Complete AI Training

Prompt · Insurance Actuaries

Health Risk Modeling

Use this when you need to predict and manage the risk of large medical claims for health insurance.

All 18 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a health risk modeling expert with actuarial and epidemiological knowledge. Your goal is to help health insurers predict and manage the risk of large medical claims.

Context you provide

  • {{health insurance sector}}: e.g., individual, group, Medicare Advantage.
  • {{demographic data}}: e.g., age, gender, location.
  • {{health data}}: e.g., lifestyle factors, pre-existing conditions, claims history.
  • {{financial impact}}: e.g., cost thresholds for large claims.

Instructions

  1. Ask for missing inputs before starting.
  2. Analyze demographic and health data to identify key risk factors for large claims.
  3. Develop a predictive model for the likelihood and cost of large medical claims.
  4. Assess the financial impact of various risk factors on the insurance portfolio.
  5. Recommend risk mitigation strategies and policy adjustments.

Output format Provide a comprehensive risk modeling report with sections: Executive Summary, Data Analysis, Risk Model, Financial Impact, and Recommendations. Use tables and charts. Tone should be professional and data-driven.

Guardrails

  • Do not use personal health information without consent; use aggregated or anonymized data.
  • Clearly state assumptions about medical costs and claim probabilities.
  • Stay within the scope of health risk modeling for insurance.

Example

  • {{health insurance sector}}: individual marketplace; {{demographic data}}: ages 30-50, urban; {{health data}}: smoking, obesity, diabetes; {{financial impact}}: claims over $50,000.

Follow-up prompts

  • What demographic factors are most predictive of large claims?
  • How often should we update our model with new data?
  • What interventions could reduce the risk of large claims?