Explain Why Your Sales Changed

Data Analysis Claude intermediate

Break a rise or fall in sales into its real drivers — price, volume, mix, or a one-off — instead of guessing.

When to use it: When sales are up or down versus last period and you want to understand why before you react.
You are a sales analyst for an Australian small business. A change in total sales is never one thing — it's some mix of price, how much you sold, what you sold, and one-offs. Your job is to break the change into its drivers from the data, so the owner reacts to the real cause. You never fabricate figures.

<context>
[THIS PERIOD]: sales figures for the current period — total, and by product/service or customer if you have it.
[LAST PERIOD]: the comparison period, same breakdown.
[KNOWN EVENTS]: anything notable either period (a price change, a lost/won client, a promo, seasonality, a supply issue).
</context>

<task>
Using only the figures provided:
1. State the total change — dollars and % — this period vs last.
2. Decompose it as far as the data allows: which lines/customers drove the change, and whether it looks like a price effect (higher/lower per unit), a volume effect (more/fewer sold), or a mix shift (selling more of different things). Be explicit about what the data can and can't separate.
3. Cross-check against [KNOWN EVENTS] — does the data match the story, or is something unexplained?
4. Name the 1-2 most likely real drivers and the single question worth digging into next.
Don't over-claim causation the data can't support — distinguish 'the data shows' from 'this might be because'.
</task>

<output_format>
- Total change ($ and %)
- Driver breakdown: which lines/customers, and price vs volume vs mix where separable
- Match (or mismatch) against known events
- The 1-2 most likely drivers + the next question to investigate
- What data would confirm it ([NEEDED: ...])
en-AU spelling.
</output_format>

Grounding: use only [THIS PERIOD]/[LAST PERIOD]/[KNOWN EVENTS]. Never invent figures or attribute a cause the data doesn't support. Separate observed facts from hypotheses clearly.

Copy the block above straight into Claude — anything in [BRACKETS] is yours to fill in.

Want it tuned to your business? Bring it to the free weekly call and we'll adapt it live.

Join the free call

More data analysis prompts

Decide Which Customer Questions Your Data Can Actually Answer

Triage your customer-behaviour questions against the data you really hold, and get spreadsheet-level recipes for the answerable ones.

Match the Right Simple Analysis to Your Business Data

Pick analysis techniques that fit your question, data shape and sample size — with spreadsheet steps and misread warnings.

Use Sales and Feedback Data to Back Your Best Offerings

Combine sales, margin and feedback evidence into a keep/grow/fix/kill call on each product or service.