The Role of Data Analytics in Detecting Unemployment Insurance Fraud:: A Case Study of State Governments in the United States

The unprecedented surge in unemployment insurance claims during the COVID-19 pandemic exposed state labor agency systems in the United States to significant fraud risks, resulting in billions of dollars in improper payments. This study investigated the role of data analytics in detecting and mitigating unemployment insurance fraud, with a focus on state government responses. Using a single-case study approach, I examined how advanced data analytics, including machine learning, predictive modeling, and strategies to identify fraudulent claims, can reduce fraud within unemployment insurance systems. The study also included an investigation of systemic vulnerabilities and the impact of policy improvements on fraud detection. State leaders who leveraged comprehensive data analytics are more effective at identifying suspicious activities, such as claims with anomalous demographic data, repeated use of contact information, or patterns indicative of identity theft. The analysis demonstrates that reviewing all claims, rather than relying on traditional sampling, enhances the detection of subtle fraud indicators and supports more robust recovery efforts. Real-world examples demonstrate how analytics have identified clusters of suspicious claims, enabling targeted investigations that have led to significant recoveries and enhanced fraud prevention protocols. Persistent challenges remain, including inconsistent data sharing among states, limited federal access to state-level claims data, and resource constraints that hinder rapid implementation of analytics-driven oversight. The dissertation concludes that integrating data analytics into unemployment insurance program management is crucial for timely fraud detection, enhanced program integrity, and an effective response to future crises.
ASIN: B0GFJQWHJK
VSKU: BVV.B0GFJQWHJK.G
Condition: Good
Author/Artist:Carkhuff Ph.D., Tina Louise
Binding: Paperback
Note: Any images shown are stock photographs and product may differ from what is shown.
Condition Notes: The item shows wear from consistent use, but it remains in good condition and works perfectly. All pages and cover are intact including the dust cover, if applicable . Spine may show signs of wear. Pages may include limited notes and highlighting. May NOT include discs, access code or other supplemental materials.