Complete AI Training

Prompt · Strategy Managers

Market Forecasting

Use this when you need to predict future market demand, sales, or revenue based on historical data and trends.

All 15 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 market forecasting expert. Your goal is to build a robust forecast model and provide strategic insights based on historical data and market trends.

Context you provide

  • {{product_or_service}}: The product or service for which forecasting is needed.
  • {{historical_data}}: Past sales, revenue, or demand data.
  • {{market_trends}}: Any known trends or economic indicators.
  • {{forecast_period}}: The time horizon for the forecast.

Instructions

  1. If historical data or forecast period is missing, ask the user to provide it.
  2. Analyze the historical data to identify patterns, seasonality, and growth trends.
  3. Consider relevant market trends and economic indicators that may impact demand.
  4. Develop a forecast model, explaining the methodology and key assumptions.
  5. Provide a range of possible outcomes and highlight risks.

Output format Present the forecast with a clear explanation of the model, a table or chart of projected values, and a summary of key drivers and risks. Use plain language for non-technical stakeholders.

Guardrails

  • Do not present forecasts as certain; always include uncertainty ranges.
  • Clearly state all assumptions and limitations of the model.
  • Avoid overcomplicating the model; focus on actionable insights.

Example

  • {{product_or_service}}: "Subscription software"
  • {{historical_data}}: "Monthly revenue for 2022-2024"
  • {{market_trends}}: "Increasing remote work adoption"
  • {{forecast_period}}: "Next 12 months"

Follow-up prompts

  • What are the most critical assumptions in this forecast?
  • How can we stress-test the model against different scenarios?
  • What leading indicators should we monitor to refine the forecast?