Member Engagement Scoring Agent
Scores loyalty members on spend, visits and sentiment and explains changes.
- Industry
- Retail
- Department
- Customer
- Team
- Customer Lifecycle
- Kind
- Investigator
- Approver
- Customer Service Manager
- Code
- CUS-13
It scores loyalty members and segments on spend, visit frequency, channel mix, returns and service sentiment, and explains why a segment's engagement moved, separating seasonality and promotions from real changes such as store closures, delivery failures or range gaps. It writes the scores back to the CRM for targeting. **The problem it solves:** Why the engagement of a loyalty segment rose or fell in the period, beyond seasonal and promotional effects.
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 loyalty and CRM platform: member spend, visits, channel mix, returns and case sentiment for the scope and period, and the same weeks last year..
- 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 Customer Service Manager with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the loyalty and CRM platform: it updates each member's engagement score and segment trend. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The engagement model: the score components and weights, seasonal norms by segment, the known distortions (sale events, store refits, weather), and the segment definitions.
Reads from
the loyalty and CRM platform: member spend, visits, channel mix, returns and case sentiment for the scope and period, and the same weeks last year.
Acts in
the loyalty and CRM platform: it updates each member's engagement score and segment trend.
Hands back
An object with segments (a list of segment, score, change_points and trend), causes (a list of segment, likely_cause, evidence and confidence) and member_scores_written (a count).
Asks a person when
The explanation points to a store, a delivery partner or a range decision, which belongs to another team to confirm.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Score change that needs explaining (points) | 5 | A segment's score moving this many points on a 100-point scale is explained. |
| Weight of the returns rate in the score | 0.15 | The share of the score from the returns rate, inverted. |
| Compare with the same period last year | On | When on, changes are judged against the same weeks last year, to strip seasonality. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Score each member on spend, visit frequency, channel mix, returns rate (weighted 0.15) and service sentiment, on a 100-point scale.
- Explain any segment whose score moved 5 points or more.
- When on is true, judge changes against the same weeks last year, not the previous period.
- Check promotions, sale events, store closures or refits, delivery failures and stock-outs in the segment's categories before naming a cause.
- Weigh at least two explanations and say what evidence separates them; never name an individual member in a segment explanation.
See the Member Engagement Scoring Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.