- Industry
- Banking
- Department
- Marketing
- Team
- Brand and Insights
- Kind
- Assistant
- Approver
- Head of Marketing
- Code
- MKT-14
It groups the bank's customers into segments by product holding, balances, channel use and life stage for campaigns and relationship coverage. It never uses protected characteristics, and keeps customers in financial difficulty out of credit-offer segments.
How it works
6 steps, and a person signs off before step 6.
- 01Looks it up
Finds the record the request is about in the risk data warehouse: customers' product holdings, balances, channel use, tenure and arrears and vulnerability flags..
- 02Reads the request
Works out what is being asked and what a complete answer needs.
- 03Checks the facts
Checks figures, dates and rules against the source records, not from memory.
- 04Works it through
Prepares the draft, match, recommendation or reply, with its sources.
- 05Asks a person
Hands the work to Head of Marketing with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the CRM: it creates the segments as audiences. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The segmentation guide: the segment model, value definitions (balances, product holding, revenue), data protection and fair-treatment rules, and the fields that must never be used.
Reads from
the risk data warehouse: customers' product holdings, balances, channel use, tenure and arrears and vulnerability flags.
Acts in
the CRM: it creates the segments as audiences.
Hands back
A list with one entry per segment, each with name, definition, size, average_balance, products_held, suggested_use and exclusions.
Asks a person when
A segment is for a credit offer, or the request asks for a criterion close to a protected characteristic.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Smallest segment | 1000 | Smaller segments are merged. |
| Most segments | 8 | No more than this. |
| Value window (months) | 12 | Value is measured over this period. |
| Fields never used | race, religion, health, gender, marital status, nationality, postcode as a proxy | Comma-separated. Protected characteristics and their proxies. |
| Keep customers in difficulty out of credit segments | On | When on, customers in arrears or flagged vulnerable are excluded from credit-offer segments. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Build at most 8 segments of at least 1000 customers, valued over 12 months.
- Never use race, religion, health, gender, marital status, nationality, postcode as a proxy, or anything that stands in for them.
- When on is true, customers in arrears, collections or flagged vulnerable are excluded from credit-offer segments.
- Export only customer ids to marketing tools, never balances or account numbers.
- Describe each segment in plain words with its size and value.
See the Customer Segmentation Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.