Search Results (517)

As a form of long-term asset allocation, pension fund investment necessitates accurate estimation of both asset returns and associated risks over extended time horizons. However, long-term asset returns are significantly influenced by macroeconomic factors, whereas variance-based risk measures cannot account for the directional nature of deviations from expected returns. To address these issues, we propose a novel CVaR-based Black–Litterman model incorporating macroeconomic cycle views (CVaR-BL-MCV) for optimal asset allocation of pension funds. This approach integrates macroeconomic cycle dynamics to quantify their impact on asset returns and utilizes Conditional Value-at-Risk (CVaR) as a coherent measure of downside risk. We employ a Markov-switching model to identify and forecast the phases of economic and monetary cycles. By analyzing the economic cycle with PMI and CPI, economic conditions are categorized into three distinct phases: stable, transitional, and overheating. Similarly, by analyzing the monetary cycle with M2 and SHIBOR, monetary conditions are classified into expansionary and contractionary phases. Based on historical asset return data across these cycles, view matrices are constructed for each cycle state. CVaR is used as the risk measure, and the posterior distribution of the Black–Litterman (BL) model is derived via generalized least squares (GLS), thereby extending the traditional BL framework to a CVaR-based approach. The experimental results demonstrate that the proposed CVaR-BL-MCV model outperforms the benchmark models. When the risk aversion coefficient is 1, 1.5, and 3, the Sharpe ratio of pension asset allocation using the CVaR-BL-MCV model is 21.7%, 18.4%, and 20.5% higher than that of the benchmark models, respectively. Moreover, the BL model incorporating CVaR improves the Sharpe ratio of pension asset allocation by an average of 19.7%, while the BL model with MCV achieves an average improvement of 14.4%. Full article

The rapid evolution of digital assets transforms cryptocurrencies into one of the most volatile and data-rich financial markets. Their nonlinear and unpredictable nature limits the effectiveness of traditional forecasting models, motivating the use of machine learning methods to identify hidden patterns and short-term price movements. This study compares the performance of Logistic Regression (LR), Random Forest (RF), XGBoost, Support Vector Classifier (SVC), K-Nearest Neighbors (KNNs), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) models in predicting the daily price directions of Bitcoin (BTC), Ethereum (ETH), and Ripple (XRP). Extensive data preprocessing and feature engineering are performed, integrating a broad set of technical indicators to enhance model generalization and capture temporal market dynamics. The results show that XGBoost achieves the highest classification accuracy of 55.9% for BTC and 53.8% for XRP, while LR provides the best result for Ethereum with an accuracy of 54.4%. In trading simulations, XGBoost achieves the strongest performance, generating a cumulative return of 141.4% with a Sharpe ratio of 1.78 for Bitcoin and 246.6% with a Sharpe ratio of 1.59 for Ripple, whereas LSTM delivers the best results for Ethereum with a 138.2% return and a Sharpe ratio of 1.05. Compared to recent studies, the proposed approach attains slightly higher accuracy, while demonstrating stronger robustness and profitability in practical backtesting. Overall, the findings confirm that through rigorous preprocessing machine learning-based strategies can effectively capture short-term price movements and outperform the conventional buy-and-hold benchmark, even under a simple rule-based trading framework. Full article

Stock return prediction in emerging markets remains difficult due to the gap between theoretical efficiency and empirical irregularities. This study assesses the statistical and economic performance of Linear Regression, Ridge Regression, Random Forest, and XGBoost in forecasting 5-day and 21-day returns for six LQ45 stocks (2016–2025). Momentum, volatility, trend, and volume indicators are used as predictors, while model performance is evaluated using MAE, RMSE, R², and backtested trading metrics that include transaction costs. All models yield near-zero or negative R², directional accuracy of 49–54%, and AUC around 0.50–0.53, indicating weak signals overshadowed by noise. XGBoost offers the lowest statistical errors, but Ridge Regression achieves slightly better risk-adjusted outcomes (Sharpe 0.1232), although every strategy underperforms Buy & Hold. SHAP results show volatility and volume features as most influential, but with minimal absolute impact. Overall, the LQ45 market exhibits semi-efficiency: patterns exist but fail to translate into profitable trading once real-world frictions are considered, underscoring the gap between statistical predictability and economic viability in algorithmic trading. This research was conducted in order to support the achievement of various goals through SDG 8 (Decent Work and Economic Growth). Full article

Flooding is one of Africa’s most impactful natural disasters, significantly affecting human lives, infrastructure, and economies. This study examines the spatial and temporal distribution of historical flood events across the continent from 1927 to 2020, with a focus on fatalities, affected populations, and economic damage. Data from the Emergency Events Database (EM-DAT), the fifth generation of bias-corrected European Centre for Medium-Range Weather Forecasts Reanalysis (ERA5), and the Climate Hazards Group InfraRed Precipitation with Stations (CHIRPS) observational datasets were used to calculate extreme precipitation indices—Consecutive Wet Days (CWD), annual precipitation on very wet days (R95PTOT), and Annual Maximum Precipitation (AMP). Spatial analysis tools and the Mann–Kendall test were used to assess trends in flood occurrences, while Pearson correlation analysis identified key meteorological drivers across 16 African capital cities for 1981–2019. A flood frequency analysis was conducted using Weibull, Gamma, Lognormal, Gumbel, and Logistic probability distribution models to compute flood return periods for up to 100 years. Results reveal a significant upward trend with a slope above 0.50 floods per year in flood frequency and impact over the period, particularly in regions such as West Africa (Nigeria, Ghana), East Africa (Ethiopia, Kenya, Tanzania), North Africa (Algeria, Morocco), Central Africa (Angola, Democratic Republic of Congo), and Southern Africa (Mozambique, Malawi, South Africa). Positive trends (at 99% significance level with slopes ranging between 0.50 and 0.60 floods per year) were observed in flood-related fatalities, affected populations, and economic damage across Regional Economic Communities (RECs), individual countries, and cities of Africa. The CWD, R95PTOT, and AMP indices emerged as reliable predictors of flood events, while non-stationary return periods exhibited low uncertainties for events within 20 years. These findings underscore the urgency of implementing robust flood disaster management strategies, enhancing flood forecasting systems, and designing resilient infrastructure to mitigate growing flood risks in Africa’s rapidly changing climate. Full article

This study explores the role of decentralized physical infrastructure networks (DePINs) in enhancing solar energy forecasting, focusing on how network density influences prediction accuracy and economic viability. Using machine learning models applied to production data from 47 residential PV systems in Utrecht, Netherlands, we developed a hierarchical forecasting framework: Level 1 (clear-sky baseline without historical data), Level 2 (solo forecasting using only local historical data), and Level 3 (networked forecasting incorporating data from neighboring installations). The results show that networked forecasting substantially improves accuracy: under solo forecasting conditions (Level 2), the Random Forests model reduces Mean Absolute Error (MAE) by 17% relative to the Level 1 baseline, and incorporating all available neighbors (Level 3) further reduces the MAE by an additional 34% relative to Level 2, corresponding to a total improvement of 45% compared with Level 1. The largest accuracy gains arise from the first 10–15 neighbors, highlighting the dominant influence of local spatial correlations. These forecasting improvements translate into significant economic benefits. Imbalance costs decrease from EUR 1618 at Level 1 to EUR 1339 at Level 2 and further to EUR 884 at Level 3, illustrating the financial impact of both solo and networked data sharing. A marginal benefit analysis reveals diminishing returns beyond approximately 10–15 neighbors, consistent with spatial saturation effects within 5–10 km radii. These findings provide a quantitative foundation for incentive mechanisms in DePIN ecosystems and demonstrate that privacy-preserving data sharing mitigates data fragmentation, reduces imbalance costs for energy traders, and creates new revenue opportunities for participants, thereby supporting the development of decentralized energy markets. Full article

The impact of the COVID-19 pandemic on the number of international tourist arrivals in the Republic of South Africa (RSA) is studied in this paper using the seasonal autoregressive integrated moving average (SARIMA) model comprising a pulse function covariate vector evaluated via trial and error as an exogenous variable (SARIMAX). This paper provides a methodological innovation that combines outlier detection with intervention quantification so that tourism academics and practitioners can correctly capture estimated economic losses caused by the COVID-19 pandemic and the response to it. In the pre-intervention modelling, four additive outliers and innovative outliers were detected and incorporated into the SARIMAX$(1,1,1)({0,1,2)}_{12}$ model, which significantly lowered the model’s evaluation metrics, making it the best fitting pre-intervention model. Next, from March 2020 to June 2025 (end of dataset), it is shown that the estimated total losses amount to 7,328,919 tourists compared to if there been no pandemic. This means that the number of tourist arrivals in the RSA has not yet returned to the pre-COVID-19 forecasted path as of June 2025, indicating that the COVID-19 pandemic continues to have long-term negative effects on the RSA’s number of tourist arrivals. Therefore, more efforts must be focused on developing innovative and advanced statistical models to assist the RSA government and private entities in creating incentives for investment, planning more effectively, providing societies reliant on tourism with more resources, and creating suitable regulations that boost the economy through the tourism sector. Full article

This study aims to forecast the combined impacts of drought and flood in the future using an integrated framework. This framework integrates U-Net++, quantile mapping (QM), Copula models, and ISIMIP3b gridded large-scale discharge data (1985–2014, 2021–2050, and 2071–2100). Copula models analyze compound effects in four dimensions to determine return periods for droughts and floods. The standalone U-Net++ and its integration with multiple linear regression, multiple nonlinear regression, M5 model tree, multivariate adaptive regression splines, and QM downscaled ISIMIP3b model river flows. U-Net++QM outperformed other models, with a 58% lower RRMSE. Ensemble GCMs showed less uncertainty than other models in river flow downscaling. For the Ensemble model, the highest drought severity was −300, the maximum duration was 300 months, flood peak flow reached 12,000 m³/s, and intervals lasted up to 22 months. Moreover, the return periods of compound events for this model ranged from 50 to 3000 years. Future river flow projections, using the Ensemble model and emission scenarios (SSP126, SSP370, and SSP585), showed increased vulnerability in 2071 and 2025 versus the observed period. Introducing an integrated framework serves as a management tool for addressing extreme combined phenomena under climate change. Full article

Accurately predicting asset returns remains a central challenge in finance, with significant implications for portfolio optimization and risk management. In response to the challenge, this study evaluates the predictive performance of machine learning algorithms in estimating excess returns of U.S. industry portfolios, within the out-of-sample prediction framework of the Fama–French three-, four-, five- and six-factor asset pricing models. In the analysis, Support Vector Regression, Multilayer Perceptron, Linear Regression, and k-Nearest Neighbor were employed using monthly return data from 1992 to 2022, covering 5-, 10-, 12-, 17-, 30-, 38-, 48-, and 49-portfolio configurations composed of NYSE, AMEX, and NASDAQ-listed firms. The findings reveal that support vector regression achieved the highest number of top-ranked results, producing the most successful outcomes in 305 out of 836 model–portfolio combinations. However, multilayer perceptron achieved the best fit in the largest number of portfolios, ranking first in all groups except the 5-industry configuration. Furthermore, the Fama–French five-factor model outperformed other specifications across all groupings, confirming the value of incorporating profitability and investment information. Predictive performance also varied by industry, as wholesale and manufacturing sectors exhibited strong alignment, whereas utilities and energy-related sectors, likely constrained by structural or regulatory features, remained less responsive and exposed to long-term risks. Full article

This paper presents a comprehensive methodology to forecast the daily energy demand associated with recharging private electric vehicles in urban areas. The approach is based on plausible scenarios regarding the penetration of battery-powered vehicles and the availability of charging infrastructure. Accurate space and time forecasting of charging activities and power requirements is a critical issue in supporting the transition from conventional to battery-powered vehicles for urban mobility. This technological shift represents a key milestone toward achieving the zero-emissions target set by the European Green Deal for 2050. The methodology leverages Floating Car Data (FCD) samples. The widespread use of On-Board Units (OBUs) in private vehicles for insurance purposes ensures the methodology’s applicability across diverse geographical contexts. In addition to FCD samples, the estimation of charging demand for private electric vehicles is informed by a large-scale, detailed survey conducted by ENEA in Italy in 2023. Funded by the Ministry of Environment and Energy Security as part of the National Research on the Electric System, the survey explored individual charging behaviors during daily urban trips and was designed to calibrate a discrete choice model. To date, the methodology has been applied to the Metropolitan Area of Rome, demonstrating robustness and reliability in its results on two different scenarios of analysis. Each demand/supply scenario has been evaluated in terms of the hourly distribution of peak charging power demand, at the level of individual urban zones or across broader areas. Results highlight the role of the different components of power demand (at home or at other destinations) in both scenarios. Charging at intermediate destinations exhibits a dual peak pattern—one in the early morning hours and another in the afternoon—whereas home-based charging shows a pronounced peak during evening return hours and a secondary peak in the early afternoon, corresponding to a decline in charging activity at other destinations. Power distributions, as expected, sensibly differ from one scenario to the other, conditional to different assumptions of private and public recharge availability and characteristics. Full article

Financial return distributions often exhibit central asymmetry and heavy-tailed extremes, challenging standard parametric models. We propose a novel composite distribution integrating a skew-normal center with skew-t tails, partitioning the support into three regions with smooth junctions. The skew-normal component captures moderate central asymmetry, while the skew-t tails model extreme events with power-law decay, with tail weights determined by continuity constraints and thresholds selected via Hill plots. Monte Carlo simulations show that the composite model achieves superior global fit, lower-tail KS statistics, and stable parameter estimation compared with skew-normal and skew-t benchmarks. We further conduct simulation-based and empirical backtesting of risk measures, including Value-at-Risk (VaR) and Expected Shortfall (ES), using generated datasets and 2083 TSLA daily log returns (2017–2025), demonstrating accurate tail risk capture and reliable risk forecasts. Empirical fitting also yields improved log-likelihood and diagnostic measures (P–P, Q–Q, and negative log P–P plots). Overall, the proposed composite distribution provides a flexible theoretically grounded framework for modeling asymmetric and heavy-tailed financial returns, with practical advantages in risk assessment, extreme event analysis, and financial risk management. Full article

Financial forecasting remains essential for supporting strategic decisions and risk oversight in the banking sector. This study examines whether Adaptive Neuro-Fuzzy Inference Systems (ANFISs) can enhance Earnings per Share (EPS) prediction for European banks by integrating four core financial indicators: Return on Assets, Return on Equity, Capital Ratio, and Profit Margin. Using an annual panel of 25 institutions between 2013 and 2023, we benchmark multiple membership function shapes and granularities to identify robust model configurations. The empirical analysis combines chronological holdout testing with Leave-One-Out cross-validation to evaluate accuracy and stability. Findings highlight a sigmoid-based ANFIS specification with four fuzzy sets per input as the most consistent performer, offering interpretable rules that complement conventional forecasting techniques. Full article

Sensor networks generate high-dimensional temporally dependent data across healthcare, environmental monitoring, and energy management, which demands robust machine learning for reliable forecasting. While gradient boosting methods have emerged as powerful tools for sensor-based regression, systematic evaluation under realistic deployment conditions remains limited. This work provides a comprehensive review and empirical benchmark of boosting algorithms spanning classical methods (AdaBoost and GBM), modern gradient boosting frameworks (XGBoost, LightGBM, and CatBoost), and adaptive extensions for streaming data and hybrid architectures. We conduct rigorous cross-domain evaluation on continuous glucose monitoring, urban air-quality forecasting, and building-energy prediction, assessing not only predictive accuracy but also robustness under sensor degradation, temporal generalization through proper time-series validation, feature-importance stability, and computational efficiency. Our analysis reveals fundamental trade-offs challenging conventional assumptions. Algorithmic sophistication yields diminishing returns when intrinsic predictability collapses due to exogenous forcing. Random cross-validation (CV) systematically overestimates performance through temporal leakage, with magnitudes varying substantially across domains. Calibration drift emerges as the dominant failure mode, causing catastrophic degradation across all the static models regardless of sophistication. Importantly, feature-importance stability does not guarantee predictive reliability. We synthesize the findings into actionable guidelines for algorithm selection, hyperparameter configuration, and deployment strategies while identifying critical open challenges, including uncertainty quantification, physics-informed architectures, and privacy-preserving distributed learning. Full article

As global warming intensifies, extreme weather phenomena such as heatwaves, flash droughts, torrential floods, cold waves, and blizzards are becoming increasingly frequent. Against this backdrop, traditional static food security assessment methods fail to capture the dynamic transmission patterns of agricultural productivity risks and their regional heterogeneity. Therefore, it is imperative to reconstruct a resilience analysis paradigm for food production systems, dynamically investigate the mechanisms through which climate change affects China’s agricultural productivity and discern the interactive effects between technological evolution and climate constraints. This will provide theoretical foundations for building a climate-resilient food security system. Accordingly, this study establishes a multidimensional resilience measurement index system for China’s grain productivity by integrating agricultural factor elasticity analysis with disaster impact response modeling. Through production function decomposition and hybrid forecasting models, we reveal the evolutionary patterns of China’s grain productivity under climate risk shocks and trace the transmission pathways of risk fluctuations. Key findings indicate the following: (1) Extreme climate events exhibit significant negative correlations with grain production, with drought and flood impacts demonstrating pronounced regional heterogeneity. (2) A dynamic game relationship exists between agricultural technological progress and climate risk constraints, where the marginal contribution of resource efficiency improvements to productivity growth shows diminishing returns. (3) Climate-sensitive factors vary substantially across agricultural zones: Northeast China faces dominant cold damage, North China experiences drought stress, while South China contends with humid-heat disasters as primary regional risks. Consequently, strengthening foundational agricultural infrastructure and optimizing regionally differentiated risk mitigation strategies constitute critical pathways for enhancing food security resilience. (4) Future research should leverage higher-resolution, county-level data and incorporate a wider range of socio-economic variables to enhance granular understanding and predictive accuracy. Full article

We present an enhanced Extreme Value Analysis (EVA) framework designed to improve the forecasting of extremely low-production events in photovoltaic (PV) systems and to reveal the key inter-variable relationships governing performance under extreme conditions. The proposed Extreme Value Dynamic Benchmarking Method (EVDBM) extends classical EVA by integrating the Dynamic Identification of Significant Correlation (DISC)-thresholding algorithm and explainable AI (XAI) mechanisms, enabling dynamic identification and quantification of correlation shifts during extreme scenarios. Through a combination of grid and Bayesian optimization, EVDBM adaptively fine-tunes variable weights to improve fit, interpretability, and benchmarking consistency. By transforming return values predicted via EVA into dynamic benchmarking scores, EVDBM evolves static tail modeling into a data-driven, explainable benchmarking system capable of identifying critical vulnerabilities and resilience patterns in real time. Applied to real PV production datasets, EVDBM achieved an average improvement of 13.2% in correlation-based $R_{corr}^2$ and demonstrated statistically significant reductions in residual error ($p_t<0.01$) in the João dataset, confirming its robustness and generalizability. Quantile-to-quantile analyses further showed improved alignment between modeled and empirical extremes, validating the method’s stability across distributional tails. Ablation studies revealed cumulative gains in interpretability and predictive stability in the EVA → EVDBM → EVDBM + XAI progression, while computational complexity remained near-linear with respect to input dimensionality. Overall, EVDBM delivers a transparent, statistically validated, and operationally interpretable framework for extreme event modeling. Its explainable benchmarking structure supports actionable insights for risk management, infrastructure resilience, and strategic energy planning, establishing EVDBM as a generalizable approach for understanding and managing extremes across diverse application domains. Full article

Unlike most other measures in flood risk management, flood forecasting stands out because it is not designed to address a pre-defined return period. In principle it is applicable to a whole range of possible events and can be operated continuously in real time. This makes flood forecasting an effective non-structural measure for saving lives and property, even in the face of increased hydro-meteorological variability and extremes. In Germany, a series of regional and transregional flood forecasting centres and services have been established that cover the entire national territory. For large basins, the existing forecasting centres are well equipped to provide accurate real-time forecasts. Nevertheless, there are remaining challenges that need to be met when the focus is on small to medium-sized catchments. This study focuses on discussing the capabilities of six state-of-the-art flood forecasting centres and derives the most important requirements for significant improvements in flood forecasting capabilities for small to medium-sized catchment areas. We emphasise that future research must focus on flood-driven predictions, including the prediction of flood inundation and consequences for buildings and infrastructure, as well as geotechnical failure mechanisms in Germany. Full article