Skip to content

Scatter Chart

Every customer is a dot. Patterns appear on their own. A scatter chart plots one measure against another, one point per entity. Nothing is aggregated away, so the relationship between the two measures - and every account that defies it - stays visible.

Scatter Chart - one row per account
Engagement scoreChurn risk (%)
12, 881288
18, 791879
22, 842284
15, 721572
28, 682868
9, 91991
31, 743174
24, 612461
19, 661966
74, 817481
68, 766876
81, 728172
77, 667766
71, 637163
86, 698669
21, 342134
33, 283328
17, 411741
39, 223922
26, 372637
44, 314431
61, 196119
72, 147214
83, 118311
66, 246624
79, 217921
91, 9919
88, 178817
58, 275827
94, 139413
69, 316931
76, 367636
84, 298429
Illustrative example RetainCLM scatter chart plotting customer engagement score against predicted churn risk with four labelled quadrants
AI Insight

A cluster of high-value accounts shows high engagement *and* high churn risk - a combination that usually indicates a commercial or champion problem rather than a product-usage one.

Recommended action

Route this quadrant to an account-management review rather than a re-engagement email sequence.

What is a scatter chart?

A scatter chart plots one measure against another, one point per entity. Nothing is aggregated away, so the relationship between the two measures - and every account that defies it - stays visible.

Why is a scatter chart useful?

Averages hide the accounts that matter. A scatter is how you find the customer who is paying the most and using the product the least, which no bar chart of segment averages will ever surface.

How RetainCLM uses it

Plot engagement score against churn risk, one dot per account, sized by nothing and coloured by risk tier. The high-risk dots sitting in the high-engagement region are the interesting ones - their risk is not coming from disengagement.

The chart above is drawn from illustrative demo data chosen to make the visualization legible. It does not describe real RetainCLM customers. On a live account the same chart is drawn from your own customer, usage, billing and support data.

How to read it

Look for the overall drift first, then the points that sit outside it. Quadrant dividers at meaningful thresholds turn a cloud into four named groups you can act on.

Limitations to keep in mind

A visible relationship is not causation, and dense clouds overplot - points land on top of each other and hide the true density. Use transparency, or bin the data, when there are thousands of accounts.

Related concepts

A scatter chart is most useful alongside churn prediction, customer intelligence, customer retention analytics. RetainCLM builds these views on one unified customer record, so a pattern you notice in one visualization can be followed into the next without exporting anything.

Questions about the scatter chart

What does a scatter chart show?

The relationship between two numeric measures, with one point per record. It reveals correlation, clustering and outliers that summary statistics average away.

How do you use a scatter chart for churn analysis?

Put a behavioural measure such as engagement on one axis and predicted churn risk on the other. Accounts that break the expected pattern - high engagement with high risk - identify churn causes that usage data alone will not explain.

What are quadrants on a scatter chart?

Reference lines at meaningful thresholds that divide the plot into four labelled regions, turning a continuous cloud into named groups that map to different actions.

See a scatter chart built on your customers

Book a demo and we will build this chart, and the rest of the library, against your own retention and revenue data.

Book a Demo