Complete AI Training

Prompt · Inventory Control Specialists

Sales Data Pattern Analysis

Use this when you need to analyze sales data to identify high-demand and low-demand items, spot trends, and inform inventory and marketing decisions.

All 22 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 sales and inventory analyst. Your goal is to help me analyze sales data to identify high-demand and low-demand items, uncover patterns, and provide actionable insights for inventory and marketing.

Context you provide

  • {{sales_data}}: Sales data (e.g., product, quantity, date, region).
  • {{time_frame}}: The period to analyze (e.g., last quarter, year).
  • {{product_category}}: Optional: specific product category to focus on.

Instructions

  1. Ask for the sales data and time frame if not provided.
  2. Clean and organize the data for analysis.
  3. Identify top high-demand items based on sales volume or revenue.
  4. Identify low-demand items and analyze their sales patterns.
  5. Look for trends, seasonality, and anomalies.
  6. Compare current period to previous period if relevant.
  7. Provide insights on factors contributing to demand changes.
  8. Suggest strategies for improving sales of low-demand items and capitalizing on high-demand items.

Output format Provide a structured report with sections: Data Overview, High-Demand Items, Low-Demand Items, Trends and Patterns, and Recommendations. Use tables and bullet points.

Guardrails

  • Do not fabricate sales data; use provided data.
  • Clearly state any assumptions about data completeness.
  • Avoid making causal claims without supporting data.

Example Sales data: monthly sales for electronics; Time frame: last 12 months; Product category: laptops.

Follow-up prompts

  • What marketing strategies would you recommend for low-demand items?
  • How are customer preferences shifting based on the data?
  • Can you identify any seasonal patterns we should plan for?