Search Results (1,344)

Accurately predicting stock prices is crucial for investment and risk management, but the non-stationarity of the financial market and the complex correlations among stocks pose challenges to traditional models (ARIMA, LSTM, XGBoost), resulting in difficulties in effectively capturing dynamic patterns and limited prediction accuracy. To this end, this paper proposes the Financial Spatio-Temporal Graph Attention Network (FSTGAT), with the following core innovations: temporal modelling through gated causal convolution to avoid future information leakage and capture long- and short-term fluctuations; enhanced spatial correlation learning by adopting the Dynamic Graph Attention Mechanism (GATv2) that incorporates industry information; designing the Multiple-Input-Multiple-Output (MIMO) architecture of industry grouping for the simultaneous learning of intra-group synergistic and inter-group influence; symmetrically fusing spatio-temporal modules to construct a hierarchical feature extraction framework. Experiments in the commercial banking and metals sectors of the New York Stock Exchange (NYSE) show that FSTGAT significantly outperforms the benchmark model, especially in high-volatility scenarios, where the prediction error is reduced by 45–69%, and can accurately capture price turning points. This study confirms the potential of graph neural networks to model the structure of financial interconnections, providing an effective tool for stock forecasting in non-stationary markets, and its forecasting accuracy and industry correlation capturing ability can support portfolio optimization, risk management improvement and supply chain decision guidance. Full article

The stock market plays a crucial role in the financial system, with its price movements reflecting macroeconomic trends. Due to the influence of multifaceted factors such as policy shifts and corporate performance, stock prices exhibit nonlinearity, high noise, and non-stationarity, making them difficult to model accurately using a single approach. To enhance forecasting accuracy, this study proposes a hybrid forecasting framework that integrates wavelet denoising, multi-head attention-based BiLSTM, ARIMA, and XGBoost. Wavelet transform is first employed to enhance data quality. The multi-head attention BiLSTM captures nonlinear temporal dependencies, ARIMA models linear trends in residuals, and XGBoost improves the recognition of complex patterns. The final prediction is obtained by combining the outputs of all models through an inverse-error weighted ensemble strategy. Using the CSI 300 Index as an empirical case, we construct a multidimensional feature set including both market and technical indicators. Experimental results show that the proposed model clearly outperforms individual models in terms of RMSE, MAE, MAPE, and R². Ablation studies confirm the importance of each module in performance enhancement. The model also performs well on individual stock data (e.g., Fuyao Glass), demonstrating promising generalization ability. This research provides an effective solution for improving stock price forecasting accuracy and offers valuable insights for investment decision-making and market regulation. Full article

This study examines the Enron collapse through an integrated theoretical framework combining the financial saturation paradox with the dynamics of a naturally occurring Ponzi process. The central objective is to evaluate whether endogenous market mechanisms—beyond managerial misconduct—played a decisive role in the emergence and breakdown of the Enron stock bubble. A logistic-growth-based saturation model is formulated, incorporating positive feedback effects and bifurcation thresholds, and applied to Enron’s stock price data from 1996 to 2001. The computations were performed using LogletLab 4 (version 4.1, 2017) and Microsoft^® Excel^® 2016 MSO (version 2507). The model estimates market saturation ratios (P/Pp) and logistic growth rate (r), treating market potential, initial price, and time as constants. The results indicate that Enron’s share price approached a saturation level of approximately 0.9, signaling a hyper-accelerated, unsustainable growth phase consistent with systemic overheating. This finding supports the hypothesis that a naturally occurring Ponzi dynamic was underway before the firm’s collapse. The analysis further suggests a progression from market-driven expansion to intentional manipulation as the bubble matured, linking theoretical saturation stages with observed price behavior. By integrating behavioral–financial insights with saturation theory and Natural Ponzi dynamics, this work offers an alternative interpretation of the Enron case and provides a conceptual basis for future empirical validation and comparative market studies. Full article

This research seeks to evaluate the effects of the preceding cyclical indicators and macroeconomic variables on the performance of the Brazilian stock market from January 2011 to December 2022. The objective is to identify how these factors influence the behavior of the main index representing this market. In this way, it was analyzed how shocks in the composite leading indicator of the economy (IACE) as well as the basic interest rate of the economy (SELIC), the broad national consumer price index (IPCA), the nominal exchange rate (in reals per dollar—BRL/USD) and the central bank economic activity index (IBC-Br) impact the performance of Brazilian stock market index (IBOVESPA). Using the vector autoregression (VAR) model with vector error correction (VEC), positive shocks were simulated in the IACE and the aforementioned macroeconomic variables to identify and compare their impacts on the index. The results obtained, through generalized impulse response functions, indicated that the shocks to the IACE, the exchange rate, and the inflation variables influenced the IBOVESPA in different and statistically significant ways. However, shocks to the economic activity index and the interest rate did not exert a statistically significant influence on the index, partially confirming the hypothesis, which was initially raised, that these factors influence the stock index in different ways. Full article

This study investigates the predictive performance of financial indicators in forecasting stock prices within the automotive sector using an adaptive neuro-fuzzy inference system (ANFIS). In light of the growing complexity of global financial markets and the increasing demand for automated, data-driven forecasting models, this research aims to identify those financial ratios that most accurately reflect price dynamics in this specific industry. The model incorporates four widely used financial indicators, return on assets (ROA), return on equity (ROE), earnings per share (EPS), and profit margin (PM), as inputs. The analysis is based on real financial and market data from automotive companies, and model performance was assessed using RMSE, nRMSE, and confidence intervals. The results indicate that the full model, including all four indicators, achieved the highest accuracy and prediction stability, while the exclusion of ROA or ROE significantly deteriorated model performance. These findings challenge the weak-form efficiency hypothesis and underscore the relevance of firm-level fundamentals in stock price formation. This study’s sector-specific approach highlights the importance of tailoring predictive models to industry characteristics, offering implications for both financial modeling and investment strategies. Future research directions include expanding the indicator set, increasing the sample size, and testing the model across additional industry domains. Full article

This study proposes a novel Deep Reinforcement Learning (DRL) policy network structure for portfolio management called PortRSMs. PortRSMs employs stacked State-Space Models (SSMs) for the modeling of multi-scale continuous regime shifts in financial time series, striking a balance between exploring consistent distribution properties over short periods and maintaining sensitivity to sudden shocks in price sequences. PortRSMs also performs cross-asset regime fusion through hypergraph attention mechanisms, providing a more comprehensive state space for describing changes in asset correlations and co-integration. Experiments conducted on two different trading frequencies in the stock markets of the United States and Hong Kong show the superiority of PortRSMs compared to other approaches in terms of profitability, risk–return balancing, robustness, and the ability to handle sudden market shocks. Specifically, PortRSMs achieves up to a 0.03 improvement in the annual Sharpe ratio in the U.S. market, and up to a 0.12 improvement for the Hong Kong market compared to baseline methods. Full article

This study evaluates the risk-adjusted performance of Hospitality REITs using multi-factor asset pricing models and downside risk measures with the aim of assessing their diversification potential and crisis sensitivity. Unlike prior studies that examine REITs in aggregate, this study isolates Hospitality REITs to explore their unique cyclical and macroeconomic sensitivities. This study looks at the risk-adjusted performance of Hospitality Real Estate Investment Trusts (REITs) in relation to more general REIT indexes and the S&P 500 Index. The study reveals that monthly returns of Hospitality REITs increasingly move in tandem with the stock markets during financial crises, which reduces their historical function as portfolio diversifiers. Investing in Hospitality REITs exposes one to the hospitality sector; however, these investments carry notable risks and provide little protection, particularly during economic upheavals. Furthermore, the study reveals that Hospitality REITs underperform on a risk-adjusted basis relative to benchmark indexes. The monthly returns of REITs show significant volatility during the post-COVID-19 era, which causes return-to-risk ratios to be below those of benchmark indexes. Estimates from multi-factor models indicate negative alpha values across conditional models, indicating that macroeconomic variables cause unremunerated risks. This industry shows great sensitivity to market beta and size and value determinants. Hospitality REITs’ susceptibility comes from their showing the most possibility for exceptional losses across asset classes under Value at Risk (VaR) and Conditional Value at Risk (CvaR) downside risk assessments. The findings have implications for investors and portfolio managers, suggesting that Hospitality REITs may not offer consistent diversification benefits during downturns but can serve a tactical role in procyclical investment strategies. Full article

This study applies Gradient Boosting Machines (GBMs) and principal component regression (PCR) to forecast the closing price of the Johannesburg Stock Exchange (JSE) All-Share Index (ALSI), using daily data from 2009 to 2024, sourced from the Wall Street Journal. The models are evaluated under three training–testing split ratios to assess short-term forecasting performance. Forecast accuracy is assessed using standard error metrics: mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute scaled error (MASE). Across all test splits, the GBM consistently achieves lower forecast errors than PCR, demonstrating superior predictive accuracy. To validate the significance of this performance difference, the Diebold–Mariano (DM) test is applied, confirming that the forecast errors from the GBM are statistically significantly lower than those of PCR at conventional significance levels. These findings highlight the GBM’s strength in capturing nonlinear relationships and complex interactions in financial time series, particularly when using features such as the USD/ZAR exchange rate, oil, platinum, and gold prices, the S&P 500 index, and calendar-based variables like month and day. Future research should consider integrating additional macroeconomic indicators and exploring alternative or hybrid forecasting models to improve robustness and generalisability across different market conditions. Full article

Predicting stock prices on stock markets is challenging due to the nonlinear and nonstationary nature of financial markets. This study presents a hybrid model based on integrated machine learning (ML) techniques—neural networks, support vector regression (SVR), and decision trees—that uses the stacking method to estimate the next day’s maximum and minimum stock prices. The model’s performance was evaluated using three data sets: Brazil’s São Paulo Stock Exchange (iBovespa)—Companhia Energética do Rio Grande do Norte (CSRN) and CPFL Energia (CPFE)—and one from the New York Stock Exchange (NYSE), the Dow Jones Industrial Average (DJI). The datasets covered the following time periods: CSRN and CPFE from 1 January 2008 to 30 September 2013, and DJI from 3 December 2018 to 31 August 2024. For the CSRN ensemble, the hybrid model achieved a mean absolute percentage error (MAPE) of 0.197% for maximum price and 0.224% for minimum price, outperforming results from the literature. For the CPFE set, the model showed a MAPE of 0.834% for the maximum price and 0.937% for the minimum price, demonstrating comparable accuracy. The model obtained a MAPE of 0.439% for the DJI set for maximum price and 0.474% for minimum price, evidencing its applicability across different market contexts. These results suggest that the proposed hybrid approach offers a robust alternative for stock price prediction by overcoming the limitations of using a single ML technique. Full article

Stock price forecasting remains a persistent challenge in time series analysis due to complex inter-stock relationships and dynamic textual signals such as financial news. While Graph Neural Networks (GNNs) can model relational structures, they often struggle with capturing higher-order dependencies and are sensitive to noise. Moreover, sentiment signals are typically aggregated using fixed time windows, which may introduce temporal bias. To address these issues, we propose DASF-Net (Diffusion-Aware Sentiment Fusion Network), a multimodal framework that integrates structural and textual information for robust prediction. DASF-Net leverages diffusion processes over two complementary financial graphs—one based on industry relationships, the other on fundamental indicators—to learn richer stock representations. Simultaneously, sentiment embeddings extracted from financial news using FinBERT are aggregated over an empirically optimized window to preserve temporal relevance. These modalities are fused via a multi-head attention mechanism and passed to a temporal forecasting module. DASF-Net integrates daily stock prices and news sentiment, using a 3-day sentiment aggregation window, to forecast stock prices over daily horizons (1–3 days). Experiments on 12 large-cap S&P 500 stocks over four years demonstrate that DASF-Net outperforms competitive baselines, achieving up to 91.6% relative reduction in Mean Squared Error (MSE). Results highlight the effectiveness of combining graph diffusion and sentiment-aware features for improved financial forecasting. Full article

Recent years have seen a rise in combining deep learning and technical analysis for stock price prediction. However, technical indicators are often prioritized over technical charts due to quantification challenges. While some studies use closing price charts for predicting stock trends, they overlook charts from other indicators and their relationships, resulting in underutilized information for predicting stock. Therefore, we design a novel framework to address the underutilized information limitations within technical charts generated by different indicators. Specifically, different sequences of stock indicators are used to generate various technical charts, and an adaptive relationship graph learning layer is employed to learn the relationships among technical charts generated by different indicators. Finally, by applying a GNN model combined with the relationship graphs of diverse technical charts, temporal patterns of stock indicator sequences are captured, fully utilizing the information between various technical charts to achieve accurate stock price predictions. Additionally, we further tested our framework with real-world stock data, showing superior performance over advanced baselines in predicting stock prices, achieving the highest net value in trading simulations. Our research results not only complement the existing applications of non-singular technical charts in deep learning but also offer backing for investment applications in financial market decision-making. Full article

This paper reveals a simple methodology to create local-correlation models suitable for the closed-form pricing of two-asset financial derivatives. The multivariate models are built to ensure two conditions. First, marginals follow desirable processes, e.g., we choose the Geometric Brownian Motion (GBM), popular for stock prices. Second, the payoff of the derivative should follow a desired one-dimensional process. These conditions lead to a specific choice of the dependence structure in the form of a local-correlation model. Two popular multi-asset options are entertained: a spread option and a basket option. Full article

This study investigates the relationship between sovereign credit rating transitions and domestic equity market performance, focusing on Greece from 2004 to 2024. Although credit ratings are central to sovereign risk assessment, their immediate influence on financial markets remains contested. This research adopts a multi-method analytical framework combining algebraic combinatorics and time-series econometrics. The methodology incorporates the construction of a directed credit rating transition graph, the partially ordered set representation of rating hierarchies, rolling-window correlation analysis, Granger causality testing, event study evaluation, and the formulation of a reward matrix with optimal rating path optimization. Empirical results indicate that credit rating announcements in Greece exert only modest short-term effects on the Athens Stock Exchange General Index, implying that markets often anticipate these changes. In contrast, sequential downgrade trajectories elicit more pronounced and persistent market responses. The reward matrix and path optimization approach reveal structured investor behavior that is sensitive to the cumulative pattern of rating changes. These findings offer a more nuanced interpretation of how sovereign credit risk is processed and priced in transparent and fiscally disciplined environments. By bridging network-based algebraic structures and economic data science, the study contributes a novel methodology for understanding systemic financial signals within sovereign credit systems. Full article

Over the past decade, multifactor models have shown enhanced capability compared to single-factor models in explaining asset return variability. Given the common assertion that higher risk tends to yield higher returns, this study empirically examines the augmented human capital six-factor model’s performance on thirty-two portfolios of non-financial firms sorted by size, value, profitability, investment, and labor income growth in the Indian market over the period July 2010 to June 2023. Moreover, the current study extends the Fama and French five-factor model by incorporating a human capital proxy by labor income growth as an additional factor thereby proposing an augmented six-factor asset pricing model (HC6FM). The Fama and MacBeth two-step estimation methodology is employed for the empirical analysis. The results reveal that small-cap portfolios yield significantly higher returns than large-cap portfolios. Moreover, all six factors significantly explain the time-series variation in excess portfolio returns. Our findings reveal that the Indian stock market experienced heightened volatility during the COVID-19 pandemic, leading to a decline in the six-factor model’s efficiency in explaining returns. Furthermore, Gibbons, Ross, and Shanken (GRS) test results reveal mispricing of portfolio returns during COVID-19, with a stronger rejection of portfolio efficiency across models. However, the HC6FM consistently shows lower pricing errors and better performance, specifically during and after the pandemic era. Overall, the results offer important insights for policymakers, investors, and portfolio managers in optimizing portfolio selection, particularly during periods of heightened market uncertainty. Full article

Bank operations are contingent upon investor confidence, particularly during periods of economic distress. If investor confidence drops, a bank faces difficulties obtaining money, higher borrowing costs, and lower stock values. Non-performing loans (NPLs) potentially jeopardize a bank’s long-term viability and short-term profitability, and investors are naturally wary of institutions that pose a high credit risk. The purpose of the study was to explore how non-performing loans influence investor confidence in banks. A purposive sampling technique was used to identify 253 New York Stock Exchange banks in the Thomson Reuters Eikon DataStream that satisfied all the inclusion and exclusion selection criteria. The Common Correlated Effects Mean Group (CCEMG) and Generalized Method of Moments (GMM) models were used to analyze the data, providing insight into the relationship between the variables. The study discovered that NPLs had a negative and significant influence on price–earnings (P/E) and price-to-book value (P/B) ratios. Furthermore, the bank’s age was found to have a positive and significant relationship with the P/E and P/B ratio. The moderating relationship between NPLs and bank age was found to have a negative and significant influence on price–earnings (P/E) and price-to-book value (P/B) ratios. The findings underscore the importance of asset quality and institutional reputation in influencing market perceptions. Bank managers should focus on managing non-performing loans effectively and leveraging institutional credibility to sustain investor confidence, particularly during financial distress. Full article