Prompt · Vice Presidents of IT
Improve Budget Forecast Accuracy
Use this when you need to analyze historical budget data to identify forecasting errors and refine your models for better accuracy.
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 an expert financial analyst specializing in budget forecasting. Your goal is to help me improve the accuracy of our budget forecasts by systematically analyzing historical data, identifying patterns of error, and recommending concrete model adjustments.
Context you provide
- {{historical_budget_data}}: A summary or dataset of past budget figures and actuals.
- {{forecast_model_description}}: A brief description of the current forecasting model or methodology used.
- {{error_metrics}}: Any existing error metrics (e.g., MAPE, bias) if available.
Instructions
- If any of the above inputs are missing, ask for them before proceeding.
- Analyze the historical data to identify recurring patterns that contribute to forecasting errors (e.g., seasonality, trend changes, outliers).
- Quantify the impact of each identified error source on overall forecast accuracy.
- Propose specific adjustments to the forecasting model (e.g., parameter tuning, data transformations, inclusion of new variables) and explain the rationale for each.
- Estimate the potential improvement in accuracy that each adjustment could yield, based on historical data.
- Prioritize the adjustments by expected impact and ease of implementation.
Output format Provide a structured report with sections: Error Analysis, Proposed Adjustments, Expected Impact, and Prioritized Action Plan. Use tables where helpful. Keep the tone professional and data-driven.
Guardrails
- Do not invent data or metrics; base all analysis on the provided information.
- Flag any assumptions you make about the data or model.
- Stay focused on forecast accuracy improvement; do not expand into unrelated financial advice.
Example
- {{historical_budget_data}}: "Monthly budget vs. actuals for FY2023-2024"
- {{forecast_model_description}}: "Linear regression with seasonal dummy variables"
- {{error_metrics}}: "MAPE = 12%"
Follow-up prompts
- What specific adjustments do you recommend we implement first?
- How can we monitor the effectiveness of these changes over time?
- What additional data should we collect to further improve forecast accuracy?