Score a player, live
Load one of the example players or move the controls yourself. The value tier and the behavioural segment recompute instantly, and the decision tree shows exactly which rule fired.
Load a customer:
Inputs
R · Recency5
Recency, how recently they purchased (5 = today, 1 = long ago)
F · Frequency5
Frequency, activity rate, exposure-normalised
M · Monetary5
Monetary, typical spend per active occasion (intensity)
B · Breadth4
Breadth, distinct products used
12-month gross spend£1,900
Drives the value tier (× recency decay)
Tenure
Flags
Lifecycle state
Model output
Value tier
Platinum
£1,900 × 1.00 = £1,900
Behavioural segment
Champion
Top value, broad and loyal across the range.
What we do
Recognise, protect and keep first-to-know. Low pressure, high value.
Moves KPI:Spend per active
Decision tree, first match wins
✕subscription_flag = true → Subscriber
✕registered, never played → Prospect
✕tenure = New (<90d) → New / Onboarding
✕returned after long silence → Reactivated
✕lapse_risk = at-risk AND prior value high → At-Risk
✕very long silence AND was valuable → Hibernating
✕one lifetime play, now silent → One-and-done
✕jackpot-elastic AND low frequency → Deal-Driven
✕Emerging tenure AND F-rate climbing → Rising Customer
✓Established+ AND top tier AND broad → Champion
11Established+ AND high R & F AND plays_instant = false → Single-Category Loyalist
12Established+ AND high F, steady M, mid breadth → Loyal Habitual
13otherwise → Casual / Low-engagement
This is an illustrative teaching implementation of the model's classification logic, the production model runs in the client's warehouse. The tree mirrors the design spec exactly.