variance-analysis

When to use

Use when a finance or leadership user needs an evidence-backed explanation of actuals against an approved budget or forecast for a named period, category, or total. Confirm the comparison period and basis before calculating.

Do not use this skill to post or reclassify ledger entries, change a budget or forecast, approve corrective action, or provide audit sign-off. Not for close-status tracking, tax advice, or a financial decision made on behalf of a human owner.

Inputs and source discipline

1. Capture the period, comparison basis, metric definition, actual source, budget/forecast source, source dates, date checked, and explicit as-of date. Record unit, currency, sign convention, and time window for every input; never invent a missing date or denominator.
2. Prefer reconciled ledger or close-package actuals, then an approved budget or forecast, then dated operational reports, then dated context in meeting notes. A narrative explanation is not evidence of a number. Preserve source hierarchy and contradictory inputs.
3. Validate that actual and comparison values measure the same category, period, unit, currency, accounting basis, and aggregation. Convert only with a cited rate or rule and date; otherwise mark the comparison not comparable rather than forcing a result.

Method

1. Work read-only and state the formula before computing: for example, dollar variance as actual - comparison, and percentage variance as variance / absolute comparison only when the denominator is non-zero and that convention is authorized. Preserve the sign and state how favorable/unfavorable is determined for revenue versus expense; never flip signs to make a result look better.
2. Recalculate each category and reconcile the category variances to the supplied total, allowing only documented rounding. Investigate missing categories, scope differences, and duplicate rows; if totals cannot reconcile, report the total as unknown or contradictory.
3. Apply the supplied materiality threshold in both amount and percentage terms when available. If no threshold is supplied, state that materiality was not assessed; do not invent a cutoff or call a result material solely because it is visually large.
4. For each material or requested variance, classify the cause as timing or permanent only when dated evidence supports it. Label a plausible but unverified explanation hypothesized, and use unknown when evidence does not establish a cause. Keep corrective actions as recommendations for human review.