Constituent Stocks Research Articles

Under the microscope: Trade initiation activities around earnings and takeover announcements in a market with continuous disclosure

We examine the impact of the release time of earnings and takeover announcements on trade initiation motives on the ASX — a market with continuous disclosure. This investigation uses intraday high-frequency data of the constituent stocks of the S&P/ASX50 index and measures market sidedness around the announcements to infer trade initiation motives. We find that during a continuous trading session: (i) in a two-sided market, investors initiate both buy and sell trades just before announcements are released during trading sessions, and (ii) in a one-sided market, investors execute either buy or sell trades just after the announcements. Our results suggest that differential information is the likely motive for trade initiation just before the release of announcements. Finally, our results suggest that announcements released during continuous trading sessions are more effective in controlling information leakage.

Do ETFs increase the comovements of their underlying assets? Evidence from a switch in ETF replication technique

We investigate the impact of Exchange-Traded Funds (ETFs) on the comovements of their constituent securities using a novel identification that exploits the switch from synthetic to physical replication of a large French ETF. After the switch, constituent stocks experience greater commonality, in both returns and liquidity. For both the full sample of ETF constituents and the least liquid ETF constituents, a larger part of the variation in individual stock returns or liquidity is explained by market-wide variations. We present evidence that ETF creation and redemption is the transmission mechanism of the comovements. Moreover, we show that the comovements do not appear excessive.

Multi-scale contrast approach for stock index prediction with adaptive stock fusion

The stock index summarizes the overall movement of a group of stocks, typically calculated as a weighted average of constituent stock prices. Stock Index Prediction (SIP) aids investors in assessing economic performance and making informed decisions. Traditional SIP methods rely heavily on historical index data, neglecting valuable insights from macro-financial indicators and stock prices. However, challenges arise when incorporating these data: (1) Including numerous unfiltered macro-financial indicators introduces noise. (2) Using non-correlated stock prices can be counterproductive. (3) Supervised training on stochastic time series can lead to overfitting. To overcome these issues, we propose a multi-scale contrast approach for stock index prediction with adaptive stock fusion (MCSIP). This method identifies highly correlated macro-financial indicators and stocks, optimizing the model through self-supervised multi-scale contrastive learning. MCSIP relies on contrastive learning in the time series domain to extract robust contextual information from stock index time series, mitigating stochastic data backpropagation and ensuring reliable representation. Experiments on US and Chinese stock datasets demonstrate superior performance compared to existing methods.

Deep Reinforcement Learning Approach to Portfolio Optimization in the Australian Stock Market

The future of portfolio management is evolving from relying on human expertise to incorporating artificial intelligence techniques. Traditional techniques such as fundamental and technical analysis will eventually be replaced by more sophisticated deep reinforcement learning (DRL) algorithms. However, it is still a long way from designing a profitable strategy in the complex and dynamic stock market. While previous studies have focused on the American stock market, this paper applies two DRL algorithms, the proximal policy optimization (PPO) and the advantage actor–critic (A2C), to trade the constituent stocks of the Australian Securities Exchange 50 (ASX50) Index. This paper also incorporates a weighted moving average into the action space and introduces a transaction threshold to help agents minimize trivial trades that lead to high transaction costs. The results are presented and benchmarked against the ASX50 Index. The A2C agent was better at following trends and had the higher upside potential but can suffer from more severe damage during bearish markets. On the other hand, the PPO agent had the lowest annual volatility and the highest maximum drawdown, which is more helpful in a bearish or volatile market.

A Study on Stock Price Prediction Based on Attention GCN-BiLSTM Modeling

It is of great significance to accurately predict stock price movements. By combining the R-Vine-Copula structure with the relationship between the conceptual sectors to which the stocks belong, the price correlation between stocks is measured and the adjacency matrix is constructed, and the model AGLSTM, which is constructed by combining the temporal attention mechanism, Graph Convolutional Neural Network and Bi-directional Long and Short-Term Memory Neural Network, is proposed to predict the price of 46 stocks from the constituent stocks of the SSE 50 by modeling them. The experimental results show that, compared with the baseline, the AGLSTM can predict the stock price. The experimental results show that compared with the baseline model, the MAE and RMSE results of the AGLSTM model predicted one step forward outperform all the comparison models, and the MAPE results are close to the best baseline model results. The results of MAPE are close to those of the best baseline model. Moreover, good results are also achieved in the experiment of multi-step forward prediction, which demonstrates the ability of AGLSTM model in long-term prediction and can provide some reference for investors to make investment decisions.

Online Portfolio Selection of Fuzzy Mean Regression Strategy Considering Investor Sentiment Based on Text Data

Investors are often affected by emotion, cognition, and other psychological factors in stock trading when making decisions. At present, people can use machine learning and other technologies to obtain a massive amount of text data from the Internet to mine information related to investor behavior and sentiment. Building intelligent online portfolio trading strategies that consider investor sentiment has become an important topic and key challenge in the financial field. Therefore, this paper explores how to use text data to depict investor sentiment, fuzzifies historical stock price data, designs a new weight transfer equation, and finally obtains a novel fuzzy mean regression strategy that considers investor sentiment based on text data. We conduct empirical tests on this strategy by using the stock price data selected from CSI300 constituent stocks, as well as the text data of investors’ opinions on the internet. The results show that the strategy proposed in this study has a higher Calmar ratio than other mean regression strategies previously studied.

Early warning signals for stock market crashes: empirical and analytical insights utilizing nonlinear methods

This study introduces a comprehensive framework grounded in recurrence analysis, a tool of nonlinear dynamics, to detect potential early warning signals (EWS) for imminent phase transitions in financial systems, with the primary goal of anticipating severe financial crashes. We first conduct a simulation experiment to demonstrate that the indicators based on multiplex recurrence networks (MRNs), namely the average mutual information and the average edge overlap, can indicate state transitions in complex systems. Subsequently, we consider the constituent stocks of the China’s and the U.S. stock markets as empirical subjects, and establish MRNs based on multidimensional returns to monitor the nonlinear dynamics of market through the corresponding the indicators and topological structures. Empirical findings indicate that the primary indicators of MRNs offer valuable insights into significant financial events or periods of extreme instability. Notably, average mutual information demonstrates promise as an effective EWS for forecasting forthcoming financial crashes. An in-depth discussion and elucidation of the theoretical underpinnings for employing indicators of MRNs as EWS, the differences in indicator effectiveness, and the possible reasons for variations in the performance of the EWS across the two markets are provided. This paper contributes to the ongoing discourse on early warning extreme market volatility, emphasizing the applicability of recurrence analysis in predicting financial crashes.

Mastery of “Monthly Effects”: Big Data Insights into Contrarian Strategies for DJI 30 and NDX 100 Stocks over a Two-Decade Period

In contrast to finding better monthly performance shown in a specific month, such as the January effect (i.e., better stock price performance in January as opposed to other months), which has been extensively studied, the goal of this study is to determine whether investors would obtain better subsequent performance as technical trading signals emitted in a specific month because, from the investment perspective, investors purchasing stocks now would not know their performance until later. We contend that our analysis emphasizes its critical role in steering investment decisions and enhancing profitability; nonetheless, this issue appears to be overlooked in the relevant literature. As such, utilizing big data to analyze the constituent stocks of the DJI 30 and NDX 100 indices from 2003 to 2022 (i.e., two-decade data), this study investigates whether trading these stocks as trading signals emitted via contrarian regulation of stochastic oscillator indicators (SOIs) and the relative strength index (RSI) in specific months would result in superior subsequent performance (hereafter referred to as “monthly effects”). This study discovers that the oversold signals generated by these two contrarian regulations in March were associated with higher subsequent performance for holding 100 to 250 trading days (roughly one year) than other months. These findings highlight the importance of the trading time and the superiority of the RSI over SOIs in generating profits. This study sheds light on the significance of oversold trading signals and suggests that the “monthly effect” is crucial for achieving higher returns.

Improving Cointegration-Based Pairs Trading Strategy with Asymptotic Analyses and Convergence Rate Filters

A pairs trading strategy (PTS) constructs a mean-reverting portfolio whose logarithmic value moves back and forth around a mean price level. It makes profits by longing (or shorting) the portfolio when it is underpriced (overpriced) and closing the portfolio when its value converges to the mean price level. The cointegration-based PTS literature uses the historical sample mean and variance to establish their open/close thresholds, which results in bias thresholds and less converged trades. We derive the asymptotic mean around which the portfolio value oscillates. Revised open/close thresholds determined by our asymptotic mean and standard derivations significantly improve PTS performance. The derivations of asymptotic means can be extended to construct a convergence rate filter mechanism to remove stock pairs that are unlikely to be profitable from trading to further reduce trading risks. Moreover, the PTS literature oversimplifies the joint problem of examining a stock pair’s cointegration property and selecting the fittest vector error correction model (VECM). We propose a two-step model selection procedure to determine the cointegration rank and the fittest VECM via the trace and likelihood ratio tests. We also derive an approximate simple integral trading volume ratio to meet no-odd-lot trading constraints. Experiments from Yuanta/P-shares Taiwan Top 50 Exchange Traded Fund and Yuanta/P-shares Taiwan Mid-Cap 100 Exchange Traded Fund constituent stock tick-by-tick backtesting during 2015–2018 show remarkable improvements by adopting our approaches.

K-Medoids Clustering dan Mean-Value at Risk untuk Optimasi Portofolio Saham Jakarta Islamic Index

<p>The problem of the portfolio is how to choose stocks and determine their weights in order to generate maximum returns with minimal risk. Portfolios are formed by selecting stocks that have different characteristics. K-Medoids Clustering can be used to group data sets that contain outliers. Validate cluster results using the Davies Bouldin Index to determine the best number of clusters. Portfolio weighting is determined using the Mean-VaR method by taking into account the expected return value and minimizing the VaR risk value. Stocks are grouped based on Return on Assets, Return on Equity, Debt to Asset Ratio, and Debt to Equity Ratio. The results of cluster formation on the Jakarta Islamic Index stocks obtained six portfolio constituent stocks based on the highest expected return value from each cluster, consisting of PTBA, ADRO, AKRA, EXCL, PTPP, and UNVR. The results of calculating the weight of the optimal portfolio with Mean-VaR obtained a weight for PTBA of 0.46536; AKRA of 0.24018; EXCL of 0.25421; and UNVR of 0.25392. ADRO and PTPP stocks have a negative weight value of -0,07775 and -0,13593 this indicates the occurrence of short selling in the weighting. At the 95% confidence level, the VaR portfolio value is 5.06%.</p><p><strong>Keywords: </strong>Clustering; K-Medoids; Daveis Bouldin Index; Portfolio; Mean-VaR</p>

Stock market openness and audit fees: evidence from the inclusion of China A-shares in the MSCI emerging markets index

This study examines how China’s stock market openness affects audit fees. In May 2018, Morgan Stanley Capital International (MSCI) announced the first wave of listing of large-cap China A-shares in the MSCI Emerging Markets (EM) Index, which marked China’s grand entrance into the global investment benchmark, and sharply expanded its stock market investor base. Using a difference-in-differences approach, we find that audit fees for constituent stocks decrease after the index inclusion. Further analyses suggest that foreign investors can reduce the risk of expropriation by controlling shareholders and mitigate agency conflicts. Our results also show that the effect is more pronounced for firms with weaker internal controls, lower levels of domestic institutional ownership, and those located in less developed markets. Our findings highlight the monitoring effect of stock market openness in improving corporate governance and advance our understanding of the key drivers of audit fees in emerging markets.

Predicting Medium-Term Stock Index Direction Using Constituent Stocks and Machine Learning

Predicting Medium-Term Stock Index Direction Using Constituent Stocks and Machine Learning

Research on improving the key indicators of enterprise ESG rating

ESG ratings, as a metric for assessing corporate social responsibility, have garnered escalating interest from both domestic and international investors within China. However, critical indicators for augmenting ESG scores remain underexplored. Utilizing data from 2017 to 2020 on CSI 300 and CSI 500 constituent stocks, this study employs advanced machine learning algorithms, including XGBoost (XGB), LightGBM (LGB), and Random Forest (RF), to conduct a quantitative analysis of corporate feature values and their correlation with institutional rating outcomes. The findings indicate a predominant influence of corporate governance indicators, particularly in the realm of information disclosure, followed by social responsibility and environmental metrics. The paper further delineates specific, actionable short-term and long-term strategies that corporations can adopt across environmental, social, and governance dimensions, tailored to the nuances of various sub-indicators.

Quantitative Stock Selection Strategy Analysis Based on Multi-factor Model Under the Epidemic Situation

Contemporarily, COVID-19 undoubtedly had a profound impact on the current Chinese economy, as well as presented various challenges and opportunities for different industries in China. As a matter of fact, these changes may profoundly affect the future development trends and competitive landscape of industries. In recent years, the number of stock investors had continued to increase, surpassing 200 million in 2022. In a highly competitive market, the ability to select high-quality stocks often determines the final returns. This study selected the constituent stocks of the “CSI 500” as the “stock pool” for stock selection between 2020 and 2023. By analysing the degree of factor exposure, the correlation between factors, and IC values of factors, suitable and effective factor combinations were selected, and an evaluation model was established using multiple regression analysis to obtain a trading strategy. To ensure its feasibility and rationality, the strategy was simulated using backtesting before actual trading, ultimately aiming to achieve excess alpha returns.

Graphical Deep Learning Prediction Model for Stock Risk Management

Forecasting the future movements of stock market indexes by utilizing historical transaction data is a prominent concern within the realm of finance. The application of graph convolutional networks to incorporate the interrelationships among various indices’ patterns is a highly advanced subject within this field. Addressing the inconsistency between historical and future dynamic graphs in current graph convolution-based index prediction, we propose a method called G-Conv that constructs a graph structure based on constituent stocks of the indices for index trend prediction. This approach extracts traditional quantitative features along with deep features from one-dimensional convolutional networks as characteristics of prediction samples. The method produces index trend predictions by constructing a graph structure using constituent stock data of indices and applying graph convolution to different index sample features. The proposed methodology’s efficacy is verified by utilizing 42 widely employed indicators in the A-share market. The experimental findings demonstrate that when utilizing mean absolute error (MAE) and mean squared error (MSE) as the loss functions for model training, G-Conv outperforms classic methods such as GC-CNN and ADGAT. Specifically, G-Conv reduces the average prediction errors by 5.10% and 4.20% respectively, as evaluated by the two error criteria. Additionally, G-Conv exhibits favorable generalization performance.

Can ChatGPT reduce human financial analysts’ optimistic biases?

This paper examines the potential of ChatGPT, a large language model, as a financial advisor for listed firm performance forecasts. We focus on the constituent stocks of the China Securities Index 300 and compare ChatGPT’s forecasts for major financial performance measures with human analysts’ forecasts and the realised values. Our findings suggest that ChatGPT can correct the optimistic biases of human analysts. This study contributes to the literature by exploring the potential of ChatGPT as a financial advisor and demonstrating its role in reducing human biases in financial decision-making.

Stock Market Forecasting Based on Spatiotemporal Deep Learning.

This study introduces the Spacetimeformer model, a novel approach for predicting stock prices, leveraging the Transformer architecture with a time-space mechanism to capture both spatial and temporal interactions among stocks. Traditional Long-Short Term Memory (LSTM) and recent Transformer models lack the ability to directly incorporate spatial information, making the Spacetimeformer model a valuable addition to stock price prediction. This article uses the ten minute stock prices of the constituent stocks of the Taiwan 50 Index and the intraday data of individual stock on the Taiwan Stock Exchange. By training the Timespaceformer model with multi-time-step stock price data, we can predict the stock prices at every ten minute interval within the next hour. Finally, we also compare the prediction results with LSTM and Transformer models that only consider temporal relationships. The research demonstrates that the Spacetimeformer model consistently captures essential trend changes and provides stable predictions in stock price forecasting. This article proposes a Spacetimeformer model combined with daily moving windows. This method has superior performance in stock price prediction and also demonstrates the significance and value of the space-time mechanism for prediction. We recommend that people who want to predict stock prices or other financial instruments try our proposed method to obtain a better return on investment.

Forecast combination puzzle in the HAR model

AbstractThe heterogeneous autoregressive (HAR) model has become the benchmark model for predicting realized volatility, given its simplicity and consistent empirical performance. Many modifications and extensions to the original model have been proposed that often only provide incremental forecast improvements. In this paper, we take a step back and view the HAR model as a forecast combination that combines three predictors: previous day realization (or random walk forecast), previous week average, and previous month average. When applying the ordinary least squares (OLS) to combine the predictors, the HAR model uses optimal weights that are known to be problematic in the forecast combination literature. In fact, an average of simpler HAR‐style models, and a simple average forecast often outperforms the optimal combination in many empirical applications. We investigate the performance of these simple combination forecasts for the realized volatility of the Dow Jones Industrial Average equity index, and a sample of individual constituent stocks, as well as across a range of other assets, commodities, exchange rates, and a range of global equity market indices. In all cases, we find dramatic improvements in forecast accuracy across all horizons and different time periods. The combinations also perform well relative to the logarithmic form of the HAR model and when using a volatility timing strategy in portfolio allocation. Thisis the first time the forecast combination puzzle is identified in this context.

Investment Strategy, Manager Characteristics, and Corporate Governance Effects on Mutual Fund Performance: A Study of PT Asuransi Jiwasraya (Persero) During Period of 2013-2018

This study aims to examine the relationships between investment strategies, investment manager characteristics, and corporate governance on the investment performance of PT Asuransi Jiwasraya (Persero)’s mutual funds investment from 2013 to 2018. The year 2013 marked the introduction of a new bancassurance product, which necessitated PT AJS to generate higher returns on investment in a short-term period. The sudden change in management in 2018 brought the mismanagement case to public attention. The analysis utilized a cross-sectional multilinear regression approach, allowing for the examination of multiple independent variables and their relationship with the dependent variable. Data for the study is collected from various sources, including annual reports, financial reports, prospectuses, and court documents. The relationships are assessed using seven regression models, with measures such as mean return, standard deviation, beta, Sharpe ratio, Treynor ratio, Jensen’s Alpha, and state loss as the dependent variables. The regression models are estimated using SPSS software, and assumptions of linearity, independence of errors, homoscedasticity, and absence of multicollinearity are checked to ensure the validity of the analysis. Hypothesis testing is conducted to determine the statistical significance of the relationships, and measures such as R-squared, adjusted R-squared, and F-statistic are used to assess the overall goodness-of-fit of the models. The findings indicate that the models for mean return, Treynor ratio, Jensen’s Alpha, and state loss are statistically significant, demonstrating a strong correlation and high explanatory power. The results suggest that value investing and smaller market capitalization of constituent stocks have a positive association with investment performance. Additionally, reducing the presence of dividend-paying and suspect stocks is beneficial for investment performance. Factors such as management fees, education background, and years of experience show significant positive relationships, while investment horizon, asset size, and past performance have significant negative relationships with investment performance. The age of the investment manager does not exhibit a significant relationship. Furthermore, corporate governance demonstrates a negative relationship with investment performance. These findings provide valuable insights for improving investment performance and offer important lessons to prevent similar cases of mismanagement of investment funds in the future.

Is it all about noise? Investor sentiment and risk nexus: evidence from China

We investigate how online investor sentiment impacts stock risk, measured as Value-at-Risk (VaR). We extrapolate online investor sentiment from information on the stock forum on the 100 constituent stocks of the Shenzhen index using a self-written code to collect daily online postings from 2016 to 2022. Then, we rely on algorithms to classify them. Using quantile regressions and controlling for firm-specific factors and COVID-19, we document that stronger sentiment increases VaR while decreasing VaR on a lagged 7-day horizon. As we move to a longer horizon (20 days), the effect vanishes as more information becomes incorporated into the stock prices.