What are your customer segments, actually?
Most segment lists get invented in a meeting: enterprise, SMB, the loyal ones. This template takes 26 customers with three numbers each, monthly revenue, orders per month, and months since signup, and lets k-means find the groups that are actually there. Sorting by any one column gets it wrong, because the segments only appear when all three columns are read together.
Marketing Advanced Clustering free
After you install, this is the model to open.
Find Your Real Customer Segments
- In your spreadsheet, click the Sortia icon in the strip of icons down the right-hand edge. No strip? Click the arrow at the bottom-right to open it. You can also use Extensions, then Sortia, then Open Sortia.
- Click Start from a template and put that name in the search box.
- Pick the card with that name and click Load this template. It arrives on a new tab with real numbers already in it.
The answer
One click on Run. Three groups come back, and they are not the ones most founders would have drawn by hand.
- Big-ticket occasional
- $535 per month each, 5 customers, $167 per order
- Everyday regulars
- 60% of all orders but 28% of revenue, 11 customers
- Newer mid-basket
- $307 per month each, 10 customers, 10 months old
- Revenue concentration
- 33% of revenue from 19% of customers
The five big-ticket buyers are 19% of the list and 33% of monthly revenue, at $167 per order against $18 per order for the eleven regulars who place 60% of all orders. That should change what you do with each group: one extra order a month from those five is worth $836 a month, about 10% of total revenue, while the same discount campaign aimed at the regulars mostly buys more shipping labels. The ten newer mid-basket customers are the biggest single revenue block at 38% and average only 10 months as customers, which makes them a retention problem rather than an acquisition one.
The model
One row per customer, three numeric columns, nothing pre-labeled. The segment names are written nowhere in the sheet; they come out of the clustering.
| Customers in the sheet | 26 rows, no labels |
| Columns clustered | monthly revenue, orders per month, tenure |
| Monthly revenue | $150 – $610 per customer |
| Orders per month | 2 – 14 |
| Tenure | 4 – 44 months |
| Total monthly revenue | $8,030 across all 26 customers |
| Clusters requested (k) | 3 |
| Scaling | automatic, each column normalized before distance is measured |
Once it is in your sheet
- The model arrives with real numbers in it and runs as it stands, so you can press the button first and understand it second.
- Change the numbers to yours. The sheet marks which cells are inputs and which hold formulas, and most labels carry a note explaining the row.
- Press the run button at the bottom of the panel. It is labeled for the tool you are in, and the result lands on its own tab, with a written reading of it beside the figures.
Never used Google Sheets? Start here goes the whole way, in seven steps, and assumes nothing.
Next question
- The remodel looks better. Would you bet the chain on it?Which Store Layout Sells More?
- Which step of your funnel moves least reliably?Spend, Visits, Sales: What Moves Together?
- Is that channel better, or just one big customer?Which Channel Brings the Big Spenders?
- How far is the campaign from breaking even?The Conversion Rate That Breaks Even
- The variant is up 25.9%. What lift can you actually promise?Did the B Version Win?
- How long does this A/B test have to run?How Many Visitors Does This Test Need?
Every model like this one, and the method behind them: Machine learning in Google Sheets.