Nabil M. Hewahi

National Statistical Offices (NSOs) face an escalating “privacy‐utility” impasse, where the demand for high‐granularity data must compete with the near zero risk tolerance of legal frameworks like the General Data Protection Regulation (GDPR). Traditional centralized collection creates “honeypots” for breaches, exposing a nation's entire digital census or tax records. This paper provides a systematic review of Federated Learning (FL) as a decentralized framework that eliminates raw microdata consolidation. Drawing on 77 peer‐reviewed. Studies and technical reports published between 2020 and 2026, the study evaluates Horizontal and Vertical FL architectures alongside Privacy‐Enhancing Technologies (PETs). The analysis reveals that while PETs introduce a “utility gap,” Under controlled experimental settings and standardized non‐IID configurations, the evaluated architectures frequently achieve utility bounds exceeding 90% of their centralized equivalents, though this outcome varies based on the assigned privacy budget () and data distribution. Crucially, the study demonstrates that the mathematical noise required for Differential Privacy (DP) can threaten strict accuracy thresholds; for example, an aggressive privacy budget can cause census distributions to shift more than 77% from the true mean, rendering indicators like Gross Domestic Product (GDP) or unemployment rates statistically meaningless. Beyond these accuracy trade‐offs, the paper addresses the Non‐Independent and Identically Distributed (Non‐IID) nature of government datasets and identifies research gaps in standardized audit trails. The paper proposes a novel roadmap for integrating FL into the Generic Statistical Business Process Model (GSBPM), offering NSOs and international statistical bodies a technically grounded and legally coherent pathway toward next generation data infrastructure.

As regulatory requirements increasingly shape automated lending decisions, fairness remains a critical challenge in high-stakes domains, particularly credit scoring. Although artificial intelligence models can achieve strong predictive performance, they may also reproduce biased outcomes that reduce financial inclusion or transfer harm to overlooked protected groups. Existing fairness interventions commonly operate at a single stage of the decision-making pipeline, despite bias often propagating across representational and decision layers. This study proposes iCert-Fair, a two-layer framework for technical fairness assessment and harm recovery in credit scoring. The first layer adopts a fairness-through-explainability paradigm, using SHAP-based explanations to identify direct and proxy dependence on protected attributes and guide structural dataset repair, while the second layer applies targeted threshold-policy adjustments to recover residual harm while preserving decision utility. Experiments on the German and Taiwanese credit datasets show that fairness gains are model- and dataset-specific and may be collective, concentrated, transferred, or recovered unevenly across protected attributes. The direct comparison with representative pre-processing, in-processing, and post-processing methods revealed that baseline methods targeting one protected attribute at a time frequently transferred residual harm to other monitored attributes. In contrast, the fairness-focused recommendations generated by iCert-Fair achieved larger collective fairness improvements across all considered protected attributes while avoiding residual harm. These gains were obtained while preserving predictive utility on the German dataset and with utility degradation remaining below 5% across the evaluated performance metrics on the Taiwanese dataset, alongside consistently lower false-negative risk. The empirical findings support the use of complementary structural and policy-level interventions and demonstrate the importance of jointly evaluating aggregate disparity, worst-case attribute-level harm, cross-attribute transfer, and predictive utility.

Physics-Informed Neural Networks (PINNs) have emerged as a powerful framework that integrates machine learning with the governing physical laws expressed by Partial Differential Equations (PDEs). By embedding the residuals of differential operators into the loss function, PINNs can simultaneously solve both forward and inverse problems within physics-based systems. In this study, we propose an adaptive inverse Decomposed Physics-Informed Neural Network (DPINN) framework for optimizing the water flocculation process, modeled through transport equations that span diffusion, advection–diffusion, and settling formulations for pollutant localization. The approach begins by constructing a forward DPINN architecture capable of representing multiscale spatio-temporal dynamics, followed by an inverse formulation in which key transport parameters such as diffusion coefficients, advection velocities, and reaction rates are treated as trainable variables. Experimental or simulated reference data are incorporated into a composite loss function to guide the inversion process. The results demonstrate that the convergence of the inverse DPINN toward physically consistent parameter estimation requires an adaptive loss-weighting strategy among the data misfit, boundary and initial conditions, and the PDE residuals. Furthermore, gradient rescaling at each training epoch enhances stability and accelerates convergence, particularly in high–Peclet-number and strongly coupled Multiphysics systems. Compared to standard PINNs, the DPINN architecture achieves superior scalability, numerical stability, and computational efficiency by decomposing the global domain into overlapping subdomains trained in parallel. These findings establish DPINN as a robust and data-efficient framework for solving multiscale environmental transport problems, offering new potential for the optimization and real-time control of complex processes such as water flocculation.

The integration of artificial intelligence (AI) in the financial sector has seen a rapid increase over the past few years, offering new possibilities to streamline processes while ensuring profitability for lending institutions. With its data-driven capability, predicting the creditworthiness of applicants has demonstrated strong predictive performance, particularly for thin-file clients. Despite these advances, growing concerns regarding AI’s fairness, explainability, and regulatory accountability have increasingly limited its adoption in high-stakes credit decision-making. This paper presents a synthesis derived from a systematic literature review (SLR) of 43 peer-reviewed studies published between 2020 and 2025, focusing on AI-based credit scoring and addressing at least one of the performance, fairness, or explainability dimensions. Eligible studies were limited to peer-reviewed journal and conference articles (2020–2025) retrieved from IEEE Xplore, Scopus, Web of Science, and ScienceDirect (last searched: 30 September), examining AI-driven credit scoring in consumer or lending decision contexts. Guided by the Relevance, Rigor, Reproducibility, and Quality (3Rs&Q) appraisal framework, the review analyzes how existing approaches navigate the interplay among performance, fairness, and explainability under regulatory and human oversight considerations. The findings indicate that these dimensions are predominantly addressed in isolation, with limited attention to their joint treatment in regulated deployment settings. By consolidating empirical and conceptual evidence, this review provides actionable guidance for designing and deploying credit scoring models in practice.

Feature selection is pivotal in enhancing the efficiency of credit scoring predictions, where misclassifications are critical because they can result in financial losses for lenders and exclusion of eligible borrowers. While traditional feature selection methods can improve accuracy and class separation, they often struggle to maintain consistent performance aligned with institutional preferences across datasets of varying size and imbalance. This study introduces a FastTree-Guided Genetic Algorithm (FT-GA) that combines gradient-boosted learning with evolutionary optimization to prioritize class separability and minimize false-risk exposure. In contrast to traditional approaches, FT-GA provides fine-grained search guidance by acknowledging that false positives and false negatives carry disproportionate consequences in high-stakes lending contexts. By embedding domain-specific weighting into its fitness function, FT-GA favors separability over raw accuracy, reflecting practical risk sensitivity in real credit decision settings. Experimental results show that FT-GA achieved similar or higher AUC values ranging from 76% to 92% while reducing the average feature set by 21% when compared with the strongest baseline techniques. It also demonstrated strong performance on small to moderately imbalanced datasets and more resilience on highly imbalanced ones. These findings indicate that FT-GA offers a risk-aware enhancement to automated credit assessment workflows, supporting lower operational risk for financial institutions while showing potential applicability to other high-stakes domains.

With industrial and technological development and the increasing demand for electric power, wind energy has gradually become the fastest-growing and most environmentally friendly new energy source. Nevertheless, wind power generation is always accompanied by uncertainty due to the wind speed's volatility. Wind speed forecasting (WSF) is essential for power grids' dispatch, stability, and controllability, and its accuracy is crucial to effectively using wind resources. Therefore, this study proposes a novel WSF framework for stationary data based on a hybrid decomposition method and the Bidirectional Long Short-term Memory (BiLSTM) to achieve high forecasting accuracy for the Dumat Al-Jandal wind farm in Al-Jouf, Saudi Arabia. The hybrid decomposition method combines the Wavelet Packet Decomposition (WPD) and the Seasonal Adjustment Method (SAM). The SAM method eliminates the seasonal component of the decomposed subseries generated by WPD to reduce forecasting complexity. The BiLSTM is applied to forecast all the deseasonalized decomposed subseries. Five years of hourly wind speed observations acquired from a location in the Al-Jouf region were used to prove the effectiveness of the proposed model. The comparative experimental results, including 27 other models, demonstrated the proposed model's superiority in single and multiple WSF with an overall average mean absolute error of 0.176549, root mean square error of 0.247069, and R-squared error of 0.985987.

In recent years, ML algorithms have been shown to be useful for predicting diseases based on health data and posed a potential application area for these algorithms such as modeling of diseases. The majority of these applications employ supervised rather than unsupervised ML algorithms. In addition, each year, the amount of data in medical science grows rapidly. Moreover, these data include clinical and Patient-Related Factors (PRF), such as height, weight, age, other physical characteristics, blood sugar, lipids, insulin, etc., all of which will change continually over time. Analysis of historical data can help identify disease risk factors and their interactions, which is useful for disease diagnosis and prediction. This wealth of valuable information in these data will help doctors diagnose accurately and people can become more aware of the risk factors and key indicators to act proactively. The purpose of this study is to use six supervised ML approaches to fill this gap by conducting a comprehensive experiment to investigate the correlation between PRF and Diabetes, Stroke, Heart Disease (HD), and Kidney Disease (KD). Moreover, it will investigate the link between Diabetes, Stroke, and KD and PRF with HD. Further, the research aims to compare and evaluate various ML algorithms for classifying diseases based on the PRF. Additionally, it aims to compare and evaluate ML algorithms for classifying HD based on PRF as well as Diabetes, Stroke, Asthma, Skin Cancer, and KD as attributes. Lastly, HD predictions will be provided through a Web-based application on the most accurate classifier, which allows the users to input their values and predict the output. Logistic Regression (LR), Naive Bayes (NB), Random Forest (RF), K-Nearest Neighbor (KNN), Extreme Gradient Boost (XGB), and Support Vector Machine (SVM) were the algorithms used. The dataset was obtained from the Kaggle repository. The attributes are divided into PRF and diseases. The selected algorithms were implemented on the dataset with the optimal hyperparameters determined by using the “GridsearchCV” method in order to obtain the best performance. The accuracy of the algorithms ranged from 70% to 76%. Based on the accuracy, recall, precision, and F1-score measures for all algorithms, all ML algorithms predicted HD more accurately than diabetes, strokes, and KD. The algorithms even performed better when predefined diseases were combined with PRF in order to predict HD. Although there was no significant difference between the algorithms, LR achieved the highest score with 75%, when using only PRF and 76% when using a combination of disease attributes and PRF using a 70/30 split. Furthermore, accuracy increased from 74.8 to 76% when using the 10-fold CV. Two conclusions have been drawn: these features are more closely related to HD compared to other diseases and can be useful in predicting HD more proactively. Furthermore, the risk of HD increases with the presence of predefined diseases, especially Diabetes and Stroke. In terms of performance, LR was always one of the superior classifiers that performed similarly to more complex Machine Learning algorithms, while NB performed the worst.

With industrial and technological development and the increasing demand for electric power, wind energy has gradually become the fastest-growing and most environmentally friendly new energy source. Nevertheless, wind power generation is always accompanied by uncertainty due to the wind speed's volatility. Wind speed forecasting (WSF) is essential for power grids' dispatch, stability, and controllability, and its accuracy is crucial to effectively using wind resources. Therefore, this study proposes a novel WSF framework for stationary data based on a hybrid decomposition method and the Bidirectional Long Short-term Memory (BiLSTM) to achieve high forecasting accuracy for the Dumat Al-Jandal wind farm in Al-Jouf, Saudi Arabia. The hybrid decomposition method combines the Wavelet Packet Decomposition (WPD) and the Seasonal Adjustment Method (SAM). The SAM method eliminates the seasonal component of the decomposed subseries generated by WPD to reduce forecasting complexity. The BiLSTM is applied to forecast all the deseasonalized decomposed subseries. Five years of hourly wind speed observations acquired from a location in the Al-Jouf region were used to prove the effectiveness of the proposed model. The comparative experimental results, including 27 other models, demonstrated the proposed model's superiority in single and multiple WSF with an overall average mean absolute error of 0.176549, root mean square error of 0.247069, and R-squared error of 0.985987.