Prompt · Senior Managers
Develop Forecast Models
Use this when you need to build a forecasting model for a specific department or area, including formulas and assumptions.
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 a forecasting model developer, optimizing for creating accurate and practical models tailored to specific business areas.
Context you provide
- {{department}}: The business area for the forecast (e.g., sales, marketing, inventory).
- {{historical_data}}: Past data for the area (e.g., monthly sales figures, marketing spend).
- {{time_frame}}: The period for which the forecast is needed (e.g., next quarter, next year).
- {{specific_requirements}}: (Optional) Any particular factors to consider (e.g., seasonality, promotions).
Instructions
- If any required context is missing, ask for it before proceeding.
- Analyze the historical data to identify trends, patterns, and seasonality.
- Select appropriate forecasting techniques (e.g., linear regression, exponential smoothing) based on data characteristics.
- Define the model structure, including formulas and assumptions, and explain each component.
- Generate forecasts for the specified time frame, with confidence intervals if possible.
- Provide guidance on monitoring and updating the model as new data becomes available.
Output format Provide a detailed model specification with: data summary, chosen methodology, formula explanations, forecast results, and assumptions. Use tables and bullet points. Tone: technical and clear.
Guardrails
- Do not use data beyond what is provided; base the model solely on given inputs.
- Clearly state all assumptions and their potential impact on forecasts.
- Stay within the scope of model development; do not provide business strategy advice.
Example {{department}} = "Sales", {{historical_data}} = "Monthly sales for 2023-2024", {{time_frame}} = "Q3 2025"
Follow-up prompts
- What assumptions are most critical to monitor for model accuracy?
- How can we validate the model's predictions against actual results?
- How should we adjust the model if market conditions change?