Search results

This study aims to examine the impact of board characteristics on firm performance while also exploring the influential mechanisms that help Chinese listed companies establish effective boards of directors and strengthen their corporate governance mechanisms.

This paper uses machine learning methods to investigate the predictive ability of the board of directors' characteristics on firm performance based on the data from Chinese A-share listed companies on the Shanghai and Shenzhen stock exchanges in China during 2008–2021. This study further analyzes board characteristics with relatively strong predictive ability and their predictive models on firm performance.

The results show that nonlinear machine learning methods are more effective than traditional linear models in analyzing the impact of board characteristics on Chinese firm performance. Among the series characteristics of the board of directors, the contribution ratio in prediction from directors compensation, director shareholding ratio, the average age of directors and directors' educational level are significant, and these characteristics have a roughly nonlinear correlation to the prediction of firm performance; the improvement of the predictive ability of board characteristics on firm performance in state-owned enterprises in China performs better than that in private enterprises.

The findings of this study provide valuable suggestions for enriching the theory of board governance, strengthening board construction and optimizing the effectiveness of board governance. Furthermore, these impacts can serve as a valuable reference for board construction and selection, aiding in the rational selection of boards to establish an efficient and high-performing board of directors.

The study findings unequivocally demonstrate the superiority of nonlinear machine learning approaches over traditional linear models in examining the relationship between board characteristics and firm performance in China. Within the suite of board characteristics, director compensation, shareholding ratio, average age and educational level are particularly noteworthy, consistently demonstrating strong, nonlinear associations with firm performance. Within the suite of board characteristics, director compensation, shareholding ratio, average age and educational level are particularly noteworthy, consistently demonstrating strong, nonlinear associations with firm performance. The study reveals that the predictive performance of board attributes is generally more robust for state-owned enterprises in China in comparison to their counterparts in the private sector.

Once regional financial risks erupt, they not only affect the stability and security of the financial system in the region, but also trigger a comprehensive financial crisis, damage the national economy, and affect social stability. Therefore, it is necessary to regulate regional financial risks through artificial intelligence methods.

In this manuscript, we scrutinize the loan data pertaining to aggregated regional financial risks and proffer an ARIMA-SVR loan data regression model, amalgamating traditional statistical regression methods with a machine learning framework. This model initially employs the ARIMA model to accomplish historical data fitting and subsequently utilizes the resultant error as input for SVR to refine the non-linear error. Building upon this, it integrates with the original data to derive optimized prediction results.

The experimental findings reveal that the ARIMA-SVR (Autoregress Integrated Moving Average Model-Support Vector Regression) method advanced in this discourse surpasses individual methods in terms of RMSE (Root Mean Square Error) and MAE (Mean Absolute Error) indices, exhibiting superiority to the deep learning LSTM method.

An ARIMA-SVR framework for the financial risk recognition is proposed. This presentation furnishes a benchmark for future financial risk prediction and the forecasting of associated time series data.

The purpose of this paper is to explore the dynamic interdependence structure and risk spillover effect between the Chinese stock market and the US stock market.

This paper mainly uses the multivariate R-vine copula-complex network analysis and the multivariate R-vine copula-CoVaR model and selects stock price indices and their subsector indices as samples.

The empirical results indicate that the Energy, Materials and Financials sectors have leading roles in the interdependent structure of the Chinese and US stock markets, while the Utilities and Real Estate sectors have the least important positions. The comprehensive influence of the Chinese stock market is similar to that of the US stock market but with smaller differences in the influence of different sectors of the US stock market on the overall interdependent structure system. Over time, the interdependent structure of both stock markets changed; the sector status gradually equalized; the contribution of the same sector in different countries to the interdependent structure converged; and the degree of interaction between the two stock markets was positively correlated with the degree of market volatility.

This paper employs the methods of nonlinear cointegration and the R-vine copula function to explore the interactive relationship and risk spillover effect between the Chinese stock market and the US stock market. This paper proposes the R-vine copula-complex network analysis method to creatively construct the interdependent network structure of the two stock markets. This paper combines the generalized CoVaR method with the R-vine copula function, introduces the stock market decline and rise risk and further discusses the risk spillover effect between the two stock markets.

This research aims to forecast the ABI as a leading indicator of U.S. construction activities, applying multivariate machine learning predictive models over different horizons and utilizing the nonlinear and long-term dependencies between the ABI and macroeconomic and construction market variables. To assess the applicability of the machine learning models, six multivariate machine learning predictive models were developed considering the relationships between the ABI and other construction market and macroeconomic variables. The forecasting performances of the developed predictive models were evaluated in different forecasting scenarios, such as short-term, medium-term, and long-term horizons comparable to the actual timelines of construction projects.

The architecture billings index (ABI) as a macroeconomic indicator is published monthly by the American Institute of Architects (AIA) to evaluate business conditions and track construction market movements. The current research developed multivariate machine learning models to forecast ABI data for different time horizons. Different macroeconomic and construction market variables, including Gross Domestic Product (GDP), Total Nonresidential Construction Spending, Project Inquiries, and Design Contracts data were considered for predicting future ABI values. The forecasting accuracies of the machine learning models were validated and compared using the short-term (one-year-ahead), medium-term (three-year-ahead), and long-term (five-year-ahead) ABI testing datasets.

The experimental results show that Long Short Term Memory (LSTM) provides the highest accuracy among the machine learning and traditional time-series forecasting models such as Vector Error Correction Model (VECM) or seasonal ARIMA in forecasting the ABIs over all the forecasting horizons. This is because of the strengths of LSTM for forecasting temporal time series by solving vanishing or exploding gradient problems and learning long-term dependencies in sequential ABI time series. The findings of this research highlight the applicability of machine learning predictive models for forecasting the ABI as a leading indicator of construction activities, business conditions, and market movements.

The architecture, engineering, and construction (AEC) industry practitioners, investment groups, media outlets, and business leaders refer to ABI as a macroeconomic indicator to evaluate business conditions and track construction market movements. It is crucial to forecast the ABI accurately for strategic planning and preemptive risk management in fluctuating AEC business cycles. For example, cost estimators and engineers who forecast the ABI to predict future demand for architectural services and construction activities can prepare and price their bids more strategically to avoid a bid loss or profit loss.

The ABI data have been forecasted and modeled using linear time series models. However, linear time series models often fail to capture nonlinear patterns, interactions, and dependencies among variables, which can be handled by machine learning models in a more flexible manner. Despite the strength of machine learning models to capture nonlinear patterns and relationships between variables, the applicability and forecasting performance of multivariate machine learning models have not been investigated for ABI forecasting problems. This research first attempted to forecast ABI data for different time horizons using multivariate machine learning predictive models using different macroeconomic and construction market variables.

This study aims to examine the asymmetric effects of average temperature (TP) and rainfall (RF) on the Moroccan food security, measured by the food production index (FPI), using annual data from 1961 to 2020.

The study uses the Climate Change and Food Security Framework (CCFS) developed by the Food and Agriculture Organization (FAO) and employs the nonlinear auto-regressive distributed lag (NARDL) model and various econometric techniques to show the effects of climate variability in the short and long-term. It also examines if the impacts on Moroccan food security are asymmetric by analyzing the positive and negative partial sums of mean temperature and rainfall.

The study shows that RF has a long-term relationship with FPI, with increased RF leading to increased FPI and decreased RF leading to decreased FPI. FPI responds more strongly and persistently to a positive shock in RF than to an adverse shock. The study also identifies an asymmetric relationship between FPI and RF, with increased TP enhancing food output in the long run and a decrease reducing food production in the long run.

The current study could have some limitations. For instance, there are several other non-climate factors that might potentially impact food security. In particular, CO2 emissions which from the literature is a key variable that represent climate change impact on food security, was not included. The present research has not included those factors mainly because adding more variables to the model reduces the degree of freedom available to estimate the parameters, resulting in inaccurate results.

This paper contributes to the food security literature by utilizing the latest asymmetry methodology to decompose climate changes into their positive and negative trends and examining the contrasting impacts food production.

Traditional grey models are integer order whitening differential models; these models are relatively effective for the prediction of regular raw data, but the prediction error of irregular series or shock series is large, and the prediction effect is not ideal.

The new model realizes the dynamic expansion and optimization of the grey Bernoulli model. Meanwhile, it also enhances the variability and self-adaptability of the model structure. And nonlinear parameters are computed by the particle swarm optimization (PSO) algorithm.

Establishing a prediction model based on the raw data from the last six years, it is verified that the prediction performance of the new model is far superior to other mainstream grey prediction models, especially for irregular sequences and oscillating sequences. Ultimately, forecasting models are constructed to calculate various energy consumption aspects in Chongqing. The findings of this study offer a valuable reference for the government in shaping energy consumption policies and optimizing the energy structure.

It is imperative to recognize its inherent limitations. Firstly, the fractional differential order of the model is restricted to 0 < a < 2, encompassing only a three-parameter model. Future investigations could delve into the development of a multi-parameter model applicable when a = 2. Secondly, this paper exclusively focuses on the model itself, neglecting the consideration of raw data preprocessing, such as smoothing operators, buffer operators and background values. Incorporating these factors could significantly enhance the model’s effectiveness, particularly in the context of medium-term or long-term predictions.

This contribution plays a constructive role in expanding the model repertoire of the grey prediction model. The utilization of the developed model for predicting total energy consumption, coal consumption, natural gas consumption, oil consumption and other energy sources from 2021 to 2022 validates the efficacy and feasibility of the innovative model.

These findings, in turn, provide valuable guidance and decision-making support for both the Chinese Government and the Chongqing Government in optimizing energy structure and formulating effective energy policies.

This research holds significant importance in enriching the theoretical framework of the grey prediction model.

The highlights of the paper are as follows:

1. A novel grey Bernoulli prediction model is proposed to improve the model’s structure.

2. Fractional derivative, fractional accumulating generation operator and Bernoulli equation are added to the new model.

3. The proposed model can achieve full compatibility with the traditional mainstream grey prediction models.

4. Energy consumption in Chongqing verifies that the performance of the new model is much better than that of the traditional grey models.

5. The research provides a reference basis for the government to formulate energy consumption policies and optimize energy structure.

A novel grey Bernoulli prediction model is proposed to improve the model’s structure.

Fractional derivative, fractional accumulating generation operator and Bernoulli equation are added to the new model.

The proposed model can achieve full compatibility with the traditional mainstream grey prediction models.

Energy consumption in Chongqing verifies that the performance of the new model is much better than that of the traditional grey models.

The research provides a reference basis for the government to formulate energy consumption policies and optimize energy structure.

This study aims to examine the effect of the board of directors (BoD) structure on environmental, social and governance (ESG) performance in publicly traded non-financial firms from the perspective of agency theory, with investors as the principal, the management team as the agent, the BoD as an information system that reduces information asymmetries between them and ESG performance as a shareholder’s expectation.

Sample data is cross-sectional as of January 2023 and includes 1,695 non-financial firms listed in 59 stock markets across 54 countries. Data were sourced from the FactSet Research Systems database. The generalized least squares method was used to run quadratic and exponential models to assess the research hypotheses.

Results revealed that board size, independence, age, gender diversity and participation on other corporate boards have a nonlinear relationship with ESG performance. Board tenure is the only BoD attribute for which a nonlinear association is not found. This study found that firms with larger boards and more female board members tend to exhibit a stronger commitment to ESG performance. In contrast, companies with a board of directors consisting of independent members, advanced age, service on other corporate boards and CEO duality may struggle to prioritize positive ESG outcomes.

This study contributes to the academic discussion on BoD–ESG by examining nonlinear relationships among a large sample of publicly traded firms; providing results that could be applied internationally; using ESG data that is based on the Sustainability Accounting Standards Board's materiality framework, which identifies key ESG factors for investors; emphasizing the significance of diversity and inclusion within the decision-making bodies of public companies, thereby improving their ESG performance; and supporting the agency theory perspective and suggesting that the effect of board structure on ESG may reflect the board's focus on investors’ best interests.

Because the dynamic characteristics of the stock market are nonlinear, it is unclear whether stock prices can be predicted. This paper aims to explore the predictability of the stock price index from a long-memory perspective. The authors propose hybrid models to predict the next-day closing price index and explore the policy effects behind stock prices. The paper aims to discuss the aforementioned ideas.

The authors found a long memory in the stock price index series using modified R/S and GPH tests, and propose an improved bi-directional gated recurrent units (BiGRU) hybrid network framework to predict the next-day stock price index. The proposed framework integrates (1) A de-noising module—Singular Spectrum Analysis (SSA) algorithm, (2) a predictive module—BiGRU model, and (3) an optimization module—Grid Search Cross-validation (GSCV) algorithm.

Three critical findings are long memory, fit effectiveness and model optimization. There is long memory (predictability) in the stock price index series. The proposed framework yields predictions of optimum fit. Data de-noising and parameter optimization can improve the model fit.

The empirical data are obtained from the financial data of listed companies in the Wind Financial Terminal. The model can accurately predict stock price index series, guide investors to make reasonable investment decisions, and provide a basis for establishing individual industry stock investment strategies.

If the index series in the stock market exhibits long-memory characteristics, the policy implication is that fractal markets, even in the nonlinear case, allow for a corresponding distribution pattern in the value of portfolio assets. The risk of stock price volatility in various sectors has expanded due to the effects of the COVID-19 pandemic and the R-U conflict on the stock market. Predicting future trends by forecasting stock prices is critical for minimizing financial risk. The ability to mitigate the epidemic’s impact and stop losses promptly is relevant to market regulators, companies and other relevant stakeholders.

Although long memory exists, the stock price index series can be predicted. However, price fluctuations are unstable and chaotic, and traditional mathematical and statistical methods cannot provide precise predictions. The network framework proposed in this paper has robust horizontal connections between units, strong memory capability and stronger generalization ability than traditional network structures. The authors demonstrate significant performance improvements of SSA-BiGRU-GSCV over comparison models on Chinese stocks.

Agriculture commodity price forecasts have long been important for a variety of market players. The study we conducted aims to address this difficulty by examining the weekly wholesale price index of green grams in the Chinese market. The index covers a ten-year period, from January 1, 2010, to January 3, 2020, and has significant economic implications.

In order to address the nonlinear patterns present in the price time series, we investigate the nonlinear auto-regressive neural network as the forecast model. This modeling technique is able to combine a variety of basic nonlinear functions to approximate more complex nonlinear characteristics. Specifically, we examine prediction performance that corresponds to several configurations across data splitting ratios, hidden neuron and delay counts, and model estimation approaches.

Our model turns out to be rather simple and yields forecasts with good stability and accuracy. Relative root mean square errors throughout training, validation and testing are specifically 4.34, 4.71 and 3.98%, respectively. The results of benchmark research show that the neural network produces statistically considerably better performance when compared to other machine learning models and classic time-series econometric methods.

Utilizing our findings as independent technical price forecasts would be one use. Alternatively, policy research and fresh insights into price patterns might be achieved by combining them with other (basic) prediction outputs.

This article aims to study the nonlinear effect of financial inclusion on tax revenue of 21 low financial development countries (LFDCs) and 22 high financial development countries (HFDCs) from 2004 to 2020.

The study calculates the world average financial development index (FD̅) for all countries using data from the IMF. The average FD of HFDCs is higher than (FD̅). On the other hand, the average FD of LFDCs is lower than (FD̅). Data of 21 LFDCs and 22 HFDCs cover the period 2004–2020. With the small sample problem, we applied the Bayesian method to examine the nonlinear effect of financial inclusion on the tax revenue of the two groups of countries.

Using the Bayesian method, the results show that financial inclusion negatively impacts tax revenue with an absolute probability of 100% in LFDCs and a lower probability of 92.45% in HFDCs. Additionally, the financial inclusion threshold at LFDCs is 18.90. Below this threshold, financial inclusion promotes tax revenue with a 100% probability. On the contrary, when financial inclusion exceeds the threshold, it will have a negative effect on tax revenue. Similarly, the financial inclusion threshold at HFDCs is 20.14, with a probability of 92.45%.

To the best of the authors’ knowledge, this is the first paper to examine the nonlinear impact of financial inclusion on tax revenue in high and low financial development countries.