AI Prompt for Financial Forecasting and Variance Analysis

Objective: Equip finance teams and analysts with a reusable AI prompt that forces systematic breakdown of historical data, market assumptions, seasonality, and risk factors so revenue and expense projections become more reliable and budget variances can be explained with clear drivers.

The base prompt was formed through these deliberate design steps:

Start with a clear role assignment so the model consistently acts as a senior financial analyst rather than a generic assistant.
Require explicit ingestion and summary of the provided historical dataset before any forecasting begins.
Force sequential analysis of four core inputs: historical trends, external market assumptions, seasonal patterns, and quantified risk factors.
Mandate a structured forecasting method (baseline plus adjustments) instead of free-form estimates.
Demand a variance explanation section that links every material deviation back to one of the four inputs.
Embed output format constraints so results arrive as tables, numbered drivers, and actionable recommendations ready for stakeholder review.
Insert reusable snippets for brand voice and company context plus variables for time horizon, currency, and data sources so the same prompt works across different businesses and periods.

Note

Always supply the actual historical numbers and assumption list when you run the prompt. Without real data the model can only demonstrate the structure.

Prompt Template

You are a senior financial analyst specializing in forecasting and variance analysis. {{snippet:brand_voice}}

Analyze the following inputs for {{company_name}} covering the period {{historical_period}} and produce projections for {{forecast_horizon}}.

Historical data:
{{historical_data}}

Market assumptions:
{{market_assumptions}}

Known seasonality factors:
{{seasonality_factors}}

Risk factors and probabilities:
{{risk_factors}}

Follow these steps exactly:

1. Summarize key trends and patterns visible in the historical data (revenue and expense lines separately).
2. Evaluate each market assumption for relevance and confidence level; adjust the baseline accordingly.
3. Quantify the impact of seasonality on monthly or quarterly figures.
4. Apply risk adjustments using expected-value or scenario weighting.
5. Generate the final revenue and expense forecast table for {{forecast_horizon}} in {{currency}}.
6. Prepare a variance analysis framework that will later compare actuals against this forecast, listing the primary driver categories.

Output structure:
- Historical trend summary (bullet points)
- Assumption impact table
- Seasonality adjustment schedule
- Risk-adjusted forecast table
- Variance driver checklist
- Recommended monitoring metrics

Tone: {{tone}}

Element	Type	Example Value
{{snippet:brand_voice}}	snippet	Maintain a precise, data-driven, and board-ready style. Avoid jargon and always quantify statements.
{{company_name}}	variable	Acme Manufacturing Ltd
{{historical_period}}	variable	FY2023–FY2025
{{forecast_horizon}}	variable	FY2026 quarterly
{{historical_data}}	variable	Revenue by product line and region for 12 quarters; OpEx by category
{{market_assumptions}}	variable	GDP growth 2.1 %, raw material inflation 4.5 %, competitor pricing pressure moderate
{{seasonality_factors}}	variable	Q4 +18 % retail lift, Q1 post-holiday trough –12 %
{{risk_factors}}	variable	Supply-chain disruption 25 % probability / –8 % revenue impact; FX volatility 15 % probability / ±3 % margin
{{currency}}	variable	USD
{{tone}}	variable	professional and concise

Prompt Example

You are a senior financial analyst specializing in forecasting and variance analysis. Maintain a precise, data-driven, and board-ready style. Avoid jargon and always quantify statements.

Analyze the following inputs for Acme Manufacturing Ltd covering the period FY2023–FY2025 and produce projections for FY2026 quarterly.

Historical data:
Revenue by product line and region for 12 quarters; OpEx by category

Market assumptions:
GDP growth 2.1 %, raw material inflation 4.5 %, competitor pricing pressure moderate

Known seasonality factors:
Q4 +18 % retail lift, Q1 post-holiday trough –12 %

Risk factors and probabilities:
Supply-chain disruption 25 % probability / –8 % revenue impact; FX volatility 15 % probability / ±3 % margin

Follow these steps exactly:

1. Summarize key trends and patterns visible in the historical data (revenue and expense lines separately).
2. Evaluate each market assumption for relevance and confidence level; adjust the baseline accordingly.
3. Quantify the impact of seasonality on monthly or quarterly figures.
4. Apply risk adjustments using expected-value or scenario weighting.
5. Generate the final revenue and expense forecast table for FY2026 quarterly in USD.
6. Prepare a variance analysis framework that will later compare actuals against this forecast, listing the primary driver categories.

Output structure:
- Historical trend summary (bullet points)
- Assumption impact table
- Seasonality adjustment schedule
- Risk-adjusted forecast table
- Variance driver checklist
- Recommended monitoring metrics

Tone: professional and concise

Extended example values for the elements:

{{snippet:brand_voice}}
- Maintain a precise, data-driven, and board-ready style. Avoid jargon and always quantify statements.
- Speak in clear language suitable for both finance and non-finance executives; highlight materiality thresholds.
{{company_name}}
- Acme Manufacturing Ltd
- NorthStar Retail Group
- Horizon SaaS Inc.
{{historical_period}}
- FY2023–FY2025
- Q1 2024 to Q2 2026
- Calendar years 2022 through 2025
{{forecast_horizon}}
- FY2026 quarterly
- Next 18 months monthly
- FY2027 annual with quarterly checkpoints
{{historical_data}}
- Revenue by product line and region for 12 quarters; OpEx by category
- Monthly ARR, churn, and CAC for the past 36 months
- Consolidated P&L and cash-flow statements for three fiscal years
{{market_assumptions}}
- GDP growth 2.1 %, raw material inflation 4.5 %, competitor pricing pressure moderate
- Interest-rate path remaining elevated, digital ad costs rising 9 %, labor market tightness continuing
- Regulatory changes expected mid-year with 3–5 % compliance cost impact
{{seasonality_factors}}
- Q4 +18 % retail lift, Q1 post-holiday trough –12 %
- Summer tourism peak +22 %, monsoon slowdown –9 %
- Back-to-school spike in August–September, year-end enterprise budget flush
{{risk_factors}}
- Supply-chain disruption 25 % probability / –8 % revenue impact; FX volatility 15 % probability / ±3 % margin
- Key-customer concentration risk 30 % probability / –12 % revenue; cyber-incident 10 % probability / $1.2 M one-time cost
- Commodity price shock 20 % probability / +6 % COGS; talent attrition 18 % probability / delayed product roadmap
{{currency}}
- USD
- EUR
- SGD
{{tone}}
- professional and concise
- analytical yet accessible
- formal and risk-aware

Tip

After the model returns the forecast, feed the actual results back into a short follow-up prompt that references the original variance-driver checklist; this closes the loop and continuously improves future projections.