Sports analytics (SA) incorporate machine learning (ML) techniques and models for performance prediction. Researchers have previously evaluated ML models applied on a variety of basketball statistics. This paper aims to benchmark the forecasting performance of 14 ML models, based on 18 advanced basketball statistics and key performance indicators (KPIs). The models were applied on a filtered pool of 90 high-performance players. This study developed individual forecasting scenarios per player and experimented using all 14 models. The models’ performance ranking was developed using a bespoke evaluation metric, called weighted average percentage error (WAPE), formulated from the weighted mean absolute percentage error (MAPE) evaluation results of each forecasted statistic and model. Moreover, we employed a comprehensive forecasting approach to improve KPI's results. Results showed that Tree-based models, namely Extra Trees, Random Forest, and Decision Tree, are the best performers in most of the forecasted performance indicators, with the best performance achieved by Extra Trees with a WAPE of 34.14%. In conclusion, we achieved a 3.6% MAPE improvement for the selected KPI with our approach on unseen data.

Despite medical advancements in recent years, cardiovascular diseases (CVDs) remain a major factor in rising mortality rates, challenging predictions despite extensive expertise. The healthcare sector is poised to benefit significantly from harnessing massive data and the insights we can derive from it, underscoring the importance of integrating machine learning (ML) to improve CVD prevention strategies. In this study, we addressed the major issue of class imbalance in the Behavioral Risk Factor Surveillance System (BRFSS) 2021 heart disease dataset, including personal lifestyle factors, by exploring several resampling techniques, such as the Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic Sampling (ADASYN), SMOTE-Tomek, and SMOTE-Edited Nearest Neighbor (SMOTE-ENN). Subsequently, we trained, tested, and evaluated multiple classifiers, including logistic regression (LR), decision trees (DTs), random forest (RF), gradient boosting (GB), XGBoost (XGB), CatBoost, and artificial neural networks (ANNs), comparing their performance with a primary focus on maximizing sensitivity for CVD risk prediction. Based on our findings, the hybrid resampling techniques outperformed the alternative sampling techniques, and our proposed implementation includes SMOTE-ENN coupled with CatBoost optimized through Optuna, achieving a remarkable 88% rate for recall and 82% for the area under the receiver operating characteristic (ROC) curve (AUC) metric.

Integrating Large Language Models (LLMs) into e-government applications has the potential to improve public service delivery through advanced data processing and automation. This paper explores critical aspects of a modular and reproducible architecture based on Retrieval-Augmented Generation (RAG) for deploying LLM-based assistants within e-government systems. By examining current practices and challenges, we propose a framework ensuring that Artificial Intelligence (AI) systems are modular and reproducible, essential for maintaining scalability, transparency, and ethical standards. Our approach utilizing Haystack demonstrates a complete multi-agent Generative AI (GAI) virtual assistant that facilitates scalability and reproducibility by allowing individual components to be independently scaled. This research focuses on a comprehensive review of the existing literature and presents case study examples to demonstrate how such an architecture can enhance public service operations. This framework provides a valuable case study for researchers, policymakers, and practitioners interested in exploring the integration of advanced computational linguistics and LLMs into e-government services, although it could benefit from further empirical validation.

As public institutions increasingly adopt AI-driven virtual assistants to support transparency and citizen engagement, the need for explainable, accurate, and context-aware language systems becomes vital. While traditional retrieval-augmented generation (RAG) frameworks effectively integrate external knowledge into Large Language Models (LLMs), their reliance on flat, unstructured document retrieval limits multi-hop reasoning and interpretability, especially with complex, structured e-government datasets. This study introduces a modular, extensible, multi-agent graph retrieval-augmented generation (GraphRAG) framework designed to enhance policy-focused question answering. This research aims to provide an overview of hybrid multi-agent GraphRAG architecture designed for operational deployment in e-government settings to support explainable AI systems. The study focuses on how the hybrid integration of standard RAG, embedding-based retrieval, real-time web search, and LLM-generated structured Graphs can optimize knowledge discovery from public e-government data, thereby reinforcing factual grounding, reducing hallucinations, and enhancing the quality of complex responses. To validate the proposed approach, we implement and evaluate the framework using the European Commission’s Press Corner as a data source, constructing graph-based knowledge representations and embeddings, and incorporating web search. This work establishes a reproducible blueprint for deploying AI systems in e-government that require structured reasoning in comprehensive and factually accurate question answering.

This study investigates the impact of injuries on National Basketball Association (NBA) player performance over 20 seasons, using large-scale performance data and a statistical evaluation. Injury events were matched with player–game performance metrics to assess how various injury types influence short-, medium-, and long-term performance outcomes, measured across 2-, 5-, and 10-game windows. Using paired sample t-tests and Cohen’s d, we quantified both the statistical significance and effect size of changes in key performance metrics before and after injury. The analysis applies paired t-tests and Cohen’s d to quantify the statistical and practical significance of performance deviations pre- and post-injury. Our results show that while most injury types are associated with measurable performance declines, especially in offensive and defensive ratings, certain categories, such as cardiovascular injuries, demonstrate counterintuitive improvements post-recovery. These patterns suggest that not all injuries have equivalent consequences and highlight the importance of individualized recovery protocols. This work contributes to the growing field of sports injury analytics by combining statistical modeling and sports analytics to deliver actionable insights for coaches, medical staff, and performance analysts in managing player rehabilitation and optimizing return-to-play decisions.

This study examines the multifaceted field of injuries and their impacts on performance in the National Basketball Association (NBA), leveraging a blend of Data Science, Data Mining, and Sports Analytics. Our research is driven by three pivotal questions: Firstly, we explore how Association Rule Mining can elucidate the complex interplay between players’ salaries, physical attributes, and health conditions and their influence on team performance, including team losses and recovery times. Secondly, we investigate the relationship between players’ recovery times and their teams’ financial performance, probing interdependencies with players’ salaries and career trajectories. Lastly, we examine how insights gleaned from Data Mining and Sports Analytics on player recovery times and financial influence can inform strategic financial management and salary negotiations in basketball. Harnessing extensive datasets detailing player demographics, injuries, and contracts, we employ advanced analytic techniques to categorize injuries and transform contract data into a format conducive to deep analytical scrutiny. Our anomaly detection methodologies, an ensemble combination of DBSCAN, isolation forest, and Z-score algorithms, spotlight patterns and outliers in recovery times, unveiling the intricate dance between player health, performance, and financial outcomes. This nuanced understanding emphasizes the economic stakes of sports injuries. The findings of this study provide a rich, data-driven foundation for teams and stakeholders, advocating for more effective injury management and strategic planning. By addressing these research questions, our work not only contributes to the academic discourse in Sports Analytics but also offers practical frameworks for enhancing player welfare and team financial health, thereby shaping the future of strategic decisions in professional sports.