- Industry
- Banking
- Department
- Customer
- Team
- Customer Lifecycle
- Kind
- Investigator
- Approver
- Head of Retail Banking
- Code
- CUS-13
It scores each customer relationship's health from product holding, digital activity, salary credits, balances trend, complaints and arrears signals using the weighted health model, and explains which signals moved the score. It separates a life change or a move of salary to another bank from a service problem, and records the scores in the CRM. **The problem it solves:** Why each customer's relationship health is what it is and what moved it: the signals and how they changed over the period, and the events that could explain them.
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: product holdings, digital activity, salary credits, balance trends, complaints and arrears flags for the customers..
- 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
Weighs competing explanations against the evidence and shows which one holds up.
- 05Asks a person
Hands the work to Head of Retail Banking with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the CRM: it records each customer's health score, drivers and route. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The relationship health model: signals and weights, the rule that arrears and financial-difficulty signals route to support rather than retention, segment benchmarks and data-protection limits on profiling.
Reads from
the risk data warehouse: product holdings, digital activity, salary credits, balance trends, complaints and arrears flags for the customers.
Acts in
the CRM: it records each customer's health score, drivers and route.
Hands back
A list with one entry per customer, each with customer_id, score, band (green, amber or red), change, drivers (a list with signal and effect), likely_cause and route (retention, support or none).
Asks a person when
A customer turns red, the score drops 15 points or more, arrears or difficulty signals appear, or a score rests on fewer than three signals.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Digital activity weight (%) | 30 | Weight for logins and transactions. |
| Salary credit weight (%) | 30 | Weight for a regular salary or income credit. |
| Service weight (%) | 20 | Weight for complaints and failed payments. |
| Product holding weight (%) | 20 | Weight for products held. |
| Red below | 50 | Scores below this are red. |
| Score drop alert (points) | 15 | A drop this large is flagged. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Score with 30, 30, 20 and 20 percent weights.
- Below 50 is red; a drop of 15 points is flagged.
- A salary that stops arriving is tested against a job change before a switch to another bank.
- Arrears or financial-difficulty signals route the customer to the financial support team, never a retention offer.
- Explain each score by the signals that moved it, and never use protected characteristics.
See the Account Health Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.