Abstract The rapid expansion of e-commerce has intensified cybersecurity threats, particularly counterfeit product listings and fraudulent transactions, which severely undermine consumer trust and marketplace integrity. Traditional rule based monitoring systems increasingly struggle to detect these sophisticated, evolving fraud patterns. This study develops and evaluates a dual layer predictive analytics framework that leverages supervised machine learning to enhance counterfeit detection and fraud governance in digital marketplaces. Utilizing... The rapid expansion of e-commerce has intensified cybersecurity threats, particularly counterfeit product listings and fraudulent transactions, which severely undermine consumer trust and marketplace integrity. Traditional rule based monitoring systems increasingly struggle to detect these sophisticated, evolving fraud patterns. This study develops and evaluates a dual layer predictive analytics framework that leverages supervised machine learning to enhance counterfeit detection and fraud governance in digital marketplaces. Utilizing a Random Forest classifier, the research analyzes two complementary datasets: static productlevel metadata comprising seller credentials and listing characteristics, and dynamic transaction-level behavioral indicators capturing purchasing anomalies and device signatures. Following rigorous preprocessing, categorical encoding, and an 80/20 stratified train-test split, the models were benchmarked using accuracy, precision, recall, F1 Score, and ROC-AUC. The product-level classifier achieved perfect class separability, demonstrating the deterministic power of structural listing indicators. Conversely, the transaction-level model attained 99.33% accuracy, 97.99% precision, and a 0.9999 ROC-AUC, effectively capturing probabilistic behavioral fraud signatures with minimal false negatives. These findings confirm that integrating static asset metadata with dynamic transactional analytics significantly improves predictive robustness. The study concludes by proposing a unified, AI-driven marketplace governance framework capable of real-time surveillance, automated threat mitigation, and scalable regulatory compliance, ultimately advancing the deployment of transparent artificial intelligence solutions across global digital commerce networks. Read More Read Less

Abstract This study presents a comprehensive data-driven investigation of global Artificial Intelligence (AI) ethics frameworks and governance patterns through machine learning and visual analytics techniques. Analyzing a curated dataset of 112 AI policy documents published between 2016 and 2019 across public-sector institutions, private corporations, and non-governmental organizations worldwide, the research employs K-Means clustering, Principal Component Analysis, hierarchical clustering, and correlation analysis to systematically examine ethical priorities... This study presents a comprehensive data-driven investigation of global Artificial Intelligence (AI) ethics frameworks and governance patterns through machine learning and visual analytics techniques. Analyzing a curated dataset of 112 AI policy documents published between 2016 and 2019 across public-sector institutions, private corporations, and non-governmental organizations worldwide, the research employs K-Means clustering, Principal Component Analysis, hierarchical clustering, and correlation analysis to systematically examine ethical priorities embedded within 25 conceptual dimensions. Results identify three distinct document clusters: Technical and Governance Leaders emphasizing accountability, privacy, and technical explainability; Thematic or Generalist Frameworks articulating broad ethical principles with limited operational guidance; and Comprehensive Adopters reflecting mainstream consensus on fairness, transparency, and safety. Sectoral analysis reveals divergent ethical emphases: private organizations prioritize technical implementation and reliability, NGOs emphasize human rights and equity, while public institutions focus on regulatory accountability and governance. Temporal analysis demonstrates a significant shift in discourse from speculative concerns about existential AI risks to practical governance challenges, including algorithmic bias, explainability, and transparency. Correlation analysis further indicates that ethical principles function as interconnected governance ecosystems rather than isolated values, with strong associations between transparency-accountability, privacy-safety, and fairness-human rights. Geographical variations highlight the influence of cultural, legal, and institutional contexts on ethical prioritization. The findings underscore the transition of AI ethics from abstract declarations toward operational, measurable governance frameworks, while emphasizing the need for interdisciplinary collaboration and globally coordinated approaches to develop trustworthy, socially responsible AI ecosystems. Read More Read Less

Abstract The rapid expansion of digital retail has generated extensive transactional data, creating unprecedented opportunities for advanced, data-driven decision-making. Traditional Market Basket Analysis (MBA) and association rule mining frequently struggle with large, sparse datasets, often producing trivial rules while overlooking temporal and network-level purchasing dynamics. To address these limitations, this study introduces an integrated analytical framework that synergizes association rule mining, product network analytics, temporal modeling,... The rapid expansion of digital retail has generated extensive transactional data, creating unprecedented opportunities for advanced, data-driven decision-making. Traditional Market Basket Analysis (MBA) and association rule mining frequently struggle with large, sparse datasets, often producing trivial rules while overlooking temporal and network-level purchasing dynamics. To address these limitations, this study introduces an integrated analytical framework that synergizes association rule mining, product network analytics, temporal modeling, clustering, and time-series forecasting. Leveraging a synthetic dataset of 30,000 grocery transactions spanning four months, the pipeline systematically extracts meaningful product affinities and visualizes complex purchasing pathways through association rule graphs and Sankey diagrams. A product co-occurrence network subsequently identifies structural purchasing communities and central hub items that drive strategic cross-selling opportunities. Temporal trend analysis captures fluctuating customer transaction volumes, while a regression-based forecasting model extrapolates future demand trajectories to optimize inventory planning and workforce scheduling. By synthesizing these complementary analytical layers, the framework transcends conventional basket analysis to deliver a holistic understanding of retail ecosystems. The findings demonstrate how multi-dimensional analytics significantly enhance nextbasket recommendation engines, inform store layout optimization, and improve demand prediction accuracy. Ultimately, this unified approach equips retailers with actionable insights to personalize marketing strategies, streamline operational efficiency, and adapt proactively to evolving consumer behaviors in highly competitive market environments. Read More Read Less