Prompt lesson · 21 prompts
Predictive Maintenance for Policies prompts for Insurance Data Analysts
21 ready-to-use prompts from our AI for Insurance Data Analysts course. Copy one, fill in the {{placeholders}}, and paste it into ChatGPT, Claude, Gemini or any other AI.
Clean and Organize Policy Data
Use this when you need to extract, standardize, and clean policyholder data for reliable analysis.
Role You are a meticulous data steward who ensures policyholder data is accurate, consistent, and ready for analysis.
Context you provide
- {{raw_data}}: The unstructured or messy dataset (e.g., text files, spreadsheets with errors).
- {{fields}}: Specific fields to extract or standardize (e.g., "names, addresses, contact details").
- {{policy_types}}: (Optional) Types of policies to classify (e.g., "life, health, auto").
Instructions
- If any context is missing, ask for it before starting.
- Extract and categorize the requested fields from the raw data, ensuring accuracy.
- Standardize formats (e.g., dates, addresses, policy numbers) for consistency.
- Identify and remove duplicate records, and flag any incomplete or inconsistent entries.
- Organize the cleaned data into a structured format (e.g., table) suitable for analysis.
Output format Provide a summary of the cleaning process, a sample of the cleaned data (if applicable), and a list of any issues found (e.g., duplicates removed, missing fields). Use tables for clarity.
Guardrails
- Do not alter data beyond the requested cleaning; preserve original values where possible.
- Do not invent data to fill gaps; flag missing information.
- Keep the output focused on data cleaning, not analysis.
Example Raw data: "A CSV file with 5,000 rows, including free-text address fields and inconsistent policy type labels." Fields: "Address, policy type, premium amount."
Open this prompt Analysis · Intermediate
Engineer Features for Predictive Maintenance
Use this when you need to identify and create relevant variables to improve predictive maintenance models.
Role You are a data scientist with expertise in feature engineering for predictive maintenance. Your goal is to help identify and create variables that enhance model accuracy.
Context you provide
- {{equipment_metrics}} — specific metrics like operating hours, temperature, vibration, or pressure.
- {{failure_data}} — historical failure data such as time to failure and failure frequency.
- {{maintenance_history}} — repair frequency, maintenance costs, and other relevant history.
Instructions
- Ask for any missing context before starting.
- Identify potential features from the provided equipment metrics and maintenance history.
- Create new variables that capture usage patterns, degradation trends, and failure indicators.
- Prioritize features based on their likely impact on predictive maintenance outcomes.
- Suggest methods to evaluate the effectiveness of engineered features.
Output format Provide a list of recommended features with descriptions, rationale, and suggested evaluation methods. Use tables or bullet points for clarity.
Guardrails
- Do not invent data; base features on provided information.
- Flag any assumptions about data availability or feature relevance.
- Stay focused on feature engineering for predictive maintenance.
Example
- {{equipment_metrics}}: "Operating hours, cycles, load levels, temperature, vibration, pressure"
- {{failure_data}}: "Time to failure and failure frequency from historical records"
- {{maintenance_history}}: "Repair frequency and maintenance costs over the past year"
Open this prompt Analysis · Intermediate
Select and Train ML Models
Use this when you need to choose and train machine learning models on policy data for specific predictions.
Open this prompt Analysis · Intermediate
Evaluate Predictive Model Performance
Use this when you need to assess the accuracy and reliability of a predictive maintenance model.
Open this prompt Analysis · Intermediate
Deploy and Monitor Predictive Models
Use this when you need to deploy predictive maintenance models and monitor their performance to reduce downtime and costs.
Open this prompt Analysis · Advanced
Policy Trend Analysis
Use this when you need to identify patterns and trends in policy data to inform predictive maintenance strategies.
Open this prompt Analysis · Intermediate
Policy Risk Assessment
Use this when you need to analyze historical policy data to identify risk factors and assess their impact on claims.
Open this prompt Analysis · Intermediate
Segment Customers by Needs and Behavior
Use this when you need to group policyholders based on their maintenance needs and behaviors to tailor services and communication.
Open this prompt Analysis · Intermediate
Generate Predictive Analytics Reports
Use this when you need to create insightful reports on predictive maintenance for various stakeholders.
Open this prompt Creating · Beginner
Predict Policy Renewal Likelihood
Use this when you need to forecast which policies will renew and identify those at risk of lapsing.
Open this prompt Analysis · Intermediate
Forecast Claim Frequency by Policy Type
Use this when you need to analyze historical claims data to predict future claim frequency for different policy types, considering key factors.
Open this prompt Analysis · Advanced
Predict Customer Churn and Drivers
Use this when you need to identify factors leading to customer churn and forecast which policyholders are at risk.
Open this prompt Analysis · Advanced
Develop Fraud Detection Models
Use this when you need to build models that identify potentially fraudulent claims and policy applications.
Open this prompt Analysis · Advanced
Underwriting Risk Prediction
Use this when you need to assess the risk of underwriting new policies based on various data points.
Open this prompt Analysis · Advanced
Predict Loss Ratios for Portfolios
Use this when you need to forecast loss ratios for policy portfolios to inform pricing and underwriting decisions.
Open this prompt Analysis · Advanced
Predict Customer Lifetime Value
Use this when you need to estimate the long-term value of policyholders to guide marketing and retention strategies.
Open this prompt Analysis · Advanced
Identify Cross-Sell and Upsell Opportunities
Use this when you need to analyze customer data to find opportunities for selling additional policies or coverage.
Open this prompt Analysis · Intermediate
Forecast Claims Severity for Reserves
Use this when you need to predict the severity of future claims to inform reserve setting and risk management decisions.
Open this prompt Analysis · Advanced
Segment Insurance Market for Targeting
Use this when you need to analyze customer data to identify market segments for tailored policies and pricing.
Open this prompt Analysis · Intermediate
Predictive Risk Mitigation
Use this when you need to build predictive models that identify potential risks and suggest proactive mitigation strategies.
Open this prompt Analysis · Advanced