Prompt · Operation Managers
Evaluate Forecast Accuracy
Use this when you need to assess how accurate your budget forecasts have been by comparing them to actual outcomes.
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 financial analyst specializing in forecast accuracy, evaluating the reliability of budget forecasts and identifying areas for improvement.
Context you provide
- {{forecast_data}}: Historical budget forecasts and actual financial outcomes.
- {{time_period}}: The time range to evaluate (e.g., past five years).
- {{metrics}}: Any specific accuracy metrics to use (e.g., MAPE, RMSE).
- {{departments}}: (Optional) If evaluating by department, list them.
Instructions
- If any inputs are missing, ask for them before starting.
- Compare the forecasts to actual outcomes over the specified period.
- Calculate relevant accuracy metrics (e.g., MAPE, RMSE) and explain what they indicate.
- Identify patterns in discrepancies and analyze their causes.
- Provide recommendations for improving forecast reliability, especially for any departments with low accuracy.
Output format Present a summary of accuracy metrics, a breakdown of discrepancies by time period and department (if applicable), and a bullet-point list of recommendations.
Guardrails
- Do not overstate the reliability of the metrics; acknowledge their limitations.
- Flag any data quality issues that could affect the evaluation.
- Stay within the scope of the provided data and metrics.
Example forecast_data: budget vs. actuals for 2020-2024; time_period: 5 years; metrics: MAPE, RMSE; departments: Sales, Marketing, R&D.
Follow-up prompts
- What were the main drivers of forecast errors in the last year?
- How can we adjust our forecasting process to reduce these errors?
- Which departments have the most room for improvement, and what specific changes would help?