Search Results (572)

This study proposes MSATE-Net for next-day stock index forecasting. The model combines parallel one-dimensional convolutions with receptive fields of 3, 7, and 15 trading days, a bidirectional LSTM operating entirely inside a historical lookback window, sample-dependent temporal attention, and a residual regularized prediction head. Here, “bidirectional” denotes paired processing of the same observed window; it does not assert time-reversal invariance of financial prices or access to observations after the forecast origin. The globally learned attention temperature controls overall selectivity and is not described as a regime-specific adaptive parameter. Experiments use S&P 500, CSI 300, and Nikkei 225 data; persistence and drift benchmarks; recent forecasting architectures; five-seed uncertainty estimates; expanding-window tests; return and directional metrics; and Diebold–Mariano comparisons. The revised evidence supports lower price-level errors, while directional and significance results are mixed across markets. Because a separate model is fitted in each market, the findings establish cross-market consistency rather than transfer learning. Full article

This study investigates whether Chinese sectoral stock returns respond heterogeneously to international oil price movements and whether such responses vary across crisis regimes. Using daily data from January 2015 to June 2026, we analyze ten major sectoral indices of the Shanghai Stock Exchange, Dubai crude oil returns, oil price volatility, and the US dollar–Chinese yuan exchange rate. Dubai crude oil is used as the benchmark because it reflects Asia-oriented crude oil pricing and China’s imported energy cost conditions. The empirical analysis proceeds in several steps. First, baseline regressions are estimated to examine the average effect of oil returns on sectoral stock returns while controlling for domestic market-wide movements and exchange rate changes. Second, market-adjusted sectoral returns are used to isolate genuine sector-specific oil transmission from common market shocks. Third, GARCH(1,1)-based oil volatility and crisis-period interaction terms are introduced to identify the uncertainty effect of oil price movements during the COVID-19 pandemic, the post-pandemic period, and the US–Iran/Middle East geopolitical conflict period. Finally, DCC-GARCH dynamic conditional correlations are used as a robustness check. The results show that Chinese sectoral stock returns do not respond uniformly to oil price movements. The timing-adjusted results provide little evidence that lagged Dubai oil returns systematically predict next-day sectoral returns. Nevertheless, oil-price uncertainty exhibits selective and regime-dependent effects, particularly for Energy, Materials, Consumer Staples, Consumer Discretionary, Industrials, and Utilities. Full article

Stock market price prediction remains a persistent challenge owing to the non-stationarity, high noise content, and intricate spatiotemporal dependencies that characterize financial time series. Existing approaches typically excel at either local pattern extraction or long-range dependency modeling, yet seldom reconcile both within a unified framework. This paper introduces a CNN–Transformer dual-channel architecture equipped with a dynamic attention fusion module for stock price forecasting. The convolutional channel applies hierarchical dilated convolutions to distill fine-grained local patterns from multi-indicator sequences while suppressing high-frequency noise. Simultaneously, the Transformer channel employs multi-head self-attention to capture long-distance temporal correlations and regime-shift dynamics. A learnable gating mechanism then fuses the two feature streams by adaptively weighting local detail against global trend information according to market conditions. Experiments conducted on four real-world stock datasets spanning the S&P 500, CSI 300, NASDAQ Composite, and Hang Seng Index show that the proposed model reduces mean absolute error by 9.7–15.3% and root mean square error by 9.5–13.8% relative to competitive baselines including LSTM, CNN–LSTM, Informer, and PatchTST. Ablation studies further indicate that both channels and the fusion module contribute to prediction accuracy, and the architecture remains effective across markets with differing volatility profiles. Full article

This study examines the asymmetric relationship between housing prices and stock market returns across China’s major economic regions. Specifically, it investigates whether positive and negative shocks exhibit different transmission dynamics and whether these dynamics vary across regions characterized by different levels of financial development and housing market maturity. Using monthly data from 2005 to 2024, the study employs region-specific asymmetric vector autoregression (VAR) models, asymmetric Granger causality tests, and generalized impulse response analysis based on asymmetric decompositions of housing prices and stock market returns. The results suggest that statistically significant housing-to-stock predictability is observed primarily following negative housing price shocks in selected regions, whereas positive shocks generally exhibit weaker or statistically insignificant predictive effects. Conversely, positive stock market shocks generally provide more consistent evidence of stock-to-housing predictability, particularly in the Eastern and Central regions, although the responses are more mixed in the Western region and vary in magnitude, statistical significance, and persistence across regional markets. Overall, the results provide evidence of heterogeneous dynamic transmission patterns across China’s major economic regions and suggest that housing-related downside risk may represent an important source of regional macro-financial vulnerability. Full article

Accurate next-day stock price forecasting remains challenging because daily price changes have a low signal-to-noise ratio and can be strongly affected by short-lived news shocks, order-flow imbalances, and abrupt changes in volatility or market sentiment. This study presents a controlled empirical comparison of deep learning architectures for next-day stock price forecasting using technical indicators. Using a decade-long daily dataset covering four large-cap NASDAQ equities (AAPL, META, SBUX, and TSLA), multivariate input sequences are constructed by combining historical prices with five widely used technical indicators: exponential moving average (EMA), relative strength index (RSI), moving average convergence divergence (MACD), on-balance volume (OBV), and average true range (ATR). Four deep sequence architectures—long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and convolutional LSTM (ConvLSTM)—are evaluated across multiple lookback windows (5, 15, and 30 trading days) and chronological train/validation/test splits (60–20–20, 70–15–15, and 80–10–10). Hyperparameters are optimized through random search, and forecasting performance is assessed on held-out test sets using normalized-scale root mean squared error (RMSE) and out-of-sample $R^2$. Within the examined fixed chronological partitions, ConvLSTM records the lowest observed RMSE for all four equities, attaining values between 0.0256 and 0.0394 and out-of-sample $R^2$ values above 0.90. Because the evaluation does not include walk-forward validation or formal statistical significance testing, these results should be interpreted as descriptive evidence within the present experimental setting rather than as proof of general architectural superiority. To assess practical utility, forecasts are translated into a transparent long-only trading rule that enters the market when the predicted next-day closing price exceeds the current closing price. Out-of-sample backtesting shows that the frictionless forecast-driven strategy achieves higher terminal cumulative returns than Buy-and-Hold for AAPL, SBUX, and TSLA, while Buy-and-Hold remains superior for META. Approximate five-day-frequency risk-adjusted estimates generally reinforce these relative patterns: the ConvLSTM strategy improves the Sharpe, Sortino, and Calmar ratios for AAPL, SBUX, and TSLA, although TSLA remains exposed to substantial drawdown risk. Transaction-cost sensitivity analysis further indicates that the terminal-return gains weaken under trading frictions and are particularly sensitive for AAPL. The findings demonstrate the value of evaluating forecasting architectures through both statistical and financial criteria, while emphasizing that lower point-forecast error does not necessarily translate into superior economic or risk-adjusted performance. Full article

Stock markets are complex adaptive systems whose feature dependencies evolve over time, and identifying which signals genuinely drive returns is fundamentally a problem of information. Traditional feature selection methods and linear models rely on statistical correlations and overlook causality, which weakens their predictive performance in non-linear, evolving markets. This paper develops an information-theoretic approach to causal feature selection based on Markov Blanket discovery. We apply the Iterative Parent–Child-based search of Markov Blanket (IPCMB), whose conditional-independence tests are conditional mutual information measures, to recover the Markov Blanket of next-month returns—the minimal feature set that carries all Shannon information about the target. We then pair it with a Classification and Regression Tree (CART), whose impurity-based splitting admits an information-gain interpretation, to predict the direction of Chinese A-share returns non-linearly. Using data on 2760 stocks, IPCMB selects 13 causal features from 72 candidates, and CART forecasts whether the next month’s return is positive. The empirical results show an accuracy of 58.0%, 7.7 percentage points above the all-features CART benchmark, and a 13-month cumulative return 35.88% higher than that of the CSI 300 index. The findings indicate that selecting features according to their causal information content and combining them with interpretable tree-based prediction can support more reliable investment decisions in emerging markets. Full article

Financial markets are increasingly shaped by heterogeneous information sources, including trading behaviors, order-book dynamics, textual events, investor sentiment, and macroeconomic conditions. These signals are often asynchronous, noisy, partially missing, and associated with different degrees of reliability, which makes trustworthy financial risk early warning challenging. To address these issues, this study proposes an uncertainty-aware multimodal financial sensing network, termed UAMF-Net. The model treats price series, trading volume, order books, news texts, investor sentiment, and macroeconomic variables as financial sensing signals and integrates them through three task-oriented modules. First, the asynchronous multimodal temporal alignment module uses absolute time encoding, relative interval modeling, event-lag representation, temporal gating, and target-time-guided cross-scale attention to align cross-frequency financial signals according to their relevance to the prediction time. Second, the risk-aware multimodal soft fusion module estimates modality-level risk contribution and signal reliability by combining fuzzy risk membership, modality confidence weights, and cross-modal consistency constraints. Third, the uncertainty-aware risk early warning module adopts evidential learning to generate nonnegative class evidence, derive risk-category probabilities from Dirichlet parameters, estimate predictive uncertainty from total evidence strength, and jointly predict continuous risk intensity. Experimental results show that UAMF-Net achieves the best overall performance, with Accuracy, Precision, Recall, F1-score, Macro-F1, ROC-AUC, and PR-AUC reaching $0.882$, $0.864$, $0.849$, $0.856$, $0.839$, $0.941$, and $0.824$, respectively, while ECE and Brier score are reduced to $0.037$ and $0.096$. Under severe temporal asynchrony, UAMF-Net maintains an Accuracy of $0.849$, a Macro-F1 of $0.797$, and a PR-AUC of $0.774$. Under the missing multiple modalities setting, it achieves an Accuracy of $0.842$ and a Macro-F1 of $0.788$. The uncertainty analysis further shows that Risk Precision@90% reaches $0.889$. Validation on FNSPID, Daily News, and StockEmotions also confirms its generalization ability across public financial benchmarks. These results indicate that UAMF-Net improves financial risk early warning by jointly modeling temporal asynchrony, modality reliability, and predictive uncertainty. Full article

While the adoption of electric vehicles can reduce CO₂ emissions, the extent of this reduction depends on the growth of the EV market. Sigmoid growth models, such as logistic or Gompertz function models, can be used to predict expected EV sales trends; however, their quality has not yet been comprehensively analyzed, as this would require looking into the future to compare today’s predictions with future data. Since this is obviously not possible, this study takes a retrograde approach. It uses the available historical data to create forecasts that are then compared with the actual values from subsequent years. For example, a forecast based on data from 2010 to 2014 can be compared with the values achieved in years from 2015 to 2025. The quality of the functions is assessed using fit indices. Among the ten distinct functions tested, including two equivalent Gompertz functions, and under the stated saturation assumptions, the Gompertz family offers the most stable retrospective forecasts of EV stock (prediction period MAPE of 16.0% for the global data, against 15.1% for the generalized logistic, which performs comparably). The generalized logistic attains marginally better global point accuracy, whereas Gompertz is preferred for its greater stability across forecast origins and its more interpretable parameters. Full article

This study provides new evidence on the predictability of confidence indices in China’s stock returns. We demonstrate that, during the sample period from January 2005 to December 2022, the business confidence index (BCI) positively and significantly predicted subsequent stock market returns, outperforming mainstream economic predictors and other confidence indices. Further, for the pricing effectiveness of the stock market, the BCI and investor sentiment provide complementary sources of information. The predictive power of confidence indices for stock market returns declined significantly during the COVID-19 pandemic. Meanwhile, confidence indices predicted better during bear market periods compared to bull market periods. Finally, in practical investment applications, the BCI and alternative confidence index produce appreciable economic gains for investors. These empirical results also pass the robustness test. Full article

Accurate stock price forecasting remains a challenging problem due to the noisy, nonlinear, and non-stationary characteristics of financial time series. Although recent advances in deep learning have improved predictive capabilities, most prior studies evaluate forecasting models primarily using statistical error metrics, with limited consideration of their practical value in trading and investment decision-making. This creates a gap between predictive performance and real-world economic utility. This study proposes a decision-oriented evaluation framework for multi-step stock price forecasting that jointly assesses predictive accuracy and trading profitability within a unified experimental setting. Using data from 91 ASX 100 stocks after data cleaning, with a testing period spanning 2019–2020, several deep learning architectures, including Multi-Layer Perceptron (MLP), Gated Recurrent Unit (GRU), Seq2Seq, and attention-based sequence models, are systematically compared under identical training and trading conditions. The results show that the Seq2Seq model achieved the best overall performance, obtaining the lowest average MAPE of 0.0293 and the highest ROI of 23.2%, while the attention-based model achieved a similar MAPE of 0.0294 but a lower ROI of 12.4%. Although differences in forecasting accuracy were relatively small, the Seq2Seq model achieved the highest observed trading profitability and generated a higher observed return than a passive market benchmark under the proposed evaluation framework. These findings suggest that evaluation based solely on prediction accuracy may not fully capture the practical value of forecasting models. Full article

This study provides an exploratory predictive analysis to examine how different dimensions of digital infrastructure—capital market development, digital payment adoption, e-commerce penetration, and market volatility—predict the financial performance metrics of fintech ventures in Egypt. Using panel data from ten fintech ventures listed on the Egyptian Stock Exchange over the period 2017–2023, the research employs Random Forest machine learning algorithms alongside Logistic Regression as a baseline comparator. Feature importance analysis identifies the most significant predictors of profitability across four performance metrics: gross revenue, sales growth, gross margin, and net profit margin. This study employs Random Forest with five-fold cross-validation. Hyperparameters were optimized via grid search, and feature importance scores are reported with cross-validation standard deviations. To address panel structure concerns, we additionally employ leave-one-firm-out cross-validation. All findings reflect predictive associations only; no causal claims are made due to potential reverse causality. Findings show that capital market development emerges as the most important predictor across all profitability metrics, accounting for 45% of feature importance for net profit margin and 42% for gross revenue (mean importance across five folds; SD = 0.07–0.08). Digital payment adoption exhibits a paradoxical dual association—positively associated with revenue and margins through operational efficiency (38% importance for gross margin; SD = 0.08) while negatively associated with sales growth (22% importance; SD = 0.10). Gross online sales show limited predictive efficacy, affecting only gross margin. Market volatility correlates solely with sales growth. Random Forest consistently outperforms Logistic Regression across all models, with accuracy rates ranging from 68% to 76% (compared to a chance level of 50% and a majority-class baseline of 52–58%). Due to the limited sample of 70 firm-year observations, these findings must be interpreted as strictly exploratory and hypothesis-generating; they apply uniquely to publicly listed fintech firms on the Egyptian Stock Exchange and cannot be generalized to private, early-stage, or unlisted fintech startups without further empirical validation. Full article

Background: This study examines how four canonical behavioral biases (overconfidence, herding, anchoring, and loss aversion) influence investor decision-making in the Saudi stock market (Tadawul), and whether overconfidence and loss aversion operate as moderating forces on herding and anchoring, respectively. Methods: Employing a quantitative, cross-sectional design with a stratified sample of 384 retail investors, the study applies Partial Least Squares Structural Equation Modelling (PLS-SEM) to test six hypotheses derived from Modern Portfolio Theory and Behavioral Finance frameworks. The measurement model satisfies established thresholds for reliability, convergent validity, and discriminant validity. Results: Results confirm that loss aversion is the dominant predictor of behaviorally influenced decision-making (β = 0.402, p < 0.001, f² = 0.188), followed by herding (β = 0.234, p < 0.001) and overconfidence (β = 0.164, p = 0.001), while anchoring does not exert a statistically significant independent effect (β = 0.102, p = 0.084 one-tailed, p = 0.168 two-tailed). Neither the overconfidence × herding (β = 0.005, p = 0.920, two-tailed) nor the loss aversion × anchoring (β = −0.039, p = 0.330, two-tailed) interaction terms reach significance, indicating that these bias pairs operate as independent additive forces rather than compounding systems. The model explains 55.7% of the variance in investor decision-making (R² = 0.557). Conclusion: The findings advance behavioral finance theory in GCC and Islamic equity markets by (1) demonstrating non-equivalence of anchoring effects relative to Western-market benchmarks, (2) resolving competing theoretical predictions about bias interaction effects, and (3) providing context-specific evidence that loss aversion subsumes anchoring cognition in the Saudi market. Practical implications for the Capital Market Authority, financial educators, and individual investors are discussed and contextualized within the Saudi market setting. Full article

Forecasting stock market returns in emerging economies remains challenging due to market volatility, structural irregularities, and limited data availability. This study investigates whether discrete wavelet transformation can enhance the predictive performance of deep learning models when applied to financial time series from emerging markets. Using daily returns of the Ghana Stock Exchange Composite Index (GSE-CI) spanning 2011 to 2022, we evaluate three widely used deep learning architectures—Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM), and Convolutional Neural Network (CNN)—in both their standard form and with preprocessing based on the Daubechies-4 (db4) discrete wavelet transform. The empirical results indicate that wavelet preprocessing consistently reduced forecasting errors across all three deep learning architectures, highlighting its effectiveness as a multiscale feature extraction and noise reduction technique for financial time series. Among the models considered, the Wavelet-LSTM achieved the lowest forecasting error, while the wavelet-enhanced variants consistently outperformed their corresponding baseline models. These findings suggest that the benefits of wavelet decomposition extend beyond a specific neural network architecture by providing a richer representation of nonlinear temporal dynamics in volatile and data-constrained financial environments. As one of the first studies to systematically evaluate wavelet-augmented deep learning models for stock market forecasting in an African equity market, this work contributes to the growing literature on hybrid forecasting frameworks and provides practical insights for researchers, analysts, and investors interested in forecasting emerging financial markets. Full article

Each financial market carries a unique “fractal signature” with its own distinct risk and return pattern. This study comparatively deciphers these fractal signatures of the leading stock market indices of the Emerging Seven (E7) countries (Turkey, India, Brazil, Mexico, Russia, China, Indonesia), using Multifractal Detrended Fluctuation Analysis (MFDFA) with data covering the 2021–2025 period. The findings reveal that all examined markets deviate from the classical random walk model and exhibit distinct multifractal characteristics. However, significant differences were observed among these signatures: in contrast to Russia’s chaotic structure, which showed extreme fragility to geopolitical shocks, the Chinese and Mexican markets presented a more stable and homogeneous risk profile. In all indices, it was found that small-scale fluctuations carry a strong long-memory effect (stable trends), while large-scale fluctuations assume a more random character (sudden shocks). This asymmetric behavior confirms the heterogeneous nature of investor expectations. For example, the generalized Hurst exponents H(q) ranged from 0.22 (RTS, Russia) to 0.73 (BIST100, Turkey), and the spectrum width Δα varied between 0.10 (Mexico) and 0.45 (Russia), confirming significant heterogeneity in market complexity. Turkey’s BIST100 index, with its structure encompassing both predictable and sudden-shock-prone dynamics, occupies a balanced position within this spectrum. Consequently, the study confirms that understanding these unique fractal signatures of emerging markets is a fundamental prerequisite for formulating effective risk management strategies and achieving global portfolio diversification. Full article

This study investigates whether volatility-related variables and traditional financial predictors can explain and forecast Taiwan stock returns. Using the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) and eight major Taiwan industry indices, we examine the predictive ability of long-term adjusted volatility (LVadj), short-term volatility (SV), the volatility index (VIX), idiosyncratic volatility (IVOL), the earnings-to-price ratio (EP), the book-to-market ratio (BM), and the turnover ratio (TURN). The sample period spans from January 2007 to December 2025. Univariate and bivariate predictive regression models are estimated using ordinary least squares (OLS) and exponentially weighted least squares (EWLS). The empirical results show that SV exhibits the strongest in-sample explanatory power for TAIEX returns, whereas TURN plays a more important role in explaining industry-level returns. Out-of-sample forecasting performance varies considerably across industries. For TAIEX returns, the combination of LVadj and TURN provides the strongest forecasting performance, while models incorporating SV and VIX perform relatively well in several industry sectors. Overall, the results suggest that volatility-related variables provide useful predictive information under certain model specifications and industry sectors, with EWLS generally outperforming conventional OLS estimation. Full article