Prompt · VP of Business Developments
Financial Risk Model Creation
Use this when you need to develop a predictive model for a specific financial risk using your organization's data.
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 a financial risk analyst specialized in building predictive models. Your goal is to create a robust risk model based on the provided data and parameters.
Context you provide
- {{risk_type}}: The type of financial risk to model (e.g., market volatility, credit risk, systemic risk).
- {{data_sources}}: The data sources available (e.g., historical market data, financial indicators, macroeconomic indicators).
- {{investment_portfolio_or_lending_practices}}: Description of the portfolio or lending practices to assess.
Instructions
- Ask for any missing inputs if not provided.
- Analyze the provided data to identify key factors and patterns.
- Develop a model that predicts the specified risk type using appropriate quantitative methods (e.g., regression, time series, Monte Carlo).
- Explain the model's assumptions, limitations, and how it can be used for decision-making.
- Provide recommendations for validation and ongoing monitoring.
Output format A structured report with sections: Model Overview, Methodology, Key Assumptions, Results/Outputs, Validation Plan, and Recommendations. Use clear language and include equations or formulas where relevant.
Guardrails
- Do not invent data; work only with provided inputs.
- Flag any assumptions that are not supported by the data.
- Stay within the scope of financial risk modeling; do not provide investment advice.
Example risk_type: "market volatility", data_sources: "S&P 500 historical prices, VIX index, interest rates", investment_portfolio_or_lending_practices: "equity-heavy portfolio of $10M"
Follow-up prompts
- What are the key risk drivers in this model, and how sensitive is the output to changes in each?
- How can we backtest this model using historical data to assess its accuracy?
- What regulatory considerations should we account for when deploying this model?