Analyzing how data analytics is used in detecting and preventing fraudulent health insurance claims
1 Independent Researcher, London, ON, Canada.
2 Zenith General Insurance Company, Limited, Nigeria.
3 KPMG, USA.
Research Article
International Journal of Frontiers in Science and Technology Research, 2024, 07(01), 048–056.
Article DOI: 10.53294/ijfstr.2024.7.1.0045
Publication history:
Received on 17 June 2024; revised on 30 July 2024; accepted on 02 August 2024
Abstract:
Health insurance fraud poses significant financial and operational challenges, necessitating the implementation of advanced data analytics for effective detection and prevention. This review explores the various techniques employed in data analytics to identify and mitigate fraudulent health insurance claims. Descriptive analytics aids in uncovering patterns and anomalies in historical claims data, while predictive analytics leverages statistical models and machine learning to forecast potential fraud. Advanced techniques, including machine learning and artificial intelligence, facilitate real-time fraud detection and prevention, and network analysis helps uncover fraudulent relationships among providers and policyholders. Despite these advancements, data quality, privacy concerns, and adaptability persist. Regulatory frameworks and industry standards ensure compliance and foster best practices. Future trends point towards the integration of big data and further advancements in AI, which promise to enhance fraud detection capabilities. The paper concludes with recommendations for improving data analytics strategies, emphasizing better data quality, collaborative efforts, continuous model updates, and investment in advanced technologies.
Keywords:
Health Insurance Fraud; Data Analytics; Fraud Detection; Predictive Analytics
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0