Segment a Fintech's Customers by Financial Behaviour
A personal finance app with 1.5M users offers the same products to everyone: savings account, automatic investing, quick loan. Product wants to design different experiences depending on how each user manages money, but nobody has defined financial segments and surveys do not reflect what people actually do.
Where the money comes from
What to do now
- 1Segment by real financial behaviour.
- 2Design one experience per segment with ethical criteria.
- 3A/B test by segment with value and risk metrics.
For your committee
One page with the decision, the impact, the risks, the steps and the KPI to track.
The print dialog opens: choose "Save as PDF".
Watch out: more volume is not always more profit
Pushing quick loans to the "at the limit" segment raises revenue in the short term and then defaults, complaints and reputational damage. Offer each segment the product that improves their situation.
KPI for the committee
Margin per user and delinquency by segment.
Detail for your data team
Proposed technique: K-Means Clustering
Why: There is no 'user type' label: the task is to discover structure in real behaviour. K-Means groups 1.5M users at scale and its centroids translate directly into profiles that product design can understand.
Cost of getting it wrong: Poorly defined segments produce generic experiences; segments used without ethics can harm vulnerable customers and attract penalties.
Data needed: Categorised transactions over 12 months: income, fixed expenses, leisure, savings, overdrafts.; App usage: frequency, features used, savings goals created.; Products held and average balance.