Stock Trading Research Articles

Research on investment returns prediction based on machine learning

With the development of the Internet and the continuous improvement of the information disclosure mechanism of the securities market, individual investors have more and more ways to obtain investment information, including company research reports from analysts. However, analysts have mixed qualifications and publish a huge number of reports. For retail investors, how to analyze and distinguish these reports and make informed investment decisions based on them has become the key to profiting in a securities market where information is asymmetrical and risks and opportunities coexist. This is a priority that every retail investor should prioritize. In recent years, machine learning has become increasingly widely used in the financial sector, especially in the prediction of return on investment. In this work, a most advanced machine learning model Transformer is used, which is widely used in a variety of scenarios due to its advantages in processing sequence data. The Transformer model can effectively process and analyze large-scale financial time series data through the self-attention mechanism to capture subtle fluctuations and potential correlations in the market. We designed a Transformer-based architecture to combine multi-source data such as market macroeconomic indicators, stock trading data, and social sentiment analysis for comprehensive learning. Experimental results show that the model significantly improves the accuracy of investment return prediction and provides investors with efficient analysis tools.

The efficacy of Relative Strength Index (RSI) in KLSE market trade

The Relative Strength Index (RSI) is a widely used technical indicator in stock trading because of its simple application. However, its application combined with fundamental analysis in Kuala Lumpur Stock Exchange (KLSE) is yet to be explored extensively. Hence, this study aimed to investigate the effectiveness of RSI as a predictive tool in the KLSE market. First, 39 stocks that met the set of criteria guided by fundamental soundness were identified. Trading signals are then initiated based on the RSI indicators, which are superimposed on the charts of the identified stocks. The return on investment (ROI) was then estimated and benchmarked against KLCI performance over a period of five years starting from 21st July 21, 2018. It was found that the average ROI was 3.46% against KLCI’s -24.37% over the same period of 5 years, measured between 21st July 21, 2018, 21st July 21, 2023. The average ROI improves as the number of trade iterations increases to five. The peak average ROI is approximately 22%. Technology is the top performer, recording an ROI of more than 40%. In conclusion, the combination of RSI and fundamental analysis yielded a mixed set of results. Although it outperforms KLCI, the annualised ROI is only slightly above 4%. Nevertheless, the results of this study provide valuable insights into the application of the RSI as a trading signal generator in the KLSE market.

Performance analysis of a blockchain process modeling: Application of distributed ledger technology in trading, clearing and settlement processes

This study aims to assess the extent to which blockchain technology (BCT) may constitute an alternative to the conventional stock trading system and emphasize the changing roles of the key parties. It is expected that BCT would enhance the performance of the process across the three stages (i.e. trading, clearing and settlement within the stock exchange environment). A thorough literature review is conducted to understand the BCT performance modeling techniques and approaches (empirical and analytical) and to examine the theoretical potentials and capabilities of BCT in the financial markets. The case study and simulation methods are used to evaluate the impact of BCT implementation in optimizing the process of trading, clearing and settlement in Abu Dhabi Securities Exchange (ADX) stock-trading activities. This paper presents a simulation analysis comparing a blockchain system with a traditional trading system in the context of stock market. The simulation procedures involve modeling processes over different durations and transaction volumes, using metrics such as process time and cycle time to evaluate performance. The performance index combines these metrics with weights to ensure accurate and consistent measurements. Simulation results reveal that the blockchain system significantly outperforms the current trading system, especially at higher transaction volumes, highlighting its scalability and efficiency. A threshold of 30,000 transactions is identified as the point where blockchain’s benefits become apparent. The analysis shows that blockchain significantly elevate the process efficiency. It reduces both cycle time and process time across varying transaction volumes, maintaining consistency and reliability. Additionally, a simple simulation using the Hyperledger Fabric platform demonstrates the practical implementation of a permissioned blockchain for clearing transactions, emphasizing the system's capability to manage high transaction volumes efficiently and securely. The use of blockchain network for handling seamless transactions using pre-defined smart contracts significantly improves the performance of the stock trading processes, specifically in the clearing phase. Interestingly, the BCT system drops the need for a “third party” (i.e. stock custodian) across the three stages. At the end of the paper, we propose a thereat mitigating model for stock trading with a new blockchain system.

Investment management approaches: A comprehensive review of equity trading simulators, methodological challenges, and future directions

This paper provides a comprehensive review of equity trading simulators, focusing on their performance in assuring pre-trade compliance and portfolio investment management. A systematic search was conducted that covered the period of January 2000 to May 2023 and used keywords related to equity trade simulators, portfolio management, pre-trade compliance, online trading, and artificial intelligence. Studies demonstrating the use of simulators and online platforms specific to portfolio investment management, written in English, and matching the specified query were included. Abstracts, commentaries, editorials, and studies unrelated to finance and investments were excluded. The data extraction process included data related to challenges in modern portfolio trading, online stock trading strategies, the utilization of deep learning, the features of equity trade simulators, and examples of equity trade simulators. A total of 32 studies were included in the systematic review and were approved for qualitative analysis. The challenges identified for portfolio trading included the subjective nature of the inputs, variations in the return distributions, the complexity of blending different investments, considerations of liquidity, trading illiquid securities, optimal portfolio execution, clustering and classification, the handling of special trading days, the real-time pricing of derivatives, and transaction cost models (TCMs). Portfolio optimization techniques have evolved to maximize portfolio returns and minimize risk through optimal asset allocation. Equity trade simulators have become vital tools for portfolio managers, enabling them to assess investment strategies, ensure pre-trade compliance, and mitigate risks. Through simulations, portfolio managers can test investment scenarios, identify potential hazards, and improve their decision-making process.

VNSMAS: A constraint-based portfolio profit maximization

Stock trading has a more significant influence on the global economy. Stock trading with portfolio optimization became challenging due to the complexity of analyzing the high variance in time series stock data. Efficient portfolio management increases profit and avoids risky situations when investing. The present work aims to model a Variable Neighborhood Search Multi-Agent System for Portfolio Optimization (VNSMASPPO) to optimize the profit on defined trading constraints on buying, selling, and holding trading decisions. This work proposes a novel Variable Neighborhood Search-based Multi-Agent System (VNASMAS) algorithm for profit computation with a constraint-based multi-agent system. The stock price history experimental data sets are collected from 8th August 2016 to 31st March 2023 with 14,567 records. The proposed model achieved an RMSE of 10.11, MAE of 2.75, and MAPE of 0.017, outperforming the literature models. VNSMASPPO maximizes the portfolio profit and is a reliable, adaptable approach.

An Empirical Study on Announcement Effect of Right Issue Ex-Date

This research aims to examine how the market reacts regarding the announcement of the rights issue and how the market reacts at the ex date. The sampling technique is purposive sampling, namely companies that carry out rights issues and are active banking on the Indonesian Stock Exchange. Testing period 2015 to 2021. The technique used is multiple linear regression test and paired sample T test. The total number of companies is 27 issuers with research results showing that the announcement of a rights issue has an effect on changes in share prices where the p-value of the pair sample t-test is less than 0.05. Meanwhile, testing the market reaction regarding the ex date shows that there was a significant decline in stock prices so that the market reacted negatively with a p-value of less than 0.05 and there was a significant change in stock trading volume during the ex date condition with a p-value of less than 0.05.

The Asymmetric Effect of Mutual Fund Herding on Price Deviation: Evidence from the Chinese Stock Market

Mutual funds, as significant participants in financial markets, play a crucial role in the formation of asset pricing. The relationship between herding behavior of mutual funds and mispricing has been a subject of intense debate among scholars. In this paper, we investigate the asymmetric impact of mutual fund herding on price deviation and explore the underlying mechanism. In terms of research design, this study selects relevant data on mutual fund holdings and stock trading in the Chinese A-share market from 2010 to 2023, we examine whether herding behavior leads to mispricing, specifically focusing on the asymmetric effects of herding buying and herding selling on stock price deviation from intrinsic value. This study distinguishes the trading direction of mutual fund herding behavior and separately examines the relationship between herding buying behavior and herding selling behavior with stock price deviation. Our empirical findings reveal that buying herding behavior is linked to positive price deviations from intrinsic value. However, selling herding behavior shows no significant relationship with price deviation. Furthermore, our results provide evidence that the herding buying of mutual funds stimulates similar trading sentiments among other market participants and contributes to the formation of market bubbles, while herding selling prompts counterbalancing trades, mitigating the impact of price deviation.

Giao dịch thuật toán trên thị trường chứng khoán dưới góc nhìn công nghệ

The power of the technological revolution, combining technology and finance, has significantly transformed the way transactions are conducted in the stock market. Algorithmic trading is not only a new trend but also an essential requirement in an increasingly complex market that demands flexible and rapid adaptation. Large financial institutions such as major stock trading companies, investment funds, and individual investors are all seeking to leverage the power of technology to optimize trading performance and maximize profits. In this paper, we provide an insight into automatic algorithmic trading in the stock market from a technological perspective: how algorithms operate, their benefits, as well as the challenges and risks investors have to deal with when using them. The paper employs synthesis, comparison, and contrast methodologies based on published research to evaluate and provide recommendations for algorithmic trading. Our evaluation confirms that algorithmic trading is an inseparable part of the modern stock market.

Examining the presence of the monday effect on the Indonesian Stock Exchange before and during the Covid-19 pandemic

This study examines the presence of the Monday effect on the Indonesian Stock Exchange before and during the Covid-19 pandemic based on stock return, transaction volume, and trading patterns. This study uses trading day and trading hour as independent variables and daily return, daily total transaction volume, and return 30-minute intervals return within a day as a proxy for daily investor trading patterns as dependent variables. The data used in this study are from the Jakarta Composite Index from 1 July 2017 to 30 November 2022. The analytical methods used in this research is one-way ANOVA and two-way ANOVA. The results of this study demonstrate that day-of-week was not a significant factor in terms of daily return and daily total transaction volume before and during the pandemic. Moreover, there was no Monday effect in daily investor trading patterns before the pandemic. During the pandemic, the Monday effect in daily investor trading patterns was also not present. However, after the change in the trading hour period, the Monday effect was found in the daily investor trading pattern.

CAPITAL MARKET REACTION TO PRABOWO-GIBRAN’S VICTORY IN THE 2024 PRESIDENTIAL ELECTION IN INDONESIA : TESTING ON INFOBANK15

This research aims to analyze the capital market reaction to the event study of Prabowo-Gibran's victory in the Indonesian Presidential Election by comparing the variables of stock price, stock return and Infobank15 stock trading volume activity in the research period 20 days before and 20 days after the announcement on March 20 2024. Including quantitative research because the data taken is secondary data sourced from idx.co.id where the population which is also a sample is 15 leading banks with good performance according to the Indonesian Stock Exchange. The research results reveal that there is no difference in the average stock price, average stock return and average TVA before and after the announcement of Prabowo-Gibran's victory.

A Case Study of Examination Malpractice Terminated Through Counselling (21-Year-Old Undergraduate Male)

The goal of counseling is to get the client better than he/she came for counselling. The aim of this case study is to share the experiences of Owunari (21-year old undergraduate male) who was invited for counselling by the counsellor on account of an alleged involvement in examination malpractice (within ethical limits). The client came for counselling because he was invited by the counsellor. Owunari did not deny the allegation, he confessed that it has been his trade in stock since his second year as he goes about doing menial jobs to finance his education after the demise of his sponsor. Counsellor with the consent of the client mapped out a weekly schedule of meeting, the goal was to have a better understanding of the client’s problem with a view to helping him overcome it. Six sessions of Counselling were held with the client during which active listening and responsiveness, empathy, questioning and directive counselling were explored to help the client to learn how to solve his problem. The counsellor did a background check on him from classmates and associates and confirmed all his claims. Counsellor provided immediate help by providing upkeep, and payed the balance of his fees, she gave him several links to seek for sponsorship. One of the links yielded dividend as George Mangibo reach out foundation offered him a full scholarship to complete his education. At this point counselling was terminated and examination malpractice jettisoned.

Institutional Brokerage Networks: Facilitating Liquidity Provision

Abstract We argue that institutional brokerage networks facilitate liquidity provision and mitigate the price impact of large non-information-motivated trades. Using commissions, we map trading networks of mutual funds (institutions) and their brokers. Central funds (institutions) tend to outperform their peripheral counterparts in terms of return gap (execution shortfall). This outperformance is more pronounced when funds experience large outflows and for large trades in less liquid stocks. Central brokers can deliver superior trade execution compared to peripheral brokers, but mainly for central institutions. We use the collapse of Lehman Brothers as a quasi-natural experiment to establish the likely causality of our findings.

Algorithmic stock trading based on ensemble deep neural networks trained with time graph

Financial forecasting is generally implemented by analyzing the time series data related to the stock. This is accomplished widely with deep neural networks (DNNs) since DNNs can directly extract the related information that is otherwise hard to obtain. Time series is the core data representation of financial forecasting problem since it comes naturally. However recent studies show that even if time series representation is necessary, it still lacks certain aspects related to the problem. One of them is the relationship between the stocks of the market which can be captured through graph representation. Therefore, DNNs might solve the financial forecasting problem better when graph and time series representations are combined. In this study, we present different graph representations that can be used for this purpose. We also present an ensemble network that gives an investment strategy related to the stock market from stock predictions. Our proposed model returns an average of 20.09% annual profit on DOW30 dataset through daily buy–sell decisions based on close prices. Therefore, it can serve as a daily financial investment strategy, offering higher annual returns than conventional heuristic approaches.

Stock Market Liquidity and Stock Market Performance in Nigeria: Evidence from the Nigerian Exchange Limited

Insufficient liquidity can become a significant obstacle to stock trading and impede the smooth operation and performance of the stock market. This motivated the study to investigate the effect of stock market liquidity on stock market performance in Nigeria. The research design employed was ex post facto, while stratified sampling technique was used to select top 30 actively traded and most liquid companies tagged NGX-30 for this study. Data were sourced secondarily from SEC Statistical Bulletin, CBN Statistical Bulletin and www.investing.com. The Vector Error Correction (VEC) System Equation Regression was employed as the estimation technique. The results revealed that liquidity depth, liquidity breadth, and liquidity immediacy have significant positive effects on stock market performance as shown by ? = 0.2019, 8.5594, 3.3268; p-value = 0.0329, 0.0052, 0.0467 respectively. Also, interest rate, inflation rate and exchange rate have varied significant effects on stock market performance as shown by ? = -0.0023, -1.1738, 0.03432; p-value = 0.0634, 0.0346, 0.0778 respectively. Therefore, the study concluded that stock liquid significantly affects stock market performance. Thus, the study recommended that the Security and Exchange Commission (SEC) should implement policies that encourage the participation of more traders to increase the number of actively traded stocks; support measures that improve the depth of the market by promoting transparency and fairness; improve the infrastructure for trade execution to enhance liquidity immediacy; and develop mechanisms to promptly identify and mitigate market risks.

Managers’ staging of earnings conference calls around actual share repurchases

AbstractWe use earnings call transcripts to examine whether managers strategically change their disclosure behaviors before an actual share repurchase. Our findings suggest that managers use tone management to strategically portray a more negative outlook for the firm in the earnings call before an actual repurchase. In addition, we find that managers of repurchasing firms “cast” the call with more unfavorable analysts even when more favorable analysts are available. These disclosure strategies aim to influence the information flows to the market and allow repurchasing firms to repurchase their shares at a discounted price. We further show that insiders of repurchasing firms adjust their subsequent stock trading accordingly. Following more negative conference calls, insiders exhibit a tendency to increase share repurchases or reduce sales of company shares. Our findings underscore the increasingly sophisticated disclosure strategies employed by managers to wield influence over information dynamics in the market leading up to share repurchases.

International crash risk premium

This paper investigates the international crash risk and the cross-section of stock index returns. We use the ex-ante model-free negative skewness measured by country-specific index options, proposed in Bakshi et al. (2003), as a proxy of the crash risk. We find that a country’s stock index with a high crash risk relates to a higher stock return as a risk premium across countries. The international crash risk premium exists robustly after controlling for volatility risk, macroeconomic variables, sensitivities to the international risk factors, and realized return moments. In contrast, other international risk premiums do not exist based on the exposure of such control variables. Based on the crash risk premium, we construct international stock trading strategies by sorting option-implied skewness across countries that outperform benchmark strategies by sorting the above control variables.

Reinforcement Learning Techniques for Stock Trading: A Survey of Current Research

Reinforcement Learning Techniques for Stock Trading: A Survey of Current Research

Effects of Stock Trading Volume, Leverage, and Dividend Payout Ratio on Stock Price Volatility

This study aims to analyze the impact of stock trading volume, leverage, and dividend payout ratio (DPR) on stock price volatility among companies included in the Kompas100 Index and listed on the Indonesia Stock Exchange (IDX) from 2018 to 2022. The data used in this research were obtained from the financial statements available on the official IDX website and additional data from Yahoo Finance. A purposive sampling method was used to select the research sample based on specific criteria. The results of the study indicate that stock trading volume and leverage have a significant positive impact on stock price volatility, while DPR also influences volatility by showing changes that can elicit sharp market reactions. These findings provide important insights for investors and company management regarding factors that can increase risk and uncertainty in stock prices in the market.

From engagement to retention: Unveiling factors driving user engagement and continued usage of mobile trading apps

The popularity of online mobile trading has led to an increase in the development of mobile stock trading applications. Despite this increase in popularity, there is a dearth of empirical studies that examine the factors influencing the continued usage intention of these applications (hereafter, apps). Drawing on stimulus-organism-response (S-O-R) theory, this paper investigates the features of stock trading apps that generate consumer engagement and consequently, continued app usage intention. In study 1, through semi-structured interviews, we establish four key drivers of customer engagement with stock trading apps, and two possible moderators influencing the relationship between customer app engagement and continued usage intention. In study 2, we examine these key drivers by surveying stock trading app users from three different Facebook stock trading communities. The results confirm that the social presence and security features of these apps are significantly associated with consumer stock trading app engagement. We also find that fear of uncertainty and perceived corporate hypocrisy weaken the effect of customer app engagement on continued app usage intention. The study findings add to the literature on app usage and customer engagement and provide insights for fintech service companies to help them understand the factors that enhance consumer engagement with these apps.

The Effect of Stock Price, Stock Trading Volume and Market Capitalization on the Stock Return of Health Sector Companies Listed on the Indonesia Stock Exchange during Covid 19 (Period 2020-2022)

The purpose of this study was to analyze the effect of stock prices, stock trading volume and market capitalization on stock returns of health sector companies listed on the Indonesia Stock Exchange (IDX) during the Covid 19 period (2020-2022 period). The capital market is a place where investors can provide a portion of their capital to invest in a company issuer to gain profit. The type of research used in this study uses quantitative research, namely research conducted using numbers as objects in conducting analysis. The data used is secondary data in the form of quarterly data over a period of 3 years. The samples used in this study were 17 health sector companies listed on the Indonesia Stock Exchange. As for the data collection method by means of documentation and sampling using purposive sampling method. The results of this study indicate that the stock price variable has a significant level of value on stock returns with the results of the t test which is worth 0.000 so it can be interpreted that the stock price variable has a significant effect on stock returns. The stock trading volume variable has a significant effect on stock returns, this can be seen by the significance value of the t test results of 0.042. The market capitalization variable has no significant effect on stock returns, this can be proven by the significance value of the t-test results of 0.212.