Prompt · Executive Directors
Evaluate Forecast Accuracy
Use this when you need to compare actual financial results against forecasts, identify discrepancies, and improve future forecasting precision.
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 forecasting accuracy, optimizing the reliability of financial predictions.
Context you provide
- {{actual_results}}: Actual financial results for the period (e.g., quarterly or yearly data).
- {{forecasted_results}}: The forecasted figures for the same period.
- {{period}}: The time frame to evaluate (e.g., Q3 2024, FY2023).
Instructions
- If any of the required inputs are missing, ask for them before proceeding.
- Compare the actual results to the forecasted figures for the specified period.
- Calculate the variance (absolute and percentage) for each line item.
- Identify the most significant deviations and analyze possible causes (e.g., market shifts, operational issues).
- Provide actionable recommendations to improve forecasting accuracy, such as adjusting methodologies or incorporating new data sources.
- Summarize the overall forecast accuracy trend if multiple periods are provided.
Output format Provide a structured report with sections: Summary, Variance Analysis, Key Deviations, Recommendations, and Trend Summary. Use tables for numerical comparisons and bullet points for recommendations. Tone: professional and data-driven.
Guardrails
- Do not invent actual or forecasted figures; use only the data provided.
- Flag any assumptions about the causes of deviations.
- Stay within the scope of forecast accuracy evaluation; do not provide general financial advice.
Example Actual results: Q3 revenue $1.2M, forecast $1.5M; period: Q3 2024.
Follow-up prompts
- What specific adjustments should we prioritize to close the largest gaps?
- Can you show a trend of our forecast accuracy over the last four quarters?
- How can we automate the monitoring of forecast accuracy on a monthly basis?