The rapid digitalization of institutional operations has increased exposure to cyber threats, particularly phishing attacks that exploit human and system vulnerabilities. Traditional security mechanisms often fail to detect evolving phishing techniques due to their static and reactive nature. This study presents an intelligent predictive analytics framework designed to enhance institutional cyber resilience through proactive phishing attack detection. Using a dataset of 2,200 labeled web-based interaction records, the study applied supervised machine learning techniques to identify malicious patterns indicative of phishing activities. Two predictive models; Random Forest (RF) and Support Vector Machine (SVM) were developed and evaluated using standard performance metrics including accuracy, precision, recall, and F1-score. Experimental results reveal that the Random Forest model achieved superior predictive performance, recording an accuracy of 95.7%, while SVM achieved 93.3%. The findings demonstrate that predictive analytics can significantly strengthen institutional cybersecurity by improving early threat detection, minimizing false positives, and enhancing overall system resilience. This study contributes to cybersecurity research by providing a scalable, data-driven framework suitable for deployment in institutional environments seeking proactive phishing mitigation strategies.

E-commerce has transformed global trade by increasing accessibility and convenience, but challenges such as fraud, data breaches, and high intermediary costs still affect trust and efficiency. In Nigeria, these issues are intensified by logistical barriers and low consumer confidence. This study developed a blockchain-based e-commerce platform using the Solana blockchain to enhance transparency, security, and cost efficiency. The system was built with Next.js and integrated with Solana for transaction execution, guided by a prototyping SDLC model. Core features included user authentication, product listings, secure payments, and merchant dashboards. Performance testing on Solana Playground showed an average throughput of 3.2 TPS and transaction confirmation times under one second, with costs below 0.015 SOL per transaction. The results demonstrate Solana’s capability for scalable, low-latency digital commerce, providing empirical evidence of blockchain’s potential for secure, real-time e-commerce operations in emerging markets like Nigeria.

This study presents the development of an intelligent cybersecurity risk management system that leverages behavioural analytics and machine learning to detect threats and anomalous user activities in real time. The system was developed in the Extreme Programming (XP) methodology in certain important stages such as gathering of data, designing of the model, implementing it, and testing of the same. A deep learning model which was a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model was involved to capture the spatial-temporal features of user behaviour logs and a Random Forest that acted as the final decision layer in anomaly classification. The process trained and assessed a complete set of information for nearly 411,000 records, consisting of the CERT Insider Threat Dataset v6.2, phishing email archives and simulated network/ system activity. The obtained results were shown to have good detection performance where the CNN-LSTM model had the highest mean accuracy 95.9%, precision 95.1%; recall 94.0%; and F1-score 94.5%. The Random Forest also increased the accuracy of classification. The real-time abilities and adaptive architecture of the system make it a feasible reality toward proactive and smart management of risks-related cybersecurity solutions in agile business environments.

Android's background execution framework has undergone significant transformation through successive API levels, implementing increasingly restrictive constraints to optimize battery consumption and enhance privacy protection. These changes have profoundly impacted application development, necessitating fundamental architectural adaptations to maintain functionality within the evolving system landscape. The platform's evolution from a permissive background execution model to a highly constrained environment has yielded substantial battery life improvements while creating complex challenges for developers. Through the system of Android's power-saving mechanisms, including Doze Mode, App Standby Buckets, and Adaptive Battery, distinct performance characteristics emerge among the principal scheduling APIs—WorkManager, JobScheduler, AlarmManager, and ForegroundService. Implementation patterns, including constraint chaining, expedited jobs, lifecycle-aware coroutines, adaptive scheduling, and proper state persistence, demonstrate significant improvements in both execution reliability and energy efficiency. Performance profiling reveals critical energy-drain antipatterns, including polling loops, unbound location updates, excessive wake locks, and inefficient network operations. The transition toward constraint-aware background processing frameworks aligns with Android's platform goals while enabling applications to maintain essential functionality across diverse usage patterns and device states, establishing a foundation for efficient background processing that respects both system constraints and user experience requirements.

This article presents an innovative framework for democratizing wealth management through artificial intelligence, introducing an AI-Infused Wealth as a Service (WaaS) platform designed to extend sophisticated financial services to underserved populations. The article proposes a comprehensive architecture that combines personalized financial guidance with systemic risk mitigation capabilities, addressing the current limitations of traditional wealth management services. By leveraging advanced machine learning algorithms, natural language processing, and real-time data analytics, the platform demonstrates significant improvements in service accessibility, cost reduction, and risk management effectiveness. The framework incorporates automated compliance monitoring systems and policy alignment measures, ensuring regulatory adherence while promoting financial inclusion. This article provides evidence that AI-driven wealth management solutions can substantially impact market democratization while maintaining robust security and compliance standards.

Smart cities integrate interconnected technologies to enhance urban living through efficient infrastructure and services, yet this technological evolution introduces significant cybersecurity vulnerabilities that threaten critical urban systems. AI-driven security architectures emerge as sophisticated solutions, utilizing machine learning algorithms and predictive analytics to provide real-time threat detection, automated incident response, and proactive defense mechanisms against cyber-attacks. These intelligent systems process vast amounts of data from sensors, cameras, traffic networks, and utility systems to maintain the integrity and availability of essential urban services. While AI-driven security delivers substantial benefits, including enhanced public safety, service continuity, and economic protection, it raises profound privacy concerns and ethical challenges related to surveillance, algorithmic bias, and data misuse. Implementing privacy-preserving technologies such as federated learning and differential privacy, with transparent governance frameworks and public engagement initiatives, offers pathways to balance security effectiveness with individual rights protection. Future developments in explainable AI, quantum-resistant algorithms, and interdisciplinary collaboration will be crucial for creating equitable and trustworthy AI-driven security systems that serve urban communities while preserving democratic values and social equity.

Digital marketplaces have transformed e-commerce by creating complex ecosystems connecting customers and suppliers globally. These platforms face unprecedented support challenges due to multi-stakeholder operations, diverse service agreements, and growing transaction volumes. Artificial intelligence technologies offer transformative solutions through intelligent automation systems that enhance support delivery while maintaining human-centric service quality. This article examines three critical AI technologies: intelligent summarization systems that distill complex information into actionable insights, conversational search assistants that democratize support access through natural language interfaces, and predictive support routing that optimizes resource allocation via machine learning. These technologies synergistically address marketplace support complexities, enabling efficient service for diverse stakeholder groups while maintaining high standards. Implementation demonstrates significant improvements in operational efficiency, stakeholder satisfaction, and platform sustainability. The article illustrates how AI augmentation reshapes support delivery paradigms, creating scalable solutions balancing automation efficiency with empathy and personalization. These technologies enable proactive support strategies, enhanced knowledge management, and improved accessibility for all marketplace participants.

Human-in-the-loop (HITL) architectures represent a critical framework for ensuring the safe and effective deployment of Generative AI in clinical settings. This article examines the design, implementation, and evaluation of HITL systems that strategically integrate clinician oversight into GenAI-driven healthcare applications. Despite the rapid adoption of AI technologies in healthcare environments, many implementations lack structured validation mechanisms, creating potential patient safety concerns. The article explores the inherent limitations of GenAI models in clinical contexts and presents evidence supporting the necessity of human oversight. It details the core components of effective HITL architectures, including explainability mechanisms, confidence scoring, contextual awareness, and feedback integration. Implementation strategies are examined across various clinical domains, including radiology, oncology, and intensive care, with domain-specific considerations highlighted. The article concludes with a framework for measuring effectiveness and ensuring continuous improvement of these systems through multidimensional metrics that capture both technical performance and real-world impact.

This article examines the emerging role of artificial intelligence in transforming portfolio management through automated morning briefing systems. As financial markets grow increasingly complex, portfolio managers face mounting challenges in efficiently processing vast amounts of data to make timely, informed decisions. AI-driven morning briefing systems aggregate overnight market developments and deliver actionable insights by leveraging machine learning, natural language processing, and predictive analytics. The article explores the architecture of these systems, including data acquisition, processing, analytics, personalization, and presentation layers. The article details advanced analytical capabilities such as predictive market analytics, risk prioritization, scenario simulation, and dynamic allocation recommendations. Implementation strategies, organizational integration approaches, and regulatory considerations are examined through case studies from hedge funds, institutional asset managers, and wealth management firms. The article concludes with perspectives on future technological developments and the evolving role of portfolio managers in an AI-augmented landscape.