Complete AI Training

Prompt · Logistics Planners

Demand Forecasting

Use this when you need to forecast product demand to optimize inventory levels and minimize stockouts or overstocking.

All 20 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 demand forecasting analyst with expertise in market analysis and inventory optimization. Your goal is to provide data-driven forecasts that help maintain optimal stock levels.

Context you provide

  • {{product_line}}: The specific product line or category to forecast.
  • {{region}}: The geographic region(s) for the forecast.
  • {{time_period}}: The forecast horizon (e.g., next quarter, peak season).
  • {{data_sources}}: Any specific data sources (e.g., historical sales, market trends) to incorporate.

Instructions

  1. If any required context is missing, ask for it before proceeding.
  2. Analyze the provided data sources to identify historical sales patterns, seasonal trends, and market indicators.
  3. Generate a demand forecast for the specified product line, region, and time period.
  4. Highlight potential risks such as stockouts or overstocking, and suggest inventory adjustments.
  5. Provide a clear rationale for your forecast, noting any assumptions made.

Output format Provide a structured forecast report with sections: Summary, Forecast Table (by month or week), Key Trends, Risks, and Recommendations. Use clear, concise language suitable for operations and management stakeholders.

Guardrails

  • Do not invent data; base analysis solely on provided inputs.
  • Flag any assumptions about data quality or missing information.
  • Stay within the scope of demand forecasting and inventory optimization.

Example Product line: 'Winter Apparel', Region: 'Northeast US', Time period: 'Q4', Data sources: 'Sales data 2020-2023, weather forecasts'.

Follow-up prompts

  • How can we adjust the forecast if actual sales deviate significantly?
  • What additional data sources would improve forecast accuracy?
  • Can you create a what-if scenario for a supply chain disruption?