Enhancing fraud detection and prevention in fintech: Big data and machine learning approaches

Omogbeme Angela 1, *, Iyabode Atoyebi 2, Adesola Soyele 3 and Emmanuel Ogunwobi 4

1 Department of Business Analytics, University of West Georgia, USA.
2 Cyber Security and Human Factors, Department of Computing and Informatics, Bournemouth University, UK.
3 Department of Applied Statistics and Decision Analytics, Western Illinois University, USA.
4 Tagliatela College of Engineering, University of New Haven West Haven, USA.
 
Research Article
World Journal of Advanced Research and Reviews, 2024, 24(02), 2301–2319
Article DOI: 10.30574/wjarr.2024.24.2.3617
 
Publication history: 
Received on 17 October 2024; revised on 24 November 2024; accepted on 26 November 2024
 
Abstract: 
The rapid evolution of digital financial services in the FinTech sector has significantly increased the volume and complexity of fraudulent activities, posing severe challenges to cybersecurity and trust in financial systems. This paper explores the application of Big Data and Machine Learning [ML] approaches in enhancing fraud detection and prevention, addressing the critical need for robust, real-time solutions in combating identity theft, account takeovers, and payment fraud. Leveraging Big Data analytics, financial institutions can process vast datasets generated by user transactions, device interactions, and behavioural patterns, enabling the identification of anomalies indicative of fraudulent activities. ML techniques, including neural networks, decision trees, and clustering algorithms, provide dynamic tools for fraud prevention, offering real-time anomaly detection and predictive insights. Behavioural biometrics, such as analysing typing speed and navigation patterns, complement traditional security measures, while advanced ML models optimize multi-factor authentication protocols, reducing vulnerabilities. Additionally, the integration of Big Data with blockchain technology strengthens transparency and security within decentralized financial systems, offering innovative methods for fraud mitigation. The paper includes case studies showcasing the successful application of ML models in detecting and preventing fraud, emphasizing their adaptability and accuracy. By aligning technological innovations with regulatory frameworks and consumer demands, this research highlights the potential of Big Data and ML to revolutionize fraud prevention in FinTech, ensuring safer and more resilient digital financial ecosystems.
 
Keywords: 
Big Data; ML; Fraud Detection; Behavioural Biometrics; Blockchain Security; FinTech Cybersecurity
 
Full text article in PDF: 
Share this