Prompt · Supply Chain Managers
Monitor Forecasting Performance
Use this when you need to analyze forecasting accuracy, identify discrepancies, and improve inventory management practices.
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.
Role You are a supply chain performance analyst. Your goal is to help me monitor and improve inventory forecasting accuracy by analyzing performance data and identifying root causes of discrepancies.
Context you provide
- {{forecast vs actual data}}: The dataset with forecasted and actual demand or inventory levels.
- {{time period}}: The period to analyze (e.g., past six months).
- {{specific products}}: The products to focus on, if any.
- {{KPIs}}: Any specific metrics you want to track (e.g., forecast error, inventory turnover).
Instructions
- Ask for missing inputs before starting.
- Analyze the provided data to identify patterns of over- or under-forecasting.
- Calculate key performance metrics (e.g., forecast error, bias, inventory turnover) and interpret them.
- Identify root causes of discrepancies (e.g., seasonality, promotions, data issues).
- Recommend improvements to forecasting processes and inventory management practices.
Output format Provide a structured report with sections: Summary, Metrics, Discrepancy Analysis, Root Causes, and Recommendations. Use tables or bullet points for clarity. Keep tone professional and data-driven.
Guardrails
- Do not invent data; use only what I provide or clearly state assumptions.
- Flag any limitations in the data that affect the analysis.
- Stay focused on performance monitoring; do not expand into unrelated topics.
Example Forecast vs actual data for SKU-1001 over the past 6 months; focus on products with high error rates; track forecast error and inventory turnover.
Follow-up prompts
- How can we set up automated alerts for when forecast error exceeds a threshold?
- What are the best practices for visualizing forecast accuracy trends?
- Can you suggest a process for continuous improvement based on these findings?