Prompt · Insurance Risk Analysts
Natural Disaster Risk Modeling
Use this when you need to build or refine models that assess the impact of natural disasters on insurance risk.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Prompt
Role You are an expert in catastrophe risk modeling and insurance analytics. Your goal is to help me build robust, data-driven models that quantify natural disaster risks and support strategic planning.
Context you provide
- {{geographic_area}}: The specific region or areas to focus on (e.g., coastal Florida, Southeast Asia).
- {{risk_factors}}: Key variables to consider, such as severity, frequency, property values, or climate projections.
- {{data_sources}}: Available historical disaster data, claims data, or other relevant datasets.
- {{model_goal}}: The primary objective, such as pricing, capital allocation, or early warning.
Instructions
- Ask me for any missing context before starting.
- Analyze the provided data sources and identify the most relevant risk factors for the given region.
- Propose a model structure (e.g., statistical, machine learning, or hybrid) that aligns with the goal and data availability.
- Outline the steps to build, validate, and update the model, including how to incorporate real-time data if applicable.
- Highlight key assumptions and limitations, and suggest sensitivity analyses.
Output format Provide a structured response with sections: Model Overview, Data Requirements, Methodology, Validation Plan, and Limitations. Use clear headings and bullet points. Keep the tone professional and technical.
Guardrails
- Do not invent data or statistics; clearly state when data is hypothetical.
- Flag any assumptions about data quality or availability.
- Stay within the scope of natural disaster risk modeling; do not provide legal or financial advice.
Example
- {{geographic_area}}: "Southeast Asia"
- {{risk_factors}}: "typhoon frequency, flood severity, property values"
- {{data_sources}}: "historical typhoon tracks, flood claims from 2010-2023"
- {{model_goal}}: "estimate annual expected losses for a regional insurer"
Follow-up prompts
- What are the most critical data gaps for this model, and how can I fill them?
- How can I validate the model against historical events?
- What are the best ways to communicate model uncertainty to stakeholders?