AI Medicaid Eligibility Fraud Investigation Playbook

A state Medicaid OIG has received a tip that 340 individuals enrolled in Medicaid may have unreported income or assets exceeding eligibility thresholds. The OIG has 90 days before a federal audit. Average Medicaid expenditure per recipient is $8,400 annually.

When to use this playbook

• Use this playbook when the decision looks like the situation above: A state Medicaid OIG has received a tip that 340 individuals enrolled in Medicaid may have unreported income or assets exceeding eligibility thresholds.
• It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Medicaid Eligibility Fraud Investigation".
• Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

• Enrollment records for 340 recipients
• State wage database cross-match results
• Property records database cross-match
• Vehicle registration cross-match
• Federal data hub cross-match (SSA, IRS, DHS)

Attachments: Documents (Documents)

You are a Medicaid OIG investigator assessing eligibility fraud for 340 flagged recipients. I am attaching:

Work only from the attached source files. If a conclusion is not supported, say so.

Produce:
1. Identify recipients where the state wage database shows earned income not reported on the Medicaid application, and calculate the income overage vs. applicable FPL threshold.
2. Flag recipients with property ownership or vehicle registrations inconsistent with declared asset levels.
3. Identify deceased recipients still receiving benefits via SSA death records cross-reference.
4. Calculate the total overpayment exposure for the flagged population and the federal share.
5. Tell me the overpayment recovery process, due process requirements before termination, and what qualifies for criminal vs. administrative referral.

Call out where independent models are likely to disagree, and list follow-up documents a reviewer should request.

What to expect

• Income discrepancy list with FPL overage
• Property and vehicle asset flag list
• Deceased recipient active enrollment list
• Total overpayment estimate with federal share
• Recovery process, due process, and referral thresholds

Review before you act

• Validate this output against source files before relying on it: Identify recipients where the state wage database shows earned income not reported on the Medicaid application, and calculate the income overage vs. applicable FPL threshold.
• Validate this output against source files before relying on it: Flag recipients with property ownership or vehicle registrations inconsistent with declared asset levels.
• Validate this output against source files before relying on it: Identify deceased recipients still receiving benefits via SSA death records cross-reference.
• Validate this output against source files before relying on it: Calculate the total overpayment exposure for the flagged population and the federal share.
• Confirm every cited figure, date, counterparty, or requirement against the attached originals — models compress and can drop a qualifier.
• Treat disagreement between models as a review item, especially on classification, materiality, and recommended next action.
• Do not authorize an operational, clinical, legal, credit, or enforcement action solely because the models agree.