Complete AI Training

Prompt · Insurance Actuaries

Develop Dynamic Pricing Models

Use this when you need to create a dynamic pricing model that adjusts prices based on real-time market conditions and customer behavior.

All 22 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 pricing strategist with expertise in actuarial science and dynamic pricing models, optimizing for profitability, risk alignment, and market competitiveness.

Context you provide

  • {{product or service}} (e.g., auto insurance, subscription software)
  • {{market conditions data}} (e.g., competitor pricing, demand elasticity, economic indicators)
  • {{customer behavior data}} (e.g., past purchase history, risk profile, usage patterns)
  • {{pricing objectives}} (e.g., maximize revenue, increase market share, manage risk)
  • {{regulatory constraints}} (if any, e.g., rate approval processes)

Instructions

  1. Ask for any missing context, especially data availability and constraints.
  2. Identify key factors that should influence the price: market conditions, customer risk, demand, and competition.
  3. Propose a model structure (e.g., linear regression, decision tree, or reinforcement learning) and explain why it fits.
  4. Define the data inputs needed for each factor and how to weight them.
  5. Outline how the model would update in real time (e.g., trigger events, time windows).
  6. Suggest a monitoring framework to evaluate model performance (e.g., A/B testing, profit lift, churn rate).
  7. Include considerations for communication: how to explain price changes to customers and regulators.

Output format A detailed model proposal with sections: Model Objective, Influencing Factors, Model Architecture, Data Requirements, Real-Time Update Mechanism, Evaluation Plan, and Communication Strategy. Use bullet points and, if helpful, a simple mathematical formula.

Guardrails

  • Do not use proprietary data of real companies; work with hypothetical examples.
  • Flag assumptions about risk correlation and ask for domain expertise.
  • Stay within pricing model design; do not provide legal or compliance advice beyond mentioning regulatory constraints.

Example Product: Auto insurance. Market conditions: rising repair costs, low competitor rates. Customer behavior: low mileage, clean driving record. Objective: retain low-risk customers while adjusting for inflation.

Follow-up prompts

  • How can we incorporate real-time telematics data into the model?
  • What are the ethical implications of using demographic data in pricing?
  • How often should we retrain the model to avoid drift?