ATM Fraud Detection using Streaming Data Analytics

Yelleti, Vivek,; Ravi, Vadlamani; Mane, Abhay Anand; Naidu, Laveti Ramesh

doi:10.48550/arxiv.2303.04946

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The successful implementation of these models showcases the potential of machine learning and big data analytics in enhancing fraud detection processes in the insurance industry. Furthermore, Vivek et al (2023) provides insights into the use of streaming data analytics for real-time fraud detection in ATM transactions. This case study employed a sliding window method to collect ATM transaction data and trained several machine learning models, including Naive Bayes, Random Forest, Decision Tree, and K-Nearest Neighbor, to detect fraudulent activities.…”

Section: Implementation Of Data Analytics In Fraud Detectionmentioning

confidence: 99%

“…Real-time fraud detection emerges as another critical implication. The significance of this is underscored by Vivek et al (2023). Organizations should prioritize the implementation of real-time analytics techniques to detect and prevent fraudulent activities as they occur.…”

Section: Implications For Fraud Detection Strategiesmentioning

confidence: 99%

“…Real-time fraud detection is poised to become the industry norm, aligning with the findings of Vivek et al (2023). As fraudsters become more sophisticated, organizations will increasingly rely on systems that can detect and prevent fraudulent activities as they occur.…”

Section: Impact On Accounting Practices and Policy Makingmentioning

confidence: 99%

See 2 more Smart Citations

Utilizing data analytics for fraud detection in accounting: A review and case studies

Benjamin Samson Ayinla,

Onyeka Franca Asuzu,

Ndubuisi Leonard Ndubuisi

et al. 2024

Int. J. Sci. Res. Arch.

View full text Add to dashboard Cite

This research paper offers a comprehensive exploration of the evolving landscape of fraud detection strategies within the accounting sector, driven by the integration of data analytics, machine learning, and big data technologies. The study aims to investigate, analyze, and provide insights into the practical application, challenges, and implications of these advanced technologies in fraud detection. Through an extensive literature review, a range of case studies, and a comparative analysis of methodologies, this paper delves into the key aspects of data-driven fraud detection. The literature review establishes the significance of data analytics in the context of fraud detection, highlighting its pivotal role in identifying and preventing fraudulent activities. Various case studies from diverse sectors, including finance, healthcare, and e-commerce, exemplify successful implementations of data analytics and the challenges faced in real-world scenarios. A comparative analysis of fraud detection approaches showcases the strengths and limitations of different methodologies, guiding organizations in optimizing their fraud detection strategies. The findings underscore the transformative impact of data analytics, machine learning, and big data in revolutionizing fraud detection. Implications drawn from this research suggest a future where these technologies will continue to be instrumental in proactively combating evolving fraudulent activities, ensuring regulatory compliance, and upholding ethical standards.

show abstract

Section: Implementation Of Data Analytics In Fraud Detectionmentioning

confidence: 99%

Section: Implications For Fraud Detection Strategiesmentioning

confidence: 99%