stdClass Object
(
    [id] => 17892
    [paper_index] => 202510-07-024494
    [title] => ENHANCING RISK MANAGEMENT AND FRAUD DETECTION IN THE U.S. FINANCIAL INDUSTRY THROUGH MACHINE LEARNING ALGORITHMS: APPLICATIONS, CHALLENGES, AND FUTURE DIRECTIONS.
    [description] => 
    [author] => Lawrence Kofi Abakah, Samuel Gyasi Adom, Ephraim Narteh-Kofi
    [googlescholar] => 
    [doi] => https://doi.org/10.36713/epra24494
    [year] => 2025
    [month] => October
    [volume] => 12
    [issue] => 10
    [file] => fm/jpanel/upload/2025/October/202510-07-024494.pdf
    [abstract] => The increasing complexity of fraud schemes and the evolving nature of financial risks present significant challenges to the U.S. financial industry, which exposes the limitations of traditional rule-based risk management systems. This study explores how machine learning (ML) algorithms enhance risk management and fraud detection capabilities within financial institutions, thereby addressing operational inefficiencies and regulatory demands. The paper uses a comprehensive literature review and empirical synthesis. The study examines various ML methodologies, including supervised learning, deep learning, reinforcement learning and generative adversarial networks (GANs) and their applications in fraud prevention, credit risk assessment, algorithmic trading and market volatility forecasting. The findings of the study indicated that ML algorithms significantly improve fraud detection accuracy, reduce false positives and support real-time monitoring. Additionally, the findings showed that ML applications in credit scoring using alternative data have expanded financial inclusion without compromising portfolio quality. However, the study highlights persistent challenges, such as algorithmic bias, lack of model transparency, regulatory compliance complexities and cybersecurity vulnerabilities. The research, therefore, concludes that although ML offers transformative potential for enhancing institutional resilience and customer protection, its sustainable implementation requires explainable AI models, ethical governance frameworks and continuous collaboration among stakeholders. Future opportunities lie in the convergence of ML with emerging technologies such as quantum computing, federated learning, edge AI and blockchain. These developments demand significant investments in infrastructure and regulatory innovation to safeguard systemic financial stability in an increasingly digitized financial ecosystem.
    [keywords] => Machine Learning, Fraud Detection, Financial Industry, Explainable AI, Predictive Analytics, Regulatory Compliance.
    [doj] => 2025-10-25
    [hit] => 
    [status] => 
    [award_status] => P
    [orderr] => 22
    [journal_id] => 7
    [googlesearch_link] => 
    [edit_on] => 
    [is_status] => 1
    [journalname] => EPRA International Journal of Economics, Business and Management Studies (EBMS)
    [short_code] => IJHS
    [eissn] => 2347-4378
    [pissn] => 
    [home_page_wrapper] => images/products_image/2.EBMS.png
)
Error fetching PDF file.