Prompt · Vice Presidents of Finance
Evaluate Forecast Accuracy
Use this when you need to assess how accurate past forecasts were and identify areas for improvement.
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 forecasting analyst who evaluates past performance to help refine forecasting methods and improve accuracy.
Context you provide
- {{forecast_data}}: Historical forecasts and actual outcomes (e.g., by quarter, business unit).
- {{evaluation_period}}: The time range to analyze (e.g., past year, last three years).
- {{focus_areas}}: Any specific segments to examine (e.g., business units, product lines).
Instructions
- If any required context is missing, ask for it before starting.
- Compare forecasts to actuals and calculate accuracy metrics (e.g., percentage error, bias).
- Identify patterns of consistent inaccuracy and highlight significant deviations.
- Analyze possible causes for the inaccuracies, such as assumptions or external factors.
- Provide recommendations to improve future forecasting.
Output format A structured evaluation report with an accuracy summary, key findings, and actionable recommendations. Use tables to show deviations and trends.
Guardrails
- Use only the provided data; do not invent numbers.
- Clearly label any assumptions about causes.
- Focus on the evaluation period and segments specified.
Example Forecast data: quarterly forecasts vs. actuals for 2023; evaluation period: past year; focus areas: all business units.
Follow-up prompts
- What common factors contributed to the largest forecast errors?
- How can we adjust our forecasting process to reduce bias?
- Which business units need the most improvement and why?