The rapid digital transformation of the financial sector has escalated cybersecurity challenges, necessitating advanced solutions to protect sensitive data and mitigate cyber threats. This study systematically reviews the application of advanced predictive analytics, powered by artificial intelligence (AI) and machine learning (ML), in enhancing financial information security. Predictive analytics enables financial institutions to proactively detect fraud, assess risks, monitor behavioral anomalies, and anticipate emerging cyber threats by analyzing vast historical and real-time data through a PRISMA-based systematic review. Key applications include real-time fraud detection, dynamic risk management, cyber threat intelligence, and ensuring data integrity from 555 previous studies across various databases such as Scopus, Web of Science, DOAJ, Google Scholar, ResearchGate, and PubMed. Additionally, 63 studies and 12 reports were finalized to address research gaps. Despite significant advancements, challenges remain regarding integration with legacy systems, data privacy compliance under regulations such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA), model robustness against adversarial attacks, and workforce skill shortages. Emerging trends such as blockchain integration, quantum-safe cryptography, privacy-preserving techniques like federated learning, and AI-driven security automation show promise for future developments. The study emphasizes the critical need for transparent, explainable predictive models and interdisciplinary collaboration to bridge existing gaps. Ultimately, leveraging advanced predictive analytics is vital for strengthening financial cybersecurity frameworks, ensuring regulatory compliance, and maintaining market stability in an increasingly complex and data-driven financial ecosystem. Continued innovation and research are essential to fully realize these benefits and address evolving threats.
Hasan et al. (Mon,) studied this question.