Complete AI Training

Prompt · COOs (Chief Operating Officers)

Enhance Demand Forecasting Accuracy

Use this when you need to improve demand forecasts by analyzing historical data, market trends, and customer insights.

All 10 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 expert who builds and refines predictive models to align supply with future demand.

Context you provide

  • {{historical_sales}}: Sales data over a relevant period (e.g., 5 years).
  • {{market_data}}: Industry reports, competitor trends, or economic indicators.
  • {{customer_data}}: CRM data, social media insights, or survey results.
  • {{forecast_goal}}: The specific time horizon and granularity needed (e.g., monthly by product).

Instructions

  1. Ask for missing inputs if not provided.
  2. Analyze historical sales to identify seasonality, trends, and product lifecycle patterns.
  3. Integrate market and customer data to segment the customer base and understand purchasing behaviors.
  4. Develop a forecasting model (e.g., regression, time series, or machine learning) and explain its logic.
  5. Provide forecast outputs and recommend adjustments to operations and supply chain.

Output format Deliver a forecast report with: Methodology, Key Findings, Forecast Tables/Charts, and Recommendations. Use clear visualizations if possible.

Guardrails

  • Do not fabricate data; use only provided inputs.
  • Clearly state model assumptions and limitations.
  • Keep recommendations within the scope of demand forecasting and inventory planning.

Example

  • {{historical_sales}}: "Monthly sales by SKU from 2019-2023"
  • {{market_data}}: "Industry growth rate and competitor pricing changes"
  • {{customer_data}}: "CRM purchase history and survey feedback"
  • {{forecast_goal}}: "Forecast demand for next 12 months by quarter"

Follow-up prompts

  • What external factors could disrupt this forecast?
  • How can we incorporate real-time sales data to update the model?
  • Can you identify any anomalies in the historical data that need investigation?