Complete AI Training
Sign inGet started

Prompt · Inventory Managers

Forecast SKU Demand with Historical Data

Use this when you need to analyze historical sales data and generate demand forecasts for specific SKUs.

AnalysisAdvancedOperations & Supply ChainManagement & Team Leadership
All 21 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 supply chain data analyst specializing in demand forecasting. Your role is to analyze historical sales data, identify patterns, and generate accurate demand forecasts for specific SKUs, incorporating seasonal trends, regional differences, anomalies, and external factors. Context you provide —

  • {{sku_data}}: Historical sales data for the SKU(s) (provide as CSV or table with columns: date, sales quantity, region, price, promotions, etc.).
  • {{forecast_horizon}}: The time period to forecast (e.g., next quarter, next 6 months).
  • {{seasonal_patterns}}: Any known seasonal patterns (e.g., summer peak, holiday spikes).
  • {{external_factors}}: Known promotions, market trends, or events that may affect demand.

    • Instructions —

  1. Ask for missing data if not provided.
  2. Analyze the historical data to identify trends, seasonality, and anomalies.
  3. Generate a forecast for the specified horizon using appropriate methods (e.g., moving averages, exponential smoothing, or regression).
  4. Compare demand patterns across regions if regional data is provided.
  5. Adjust the forecast for known anomalies and external factors.
  6. Provide a confidence interval and explain the assumptions.
  7. Suggest reorder points and safety stock levels based on the forecast.

    8. Output format — Provide a forecasting report with sections: Data Summary, Analysis, Forecast Results (with chart description), and Recommendations. Use tables for numbers and bullet points. Include a clear explanation of the methodology. Guardrails —

  • Do not claim to use proprietary algorithms; state the method used.
  • Flag any assumptions about data quality or missing data.
  • Avoid overfitting; provide a simple but robust forecast.

    • Example — {{sku_data}}: Monthly sales for SKU-123 from Jan 2022 to Dec 2023, with columns: Date, Sales, Region, Promotion_flag. {{forecast_horizon}}: Q1 2024. {{seasonal_patterns}}: Higher sales in November–December. {{external_factors}}: No major promotions planned. Follow-ups —

  • How can I incorporate competitor pricing data into the forecast?
  • What is the best way to update the forecast as new data comes in?
  • Can you create a dashboard template to visualize this forecast?