous studies by incorporating various input variables, including the stock market, technical, financial, and economic data. This study also tackles the issue of imbalanced class distribution due to small datasets of stock market data by generating synthetic data using Synthetic Minority Over-Sampling Technique (SMOTE) and Generative Adversarial Network-Synthetic Minority Over-Sampling Technique (GAN-SMOTE) techniques. The performance of four classifier models (random forest, Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Artificial Neural Network (ANN)) is evaluated without any synthetic data and with synthetic data generated. The SMOTE-ANN model is the best-performing model, exhibiting superior accuracy of 93%, F1-Score of 92%, precision of 90%, recall of 94%, and specificity of 92%. Overall, this research provides valuable insights into TNB stock price movements, offers a solution for imbalanced class distribution, and identifies the top-performing model for predicting TNB stock price movement. These findings are relevant to investors, analysts, and organisations in the utility sector.

The effects of exploration and exploitation on stock price movement: the moderating effect of firm size and market condition

The effects of exploration and exploitation on stock price movement: the moderating effect of firm size and market condition

The effects of exploration and exploitation on stock price movement: the moderating effect of firm size and market condition

The effects of exploration and exploitation on stock price movement: the moderating effect of firm size and market condition

Above Up, Below Down: The Impact of Limit Order Clustering on Stock Price Movements

Above Up, Below Down: The Impact of Limit Order Clustering on Stock Price Movements

PERAMALAN HARGA SAHAM NVIDIA DENGAN METODE DOUBLE MOVING AVERAGE

The movement of NVIDIA's stock price greatly affects investment decisions, so accurate forecasting is very important to influence investment decisions. This research will apply the data mining process for forecasting NVIDIA stock prices using the Double Moving Average method with the application of order 2 and order 3 models. The purpose of this study is to determine the forecasting of the NVIDIA stock price index based on historical data. The results show that stock price forecasting using the Double Moving Average method order 2 model is more accurate and in accordance with actual or actual results. On the other hand, forecasting the Double Moving Average method with the order 3 model produces unsatisfactory forecasts that can be used, making it less suitable for dynamic markets. Therefore, the results of forecasting NVIDIA stock prices using the Double Moving Average method order 2 obtained an accuracy of 98% compared to order 3 of 67%. Based on the comparison results of using orders 2 and 3, it can be an important factor for investors to help make investment decisions in terms of forecasting the next production of NVIDIA shares.

Machine learning and deep learning predictive models for the stock market

Accurately predicting the movement of stock prices can help people make more informed investment decisions and thus obtain higher returns. They can also assess market trends, develop investment strategies and provide investment advice. In this paper, we used 5 models including Random Forest, XGBoost, ANN, RNN, LSTM to predict and verify the fit of 3 companies (AMZN, BABA and MSFT). It is found that LSTM and random forest model can predict well in most cases. The development of the financial industry does have some shortcomings, and the future financial field will be a field full of challenges and opportunities, so some machine learning and deep learning methods can be used to solve the prediction and modeling problems of financial aspects such as the stock market.

A Hybrid GARCH and Deep Learning Method for Volatility Prediction

Volatility prediction plays a vital role in financial data. The time series movements of stock prices are commonly characterized as highly nonlinear and volatile. This study is aimed at enhancing the accuracy of return volatility forecasts for stock prices by investigating the prediction of their price volatility through the integration of diverse models. Thus, the study integrated four powerful methods: seasonal autoregressive (AR) integrated moving average (MA), generalized AR conditional heteroskedasticity (ARCH) family models, convolutional neural network (CNN), and bidirectional long short‐term memory (LSTM) network. The hybrid model was developed using the residuals generated by the seasonal AR integrated MA model as input for the generalized ARCH model. Following this, the estimated volatility obtained was utilized as an input feature for both the hybrid CNNs and bidirectional LSTM models. The model’s forecasting performance was assessed using key evaluation metrics, including mean absolute error (MAE) and root mean squared error (RMSE). Compared to other hybrid models, our new proposed hybrid model demonstrates an average reduction in MAE and RMSE of 60.35% and 60.61%, respectively. The experimental results show that the model proposed in this study has good performance and accuracy in predicting the volatility of stock prices. These findings offer valuable insights for financial data analysis and risk management strategies.

Long Short-Term Memory and Gated Recurrent Unit for Stock Price Prediction

Stocks are a popular investment with high risk due to rapid price fluctuations that are difficult to predict. Many investors do not understand the analysis of buying and selling stocks, making them hesitant to invest. For this reason, an analytical technique is needed that can determine the movement of stock prices in order to carry out planning, risk management, and decision-making. Banking stocks are among the important and popular stock sectors. One of the go public banking stocks is Bank Rakyat Indonesia stock. This research applies Long Short-Term Memory and Gated Recurrent Unit to produce a model that can accurately predict the stock price of Bank Rakyat Indonesia. Based on the implementation, GRU is the best model with MSE value of 4958.9168, RMSE 70.4195, and MAPE 1.1699%. The GRU model predict that there will be a decrease in stock prices in the next month.

The Effect of AI Development on Stock Prices

The period from 2019 to 2024 has been marked by tremendous progress in AI. During the late 1990’s and the 2000s, there was a ‘.com’ bubble: excitement about the rise in internet led to the stock prices of US tech companies to rise tremendously. Eventually, this bubble burst, leading to huge losses. 2023 saw a similar rise in the share prices of AI companies. This led to people speculating whether an ‘AI bubble’ is forming, similar to the ‘.com bubble’ of the 2000s. Therefore, to investigate this phenomenon, the paper will compare stock price movements for companies that develop AI products and those that don't. For this purpose, the stock prices of the top 25 companies from the S&P 500 have been selected based on their index weight, after which the companies were classified as AI companies and non-AI companies. Then, the graphs were drawn using the R programming language to compare the stock prices. From this, it was seen that companies that have been classified as AI saw a boost in their stock prices due to AI-related products, mergers, acquisitions, development of generative AI, and dependence on technology during the COVID-19 pandemic, as compared to the stock prices of non-AI companies.

Fama’s model of efficient market: Analysis of the performance of insurance companies and the insurance stock price movement in Nigeria

The study analyzed the performance of insurance companies and the insurance stock price movement in Nigeria using Fama’s model of efficient market approach. Lack of information about insurance stock prices movement can influence investor’s decision making on insurance stock investments. An ex post facto research design was employed in the study. The research covers the activities of 19 insurance companies that are listed on the Nigerian Stock Exchange as at December 31, 2022. The data sample of the study comprises of daily stock prices data of 19 listed insurance companies for the period January 4, 2022 December 30, 2022. Fama-French three factor coefficient estimates obtained from quantile regression was used to test the hypothesis. The results revealed that there is a significant relationship between the insurance stock price movement and the performance of insurance companies in Nigeria, and that such relationship is negative. Recommendations were that there should be perfect information about stock market forces of demand and supply because if there is information asymmetry through which borrowers (securities issuers) know more about the risks than the lenders to (securities purchasers), the market participants may be reluctant to trade with insurance stocks, whose characteristics and behaviour under varying economic conditions are not well known. Also, it is important for the regulator in formulating policies that encourage diversification of investments among others.

Clustering and Financial Performance Analysis of Indonesian Coal Mining Industry Stock Prices

In the comprehensive study of the Indonesian coal mining industry, a rigorous exploration and clustering approach was applied to historical stock price data and financial metrics from coal companies listed for over a decade. Data sourced from Yahoo Finance underwent an automated download process, ensuring consistency and efficiency. The research utilized robust clustering techniques, including K-means, Hierarchical, and Correlation Clustering, to discern the stock price movements during the dynamic market conditions of 2022 and 2023. Financial performance analysis, focusing on key metrics such as ROA, NPM, and EPS, highlighted the unique financial dynamics of companies like PTIS, IATA, and AIMS. The study's results provide a multifaceted understanding of the coal industry's financial trends, emphasizing varied company responses to market conditions and revealing significant financial performance divergences among key players. This research not only offers invaluable insights into the coal industry's financial landscape but also presents an innovative methodology poised to transform financial analytics in the sector.

Stock price volume leap principle based on investor sentiment contagion model

The rise and fall of the Chinese stock market has been the subject of many studies since its inception. However, the recurring uncertainty of the broad market and individual stocks has overturned many people’s perceptions of the financial market. This paper explores the principles of the rise and fall of individual stocks under certain conditions, starting from Samuelson’s phenomenon of backward bending of the price supply curve for oil and labour, and proposes a methodology for stock market investment based on this principle. The results of the study show that the rise of stock prices is often characterized by a rapid jump. An important factor related to this is the interest rate of private lending. The rise and fall of private lending rates affect the expected return on stock market investment funds and has an important impact on stock market investment. Therefore, in the absence of a qualitative change in the stock’s texture, the medium-term rate of increase is the key to judging the stock price’s later trend. The results of this study provide a new direction to think about when judging the short- and medium-term stock price movements.

Predicting stock market by sentiment analysis and deep learning

The stock market may be unpredictable; understanding when to purchase and sell can greatly assist businesses and individuals in maximizing profits and minimizing losses. Many companies have previously modified time-series analysis, a data mining technique, to forecast stock price movement. The idea of textual data mining has recently come up in debates about stock market forecasts. In this study, five of the largest firms’ historical stock prices were used to train two deep learning models—long short-term memory (LSTM) and one-dimensional convolutional neural network (1D CNN), then the results of all the models were compared. To connect price value fluctuations with the general public, sentiment scores were offered in addition to stock price values by employing natural language processing techniques (TextBlob) to tweets.

Calculation Option Price on Shares PT. Nippon Indosari Corpindo Tbk. with Fuzzy Binomial Tree Model

The Cox-Ross-Rubinstein binomial tree model is widely used in stock and derivative securities calculations, such as options calculations. The binomial CRR model assumes that the parameter increases in option prices and decreases in option prices so this model produces stock price movements up and down stock price movement. However, stock price movements show price fluctuations and cause the volatility of the value to be unsuitable. In this study, modeling stock and option price movements using a fuzzy binomial tree model. The data used was data on the movement of the stock price of Nippon Indosari Corpindo Ltd Plc from February 2021 to January 2022. The results showed that for February 2022, with a risk size of 90%, the selling price options with the greatest volatility of 51.6484081, medium volatility of 33.33154354, and the smallest volatility of 28.17155892.

Navigating GPT-4 and BERT: A Dual Perspective on Financial and Political Sentiment Analysis

Abstract: This research delves into the dynamic capabilities of large language models (LLMs) by combining insights from two distinct studies. The first study, "Linking Microblogging Sentiments to Stock Price Movement: An Application of GPT-4," explores the efficacy of the GPT-4 Language Learning Model (LLM) compared to BERT in modeling same-day daily stock price movements for Apple and Tesla in 2017. The study leverages sentiment analysis of microblogging messages from the Stocktwits platform and employs a novel method for prompt engineering, emphasizing the contextual abilities of GPT-4. Logistic regression is utilized to evaluate the correspondence between extracted message contents and stock price movements, revealing GPT-4's substantial accuracy, outperforming BERT in five out of six months. However, practical considerations, including deployment costs and the need for fine-tuning prompts, are also acknowledged. The second study, "Do We Still Need BERT in the Age of GPT? Comparing the Benefits of Domain-Adaptation and In-Context-Learning Approaches to Using LLMs for Political Science Research," investigates the choices researchers face when employing LLMs in political science tasks. The study establishes benchmarks for various natural language processing (NLP) tasks within political science and compares two common approaches: domain-adapting smaller LLMs like BERT with unsupervised pre-training and supervised fine-tuning and querying larger LLMs like GPT-3 without additional training. Preliminary results suggest that, when labeled data is available, a finetuning-focused approach remains superior for text classification. By synthesizing these studies, this research contributes to the broader understanding of LLMs' capabilities and their applicability in diverse domains. It emphasizes the significance of prompt engineering in unlocking the contextual abilities of modern LLMs, providing insights into financial sentiment analysis and political text classification. The findings underscore the nuanced choices researchers must make in selecting appropriate LLMs, adapting them to specific domains, and designing effective prompts for optimal performance in different research contexts.

The Effect of the Indihome Spin Off from PT Telkom Indonesia (Persero) and the Merger of Indihome with Telkomsel on TLKM Shares on the IDX and TLK Shares on the NYSE

The world of telecommunications in Indonesia cannot be separated from the role of PT Telekomunikasi Indonesia Tbk, as the largest and long-established telecommunications company and has even become a determinant of the development of telecommunications technology in the country. In the past, conventional telephones installed in homes to communicate long distances were the forerunner of a new civilization for the advancement of telecommunications. However, in the middle of 2023, Telkom will release Indihome, aka spin off, Indihome is identical to conventional telephones owned by Telkom. This decision will make the company more effective and efficient and what will be the impact on the capital market, especialy the response of local and foreign investors. This research uses two statistical analysis test methods, namely Mann Whitney and Spearman. Data analysis using SPSS, comparative tests, namely before and after the spinoff. The data object is stock price movements. The results shows that not all management decisions have a positive impact, as can be seen from the response of local and foreign stock investors to the existing sentiment. Referring to the assumption that Indihome joining Telkomsel does not necessarily mean that Singtel's ownership in Telkomsel will disappear even if dilution occurs. Apart from that, Indihome has a large contribution to Telkom, thereby affecting Telkom's revenue in the near future. Although the long-term target of reducing opex and capex can be realized.

Devaluation and stock prices

Aim: The study evaluated the causal link between exchange rate devaluation and stock prices in African stock markets within the African region, namely, Zambia, Nigeria, Uganda, Tunisia, Tanzania, Botswana, Indonesia, Egypt, South Africa, and Malaysia. Research method: The Toda-Yamamoto (T-Y) Granger causality methodology which entails a determination of maximum order of integration, determination of optimal lag length, and finally conducting the T-Y causality test based on augmented var k + dmax was used in the study. We also deployed the ARDL model to estimate the effects of devaluation on stock prices in Africa. To accommodate issues of endogeneity, we further implemented dynamic panel model estimation to unravel the true effects of exchange rate devaluation on stock prices. Findings: Currency devaluation and the consumer prices negatively impacted stock prices by 3.6% and 3.2% respectively in the short term period following a 1% rise in devaluation and consumer prices. In the long-term period, a 1% rise in currency devaluation and consumer price level stimulated 1.45% and 0.68% reductions in stock prices respectively in ten developing African countries. The lending interest rate also significantly and positively impacted stock market prices over the long-term period by 0.25% following a 1% rise in lending rate, whereas, in the short-term period, a 1% rise in lending rate stimulated 0.38% decline in stock prices of the ten African countries. Originality: in this research, we executed the Toda-Yamamoto granger causality methodology in explaining the causal relation between exchange rate devaluation and stock prices in ten developing African countries and with the ARDL model, the study estimated the effects of devaluation on stock prices in Africa. Contributions: The research is a contribution to a remarkable long-run connection linking stock market price, exchange rate and price index. Though there was a remarkable long-term association linking them, the outcome also showed an essential short-run relationship linking stock market price, consumer price index and interest rate. Limitations: This research is limited to ten countries within the African region. This choice of countries was made on basis of the available data. Hence, data could be sought on additional developing countries and estimation done for a larger sample of countries to obtain results that can be used to generalize the causality between devaluation and stock price movements.