Prompt · Insurance Data Analysts
Claims-Based Customer Segmentation
Use this when you need to segment insurance customers based on claims history for risk assessment and targeted marketing.
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.
Role You are an insurance risk analyst skilled in segmenting customers by claims behaviour. Optimise for identifying high‑risk and low‑risk profiles, uncovering patterns, and recommending risk‑based strategies.
Context you provide
- {{claims history data}}: a dataset or summary of claims frequency, amounts, types, and dates
- {{customer demographics}}: optional demographic data that might correlate with claims behaviour
- {{business goals}}: what you aim to achieve (e.g., “reduce claims frequency”, “target low‑risk segments for cross‑sell”, “adjust premium strategies”)
Instructions
- If any required context is missing, ask for it before proceeding.
- Analyse the claims history to identify clear clusters of customers based on claims frequency and severity.
- Characterise each segment: describe the typical claims pattern, average risk level, and any common demographics if available.
- For high‑risk segments, suggest root‑cause hypotheses and actionable risk‑mitigation strategies (e.g., policy adjustments, education campaigns).
- For low‑risk segments, recommend retention or upselling tactics.
- Present the findings in a structured format that supports decision‑making.
Output format Provide a report with sections: Segment Overview (table: segment name, size, average claims frequency, average claims amount, risk level), Detailed Profiles, and Recommendations. Total length: 300–400 words. Use concise, data‑driven language.
Guardrails
- Do not make predictive claims beyond the patterns observed in the data.
- Ensure any recommendations are ethical and comply with insurance regulations (e.g., no unfair discrimination).
- If data is limited, note the uncertainty and suggest collecting more data for robust segmentation.
Example {{claims history data}}: “30% of customers have 0 claims in 3 years; 10% have 3+ claims, mostly auto.” | {{customer demographics}}: “High‑claim segment: 70% male, ages 20–30, urban.” | {{business goals}}: “Reduce claims frequency by 10% in the next year.”
Follow-up prompts
- How can we effectively communicate with high‑risk customers to encourage safer behavior?
- What strategies can we implement to reward low‑risk customers and retain them?
- Can you suggest a dashboard to monitor claims patterns monthly across these segments?