Business case, 28 September 2026
Managing risk on 6/9/12
Edvin Maehre
The main risk question
How do we let customers buy bigger baskets over longer terms, when each bad approval costs more and takes longer to show?
Answer: customer-level data improves risk ranking; a control group proves the NPV.
Add customer data to the score
Bureau data and Scalapay history rank risk better than the internal risk score alone: Gini 35 to 45.
Slide 6
Read each cohort in its first months
The first missed instalment shows the direction long before a 12-month loan matures.
Slides 4 and 7
Prove the NPV on a control group
Today's cutoff is already tight. A control group measures what approving more customers earns.
Slide 7
2
Risk grows Scalapay's total profit
6/9/12: the first product built on the customer view
Customer-level data sharpens each decision at checkout. A control group shows where approving more pays, and whether the term itself adds risk. We read each cohort in its first months.
Scalability
Every product and market reuses one view of each customer, so each launch starts from what we already know.
Performance
Every rule, data source and provider keeps proving its worth, or we remove it.
One view of each customer
Assumption to verify: one credit limit per customer, shared by all products
Judge each decision and each customer by their expected NPV.
3
The score ranks risk overall, but not in order in the middle
Missed rate by score decile (10 = lowest risk)
8.1% vs 3.3%
Decile 4 misses 2.4 times as often as the safer-looking decile 5.
7.9% vs 3.4%
Decile 6 misses 2.3 times as often as decile 7.
A third of orders sit in deciles 4 to 7.
The book is too young to show losses: 83% of orders are under two months old, and 72 are in default. So we analyse loans through the first missed instalment, at the same loan age for every plan.
Something the score may not fully incorporate drives this risk (slide 5).
Missed: first instalment after checkout overdue or paid 15+ days late. 5,385 orders with a score reached it by 23 Sep 2026.
4
The opportunity: incorporating more customer-level data
Bureau: depth of credit history
4.6% vs 1.2%
Same score (decile 9): customers the bureau does not find miss 4 times as often as customers it finds.
The number of credit lines alone ranks risk almost as well as the score.
Scalapay: plans already open
8.6% vs 2.7%
Orders placed while another Scalapay plan is open miss 3.1 times as often. They miss more in every score band.
The score places these orders only a little lower.
Both describe the customer, not the order: the base of one view of each customer.
Missed: first instalment after checkout overdue or paid 15+ days late. Bureau: decile 9, 1,199 orders. Open plans: 5,385 orders with a score.
5
Customer data ranks risk better than the score alone
Proof of concept: a scorecard built on top of today's score, adding bureau data and Scalapay history.
Ranking power (Gini), on customers the model never saw
Scorecard: +10 points (95% range +4 to +17). Holds out of time: 26 to 45.
56 vs 48
misses caught of 172 at a 10% decline rate: the scorecard catches 17% more.
5.6% vs 8.8%
Orders only the scorecard declines miss 1.6 times as often as orders only the score declines.
Today's cutoff is already tight: the value is in approving more customers safely.
Declining more loses NPV for every model tested on this data. A control group beyond the risk frontier can measure what approving more earns.
Proof of concept: points scorecard, 5,385 orders with a score, 172 missed. 5-fold, each customer in one fold.
6
Grow 6/9/12 with a learning budget and stop rules
How each rollout learns
A learning budget
Mature products fund the learning on 6/9/12. Risk and the business agree its size.
A control group
Tests the scorecard, and whether the term adds risk. Also tests new data for thin files.
Stop rules
Each rollout has a warning level (mitigate) and a limit level (pause). The risk appetite sets both.
AI: an LLM does the first analysis of weak rules. An analyst then keeps, changes or removes each rule.
7
Roadmap for 6/9/12: the first four months
Compliance: the creditworthiness check is a legal duty; CCD II applies from 20 November 2026.
8
Where 6/9/12 leads: one view of each customer drives every decision
The customer
Sees their credit limit in real time, and how to raise it.
6/9/12: the first product built on it
Customer-level data sharpens every decision. A control group shows where to approve more.
Scalability
Every product, market and channel plugs into the same base.
Performance
Every rule and data source keeps proving its worth, or we remove it.
One view of each customer
One risk score per customer, updated on every significant event.
9
The customer side: what one view makes possible
Customers understand their credit
The customer sees their credit limit in real time, and what shapes it.
A reason to share data
The app shows how to raise the limit, for example by sharing bank data, and what sharing is worth.
An explanation on demand
We tell the customer everything we can within our regulatory duty: their situation and how to improve it.
First step: test open banking data on a subset of our customers. If it performs, we productise and incentivise sharing data directly in the app.
10
The 12-month plan misses more, at every score
Missed first instalment, by score band and plan
1.6×
At the same score, a 12-month order is 1.6 times as likely to miss.
Same score: 3.9% of 12-month orders miss, against 2.4% on 6. Months 1-2 only.
57-71%
of orders in deciles 1-3 are on 12 months. Decile 10: 44%.
The merchant mix does not explain it
Plan or customer? A random term offer on the control group will tell us.
A lower payment does not make 12 safer: at the same score and budget, it misses 1.9 times as often.
Part of the gap: 8% of orders come while another plan is open. 84% of them are on 12, and they miss 3 times as often.
Missed: first instalment after checkout overdue or paid 15+ days late. 5,507 orders, cutoff 23 Sep 2026.
11
Backup: the rating R1-R9 does not rank risk
Missed rate by rating R1-R9
0.6%
10.7%
20.0%
n=60, thin
1.1%
R1
R2
R3
R4
R5
R6
R7
R8
R9
Purple: ratings that break the order (R5, R8)
Missed: first instalment after checkout overdue or paid 15+ days late. 5,507 orders reached it by 23 Sep 2026.
12
Backup: one test we would run, terms by risk
| Score band | 6 months | 9 months | 12 months |
|---|---|---|---|
| Safest | Offered | Offered | Offered |
| Middle | Offered | Offered | Not offered |
| Riskiest | Offered | Not offered | Not offered |
Illustrative grid. Tests set the bands and cutoffs.
1
The risk grid sets the terms shown
The customer sees only the terms their band allows.
2
Affordability caps the payment
In the data, a higher payment against income predicts misses.
3
The limit caps exposure
Limit minus existing debt. New customers start low and grow.
Assumptions to verify
1. One limit per customer, and 6/9/12 draws on it.
2. We can vary the terms shown at checkout. If not: a stricter cutoff on 12, then offer 6 after a decline.
Question for the room
What must be true for a term restriction to make money?
13
Backup: merchant tiers on healthy volume
| Merchant | Volume (EUR k) | Refunded | Missed (n) | Healthy volume |
|---|---|---|---|---|
| M1 | 347 | 3.0% | 0.0% (23) | 95.9% |
| M2 | 338 | 16.0% | 8.7% (298) | 79.9% |
| M3 | 332 | 0.7% | 3.4% (58) | 97.3% |
| M4 | 319 | 5.3% | 1.9% (53) | 93.4% |
| M5 | 270 | 2.2% | 5.2% (173) | 95.0% |
| M6 | 260 | 4.8% | 3.2% (126) | 93.4% |
| M7 | 255 | 0.0% | 0.0% (49) | 99.3% |
| M8 | 245 | 0.4% | 3.7% (109) | 97.5% |
| M9 | 228 | 0.0% | 3.9% (102) | 97.8% |
| M10 | 203 | 1.4% | 0.8% (132) | 97.9% |
Why tiers
The top 10 merchants hold 25.5% of volume. A 10% gain on them adds about 2.5% to the whole book.
How tiers work
Group merchants by healthy volume. Tune 6/9/12 policy per tier, not per merchant.
Healthy volume
Volume minus refunds minus expected loss. Book: 94.0%.
Top 10 merchants by volume. Healthy volume assumes 60% of misses do not cure (illustrative).
14
Backup: data detail
Orders with a missed instalment, by plan (n)
| Months after checkout | 6 months | 9 months | 12 months |
|---|---|---|---|
| Month 1 | 2.1% (1,956) | 2.1% (817) | 3.8% (3,028) |
| Month 2 | 3.7% (630) | 3.3% (181) | 6.5% (749) |
| Month 3 | 7.3% (273) | 2.6% (77) | 5.3% (300) |
| Month 4 | 6.1% (82) | n under 30 | 5.7% (70) |
After month 2, only the April-June cohorts remain. The 12-month gap cannot be confirmed there.
Affordability
Bigger baskets for the income miss more: 2.0% at a payment of 4% of income, 3.1% at 12%. Tighter budgets choose 12 only a little more: 48%, 51%, 55%.
Several plans at once
8% of orders come while another plan is open. 84% of them are on 12, and they miss 3 times as often.
Refunds
Orders 30+ days old: about 8% refunded on 12, about 4% on 6, in every score band.
15