Search Results (2,239)

In the field of financial forecasting, the complexity–accuracy paradigm—the assumption that more complex models yield superior performance—is frequently challenged by market noise and non-stationarity. This study tests this paradigm by evaluating advanced LSTM variants: the core Long Short-Term Memory (LSTM) unit (sLSTM), the matrix LSTM unit (mLSTM), and the extended LSTM architecture (xLSTM), which integrates these units into stacked residual blocks. We systematically benchmark these variants against standard LSTMs and the advanced benchmark model, TimesNet. Extensive experiments span six diverse financial datasets (comprising mature U.S. equities, a macro index, and high-volatility Chinese A-shares) and four historical window lengths. Results demonstrate that the core sLSTM and mLSTM units consistently deliver superior forecasting performance. Crucially, the targeted architectural innovations of sLSTM and mLSTM not only outperform the standard LSTM and TimesNet benchmarks individually but also surpass the more structurally complex xLSTM module configuration. This advantage remains robust across different asset types, indicators, and window lengths, with particularly outstanding performance at the 10-day length window. This study thus provides strong counterevidence to the “complexity–accuracy” paradigm in this field, proposing a data-driven innovation direction for practical trading systems: prioritizing efficient, high-performance core model innovations over generalized architectural complexity. Full article

Stock price prediction is vital for quantitative investment but challenging due to multi-source data complexity, including endogenous, exogenous, and noise components. Standard deep learning models rely on end-to-end modeling of raw market data, failing to disentangle these distinct drivers and hindering prediction accuracy. To address this, we propose MMCAD-Net, a novel model based on time series decomposition. It first decomposes the original stock series into an exogenous cyclical component, endogenous temporal component and residual component, thereby disentangling the mixed temporal patterns. Subsequently, deep feature extraction and information refinement are applied to each component: multi-scale convolutions capture diverse patterns in the cyclical component; multi-level convolutional networks refine local and global features in the temporal component; and an attention mechanism sifts for potentially informative signals within the residuals. Finally, a multi-source feature aggregation mechanism fuses all enhanced information. Experiments on real-world stock market datasets demonstrate that MMCAD-Net surpasses mainstream models in both prediction accuracy and efficiency. Ablation studies further confirm the necessity and effectiveness of each core module. Full article

This study examines the acceptance-related and usage patterns of smart office furniture among Chinese office users. Building on UTAUT2 and a usability-oriented perspective, we compare five alternative structural models that assign different roles to perceived usability in explaining intention and self-reported use of smart office furniture. Using partial least squares structural equation modeling on 239 valid responses, and comparing explanatory performance with out-of-sample prediction, we found that the model in which perceived usability and behavioral intention jointly predict use performed slightly better, although two specifications should be regarded as closely competing alternatives. Results show that facilitating conditions, effort expectancy, price value, and habit are positively associated with behavioral intention, whereas habit, perceived usability, and behavioral intention are positively associated with self-reported usage behavior. Robustness checks with sedentary-context controls indicate that discomfort is positively associated with adoption intention, whereas posture-management tendency is positively associated with self-reported usage behavior. Overall, the main pattern of associations remains broadly similar. The findings suggest a cross-sectional intention–behavior pattern among experienced Chinese users and offer actionable implications for usability-centered design, service delivery, and health-needs-based market segmentation. Full article

Stock price sequences are characterized by pronounced nonlinearity, non-stationarity, and multi-scale volatility. They are further influenced by complex, multi-source factors, such as macroeconomic conditions and market behavior, making high-precision forecasting highly challenging. Existing approaches are limited by noise and multi-dimensional market features, as well as difficulties in balancing prediction accuracy with model complexity. To address these challenges, we propose Wavelet Entropy and Cross-Attention Network (WECA-Net), which combines wavelet decomposition with a multimodal cross-attention mechanism. From an information-theoretic perspective, stock price dynamics reflect the time-varying uncertainty and informational complexity of the market. We employ wavelet entropy to quantify the dispersion and uncertainty of energy distribution across frequency bands, and multiscale entropy to measure the scale-dependent complexity and regularity of the time series. These entropy-derived descriptors provide an interpretable prior of “information content” for cross-modal attention fusion, thereby improving robustness and generalization under non-stationary market conditions. Experiments on Chinese stock indices, A-Share, and CSI 300 component stock datasets demonstrate that WECA-Net consistently outperforms mainstream models in Mean Absolute Error (MAE) and R² across all datasets. Notably, on the CSI 300 dataset, WECA-Net achieves an R² of 0.9895, underscoring its strong predictive accuracy and practical applicability. This framework is also well aligned with sensor data fusion and intelligent perception paradigms, offering a robust solution for financial signal processing and real-time market state awareness. Full article

This study examines whether international food price dynamics provide a reliable signal of undernourishment and human development outcomes relevant to the attainment of SDG 2 (Zero Hunger) by 2030. We apply wavelet coherence analysis to the FAO Food Price Index and the prevalence of undernourishment (SDG Indicator 2.1.1) over 2001–2023, testing statistical significance against an AR(1) red-noise null hypothesis. Hybrid ARIMA–Random Forest models generate probabilistic price forecasts through 2030. Despite strong raw coherence (R² ≈ 0.77), only 7.8% of time–frequency cells achieve statistical significance, indicating that apparent co-movement largely reflects autocorrelation rather than substantive dependence. Where significant coherence emerges, it concentrates at medium-run horizons (3–6 years), consistent with undernourishment as a habitual dietary adequacy measure linked to sustained affordability pressures affecting health, productivity, and human capital formation. Rolling correlation analysis reveals suggestive evidence of a regime change around 2012—from negative to positive correlation—coinciding with a slowdown in progress toward reducing hunger, although the 5-year rolling windows yield only 19 observations, limiting the power of formal structural break tests. Price forecasts exhibit rapidly widening confidence intervals (by ±131 index points by 2030), underscoring fundamental limits to predictability. The annual PoU series comprises only 23 observations, which constrains the estimation of long-run (8–12-year) wavelet cycles; results at those horizons should therefore be interpreted with caution. These findings caution against mechanistic inferences from global price indices to hunger and human development outcomes, redirecting policy emphasis toward domestic transmission channels and nutrition-sensitive safety nets. Full article

Heat recovery from greywater is one solution for improving the energy efficiency of buildings and reducing greenhouse gas emissions. Particular attention is paid to systems utilizing heat from shower water, which, due to its high temperature and regularity, represents a promising energy source. However, the interplay of parameters determining the financial and environmental effectiveness of such a solution has not yet been fully explored. Therefore, the aim of this paper was to identify key variables influencing the feasibility of using a shower heat exchanger operating under unbalanced flow conditions and to assess the consistency between financial and environmental effects. The analyzed net present values ranged from −€1381 to €52,168. Greenhouse gas emission reduction values ranged between 61 kgCO₂e and 37,207 kgCO₂e. The analysis was conducted using predictive modeling and the SHAP (SHapley Additive exPlanations) method, which allows for the interpretation of the impact of individual variables on the forecasted net present value and potential greenhouse gas emission reduction. A global analysis was carried out to determine the relative importance of variables, as well as a local analysis for selected cases. The results showed that operational variables related to shower use, particularly shower length and mixed water flow rate, significantly influenced the prediction results of both models. In the case of emission reduction, greenhouse gas emission intensity and its change over time also had a significant impact, whilst the financial effects were determined by the energy price from the perspective of the subsequent years of the system’s operation. Full article

This study examines the predictability of monthly excess returns for the “Magnificent Seven” U.S. technology firms using machine learning and economically motivated thematic feature grouping. Framed as a focused study of the most systemically consequential equity panel in modern markets—seven firms representing over 30% of the S&P 500—the analysis confronts a small-N, large-P environment where economically structured dimensionality reduction is essential. Using 154 firm-level characteristics categorized into 13 economic themes, we evaluate linear, penalized, tree-based, and neural network models in a small-N, large-P setting. Unrestricted models suffer substantial overfitting and fail to outperform the historical average benchmark out-of-sample. In contrast, theme-based models generate economically meaningful and regime-dependent predictive gains. Short-Term Reversal and seasonality exhibit stronger expansion-period predictability, while size and profitability perform better during recessions. Regularized linear models provide the most stable performance in limited-data environments, whereas nonlinear ensemble methods improve only when training windows are extended. The findings underscore the importance of economically structured dimensionality reduction and adaptive factor allocation in managing concentration risk among systemically important mega-cap firms. Full article

The formulation of construction material unit price policies in areas with limited accessibility is a critical issue in ensuring effective and accountable government infrastructure planning. In such regions, construction costs are often highly volatile and difficult to predict, primarily due to transportation constraints, logistical inefficiencies, and geographical challenges. These conditions frequently result in budget overruns and inconsistencies between planned and actual project expenditures. Therefore, a rational and context-sensitive policy framework is required to support accurate cost estimation and sustainable infrastructure development. This study aims to develop a policy-oriented model for determining construction material unit prices in areas with limited accessibility based on influencing factors. A quantitative research approach was employed through a questionnaire survey involving 235 respondents, consisting of contractors, government representatives, consultants, and academics with experience in infrastructure development in remote or access-constrained regions. The collected data were analysed using Partial Least Squares–Structural Equation Modelling (PLS-SEM) to identify and validate the dominant factors affecting construction material unit prices. The results of the PLS-SEM analysis identified 33 influential factors that significantly contribute to the unpredictability of construction material unit prices in limited-accessibility areas. These factors encompass logistical costs, material price dynamics, government policies, geographical conditions, and local cultural aspects. The proposed model demonstrates that government policy plays a central role, both directly and indirectly through local cultural mediation, in influencing project performance and cost reliability. The findings of this study provide a structured and empirically grounded framework that can be utilized by local governments as a policy reference in establishing construction material unit prices for remote and access-constrained areas. By incorporating the identified influencing factors into unit price formulation, cost prediction accuracy can be improved, thereby supporting more effective budget allocation and ensuring that infrastructure quality is maintained without compromise due to unanticipated cost escalation. These improvements contribute to more sustainable infrastructure development by enhancing resource efficiency, minimizing cost overruns, and supporting equitable infrastructure provision in remote areas. Full article

Accurate forecasting of pork prices is important yet challenging because pork price series are highly volatile and non-stationary. Existing hybrid forecasting models often rely on fixed-weight integration, which may limit their ability to adapt to multi-scale temporal variation and complex temporal dependencies. To address these issues, this study proposes VMD–EMSA–HCTM–Informer, a hybrid forecasting framework that combines signal decomposition with an enhanced encoder–decoder architecture. Variational Mode Decomposition (VMD) is first used to reduce signal non-stationarity by extracting intrinsic mode functions. Within the Informer backbone, an Enhanced Multi-Scale Attention (EMSA) encoder is introduced to capture local fluctuations at different temporal scales, while a Hybrid Convolutional–Temporal Module (HCTM) decoder is used to strengthen temporal feature extraction and channel interaction modeling. Empirical evaluation was conducted on daily pork price data from the China Pig Industry Network and a large-scale intensive breeding enterprise in southern China over the period 2013–2025. Under the current experimental setting, the proposed framework achieved the lowest average errors among the compared baselines across five independent runs, with an average MAE of 0.4875 and an average MAPE of 3.0540%. These results suggest that the proposed framework provides a useful and relatively stable univariate forecasting approach for volatile pork prices. However, the findings should be interpreted within the scope of the present dataset and experimental design, and future work will extend the framework to multivariate forecasting with exogenous drivers and uncertainty quantification. Full article

This study evaluated thermal and thermo-alkaline post-treatment of digested cattle manure (DCM) as a strategy to increase methane recovery and improve the flexibility of biogas systems within hybrid renewable energy alternatives. A 10 L mesophilic CSTR was operated for 311 days, producing lignin-rich digestate that was subjected to a statistically designed range of post-treatment conditions varying temperature (50–90 °C), pH (8–12), and contact time (6–24 h). Biomethane potential assays and lignocellulosic fractionation were used to determine changes in solubilization, biodegradability, and methane production kinetics. Thermal treatment provided modest improvements, reaching 84 mg SCOD g⁻¹ PCOD solubilization and a 26 mL CH₄ g⁻¹ COD increase in methane yield. Thermo-alkaline treatment produced substantially higher enhancements, with the most severe condition (90 °C-pH 12–24 h) achieving 493 mg SCOD g⁻¹ PCOD solubilization, 66% removal of structural carbohydrates, and a 60.2 mL CH₄ g⁻¹ COD increase in methane yield, corresponding to a 16% rise in biodegradability and a twofold increase in methane production rate. Gompertz modeling indicated accelerated kinetics and minimal lag time. A strong linear correlation (R² = 0.90) between severity index and solubilization supported predictable scalability. These results demonstrate that thermo-alkaline hydrolysis can significantly enhance post-digestion methane recovery and strengthen the role of agricultural biogas in integrated renewable energy systems. The techno-economic analysis revealed that, despite higher operating costs for thermo-alkaline post-treatment than for the control, the main drivers are chemical costs and the price of renewable energy, and thus the application of post-treatment as a sustainable solution for animal manure treatment will likely improve as renewable energy prices increase in the future. Full article

This study proposes a machine learning framework tailored to the institutional characteristics of Taiwan’s stock market, aiming to enhance forecasting accuracy for the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX). The model employs the Radius Neighbors Regressor with a dynamic radius-based similarity measure and integrates domain-specific features including technical indicators, volume–price relationships, and Qualified Foreign Institutional Investor (QFII) activity. A custom 60-day input window with a 20-day forecast horizon is applied to capture medium-term market dynamics. The framework was evaluated through extensive backtesting and real-world validation with the TAIEX Futures. The results demonstrate that the model achieves a peak directional accuracy of 85.1% under optimal parameter settings. Moreover, trading simulations confirm its practical viability, yielding a cumulative return on investment (ROI) of approximately 1600% during the short-term evaluation period (2023–2025) and nearly 2000% in the long-term evaluation (2019–2025), even after accounting for transaction costs and stop-loss mechanisms. These findings indicate that combining historical pattern similarity with institutional investor behavior substantially improves predictive power and profitability. Nevertheless, the framework remains constrained by its reliance on Taiwan-specific institutional features and historical trading data, limiting generalizability. Future research should extend applications to other markets while incorporating macroeconomic variables, corporate fundamentals, and news-driven signals to enhance adaptability. Full article

This study frames next-day ETF market behavior as a binary regime classification problem—distinguishing between “oscillating” days, on which intraday price movements remain within a defined threshold, and “trending” days, on which movements exceed that threshold. This framing is economically motivated: active traders employing Martingale-style strategies and ETF options traders require precisely this type of regime prediction to manage risk and time positions. Using 25 years of daily data (2000–2024) for four major ETFs—IWM (Russell 2000), SPY (S&P 500), QQQ (Nasdaq-100), and DIA (Dow Jones)—the study trains and evaluates Random Forest and Neural Network classifiers enriched with macroeconomic announcement indicators and technical features (VIX, RSI, ATR) under a rolling window cross-validation framework. Oscillation is defined as daily intraday price movements within thresholds of 0.5%, 0.75%, and 1%; movements exceeding these levels constitute trending behavior. At the 0.5% threshold—the most practically relevant given typical ETF transaction costs—Neural Networks outperform a naive classifier by 13.4% for IWM, 15.4% for SPY, 4.7% for QQQ, and 3.2% for DIA. AUC values exceed 0.5 in most configurations, with stronger discrimination observed for SPY (AUC up to 0.74) and IWM (AUC up to 0.59) than for QQQ and DIA at some thresholds. Results are stronger for some ETFs and thresholds than others, and cases where AUC approaches 0.5 are explicitly acknowledged as reflecting limited discriminatory power. Full article

The crude oil market has obvious financial entropy, and there are characteristics such as continuous uncertainty, multi-scale fluctuations and nonlinear state transitions. These characteristics bring challenges to the traditional prediction method. In this context, in order to improve the accuracy of energy financial market prediction, this study proposes an artificial intelligence-driven hybrid prediction framework, ALA-VMD-CASA. This framework is divided into three stages. First, with the goal of minimizing envelope entropy, ALA is introduced to adaptively optimize the hyperparameters of VMD, so as to generate informative sub-modes with reduced entropy. Next, the parallel prediction of each sub-mode is carried out by using the score attention mechanism based on the CNN autoencoder, and its linear time complexity can capture volatility clustering and sudden price fluctuations. Finally, the final price prediction is generated through the aggregation component. The empirical experiment of Brent crude oil spot prices from 2010 to 2025 shows that the ALA-VMD-CASA framework is superior to benchmark models such as ARIMA, RW, RWWD, LSTM, GRU, Transformer and Informer. Compared with the best standalone model, the proposed framework reduces the mean square error by more than 63% and obtains a perfect win rate in expanding-window evaluations. These results prove that the proposed framework is effective and robust for modeling financial entropy and improving energy price forecasting. Full article

This study examines the dynamic interactions between oil price shocks, monetary policy, and non-oil output in Saudi Arabia using Vector Autoregressive Model (VAR), and quarterly data spanning 2010: Q1–2025: Q3. The study aims to provide policy-relevant insights through which external oil price shocks and domestic monetary policy shocks affect inflation and non-oil economic activity in the context of Saudi Arabia’s structural transformation under Vision 2030. The results show that global oil prices behave largely as exogenous shocks, with limited feedback from domestic monetary conditions, implying that monetary policy effectiveness operates primarily through inflation and domestic demand channels rather than through oil prices directly. The findings underscore the importance of gradual and predictable monetary tightening, coordinated with fiscal and macroprudential policies, to mitigate the indirect spillovers of oil price volatility on the non-oil sector. While monetary policy plays a stabilizing role by containing inflation and supporting macroeconomic balance, sustaining diversification and non-oil growth under Vision 2030 requires complementary measures, including targeted credit support, financial market deepening, and structural reforms that enhance productivity and private-sector investment. Full article

The inflation rate has shown an upward trend globally, specifically after COVID-19, and the economies of the Gulf Cooperation Council (GCC) are not an exception. A heightened inflation in the modern globalized world is indeed undesirable due to its enormous adverse consequences on all sectors of the economy. However, the true determinants of the inflation rate, particularly in the case of GCC economies, are not well-explored. Accordingly, this research paper attempts to see whether the inflation rate in GCC economies is driven by internal factors or global factors. This paper focuses on data for the period 1998 to 2023 and applies the PMG-ARDL methodology for the estimation. The results confirmed that money supply, oil prices, GDP, and global supply chain pressure are the key inflationary drivers in the long run. In contrast, trade openness has reduced the inflation rate in the long run, which is consistent with the prediction of Romer’s hypothesis. In the short run, we found that real GDP and trade openness are the main driving forces behind the heightened inflation rate. Furthermore, the causality findings indicated several unidirectional and bidirectional relationships among the variables under consideration. Our results are robust to alternative econometric estimators and hence offer valuable policy implications for the consideration of policymakers. Full article