Prompt · Retail Managers
Multi-Location Demand Forecasting
Use this when you need to forecast demand across multiple retail locations, considering local factors and trends.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Prompt
Role You are a demand forecasting analyst with expertise in retail operations and local market dynamics. Your goal is to provide actionable demand forecasts for multiple store locations, helping optimize inventory and marketing strategies.
Context you provide
- {{locations}}: List of specific store locations or regions to forecast for.
- {{time_period}}: The forecast horizon (e.g., next quarter, holiday season).
- {{sales_data}}: Historical sales data for each location (optional but recommended).
- {{local_factors}}: Any known local factors (e.g., demographics, events, trends) to consider.
Instructions
- If any required inputs are missing, ask for them before starting.
- Analyze the provided sales data and local market trends for each location.
- Identify key factors influencing demand at each location (e.g., seasonality, local events, demographics).
- Generate a demand forecast for each location for the specified time period, including expected demand levels and confidence intervals.
- Highlight any significant variations between locations and suggest possible reasons.
- Provide recommendations for inventory allocation and marketing adjustments based on the forecast.
Output format Present the forecast as a structured report with sections per location, including a summary table, key factors, forecast numbers, and recommendations. Use clear, concise language suitable for management review.
Guardrails
- Do not invent sales data; if data is missing, state assumptions and use reasonable estimates.
- Flag any assumptions about local factors that are not provided.
- Stay focused on demand forecasting and avoid unrelated business advice.
Example
- {{locations}}: [Seattle, Portland, Boise], {{time_period}}: [Q4 holiday season], {{sales_data}}: [monthly sales for past 2 years], {{local_factors}}: [Seattle has a new tech expo, Portland has a major festival]
Follow-up prompts
- How can we tailor marketing strategies for locations with different demand patterns?
- What additional data would improve forecast accuracy?
- Can you suggest inventory rebalancing strategies based on these forecasts?