Adaptive · cost / incremental buyer
45,198₫Ratio of all 24-run totals · inspect both components
SIMULATION ON SYNTHETIC DATA / CMS-2
An adaptive action × timing × touchpoint, measured against people who receive no follow-up.
Adaptive · cost / incremental buyer
45,198₫Ratio of all 24-run totals · inspect both components
Adaptive conversion
26.9%Fixed conversion: 28.3% · primary seed
Synthetic trialists
12,00011697 eligible · 3 disjoint experiment arms
Outreach suppressed
2,401Consent, purpose or frequency gate · existing buyers counted separately
Fixed: 28.3% conversion, 3,185,282₫ follow-up / 1,000. Adaptive: 26.9% conversion, 809,918₫ follow-up / 1,000.
Adaptive conversion is lower across the reported repeated-seed range. Adaptive uses less follow-up cost per 1,000 trialists across the reported range.
A programme may fall back to redemptions because it never recruited enough trialists to measure incremental buyers.
Planner requirement: 3,463 / arm, including 15% attrition.
This primary seed resolves positive adaptive lift over hold-out; compare conversion and cost directly against fixed before deciding.
Planner requirement: 3,463 / arm, including 15% attrition.
This primary seed does not resolve positive adaptive lift over hold-out; more sample alone does not fix a weak policy or small effect.
Both sizes use the same response model and unit costs, equal 10,000₫ redemption budget per assigned trialist, overlapping intent signals and weak equal priors. The plan sizes conversion against hold-out, not a difference between two unstable cost ratios.
Equal 10,000₫ coupon budget per assigned trialist, charged on redemption. No simulator reservations.
| Arm | Trialists | Surveys sent | Coupons issued / redeemed | Nothing sent | Coupon budget used / allocated |
|---|---|---|---|---|---|
| holdout | 3900 | 0 | 0 / 0 | 3900Budget-suppressed: 0 | 0₫ / 39,000,000₫ |
| fixed | 3900 | 870 | 3523 / 1012 | 377Budget-suppressed: 0 | 10,120,000₫ / 39,000,000₫ |
| adaptive | 3897 | 155 | 1144 / 299 | 857Budget-suppressed: 0 | 1,820,000₫ / 38,970,000₫ |
Fixed: survey when incomplete and a survey-capable channel is consented, followed by a coupon. Voucher-only permission permits the coupon but cannot carry the questionnaire. Recent frequency caps delay this sequence within the 30-day window; withdrawal and missing purpose/channel permission suppress it. Adaptive still chooses one next step, not a full repeated journey.
A coupon is useful only when it changes a purchase.
Pack size, intent,
channel permission
Action × timing
× touchpoint
Rules + a second
model review
The engine must learn which action and timing are worth their cost. Intent is noisy, some surveys are absent, and cold-start exploration can lose buyers. Keep a random hold-out and compare conversion as well as cost.
Seeded simulator · six feedback waves
Adaptive conversion is lower across the reported repeated-seed range. Adaptive uses less follow-up cost per 1,000 trialists across the reported range.
24 seeds per cohort · costs and buyers normalized to 1,000 trialists · empirical 2.5th–97.5th percentile component ranges
| Cohort / policy | Follow-up cost / 1,000 | Incremental buyers / 1,000 | Cost / incremental buyer |
|---|---|---|---|
| Main · fixed24 / 24 runs retained | 3,265,495₫3,151,199₫–3,363,879₫ | 43.131 to 57.5 | 75,806₫54,834₫–108,445₫ · component envelope |
| Main · adaptive24 / 24 runs retained | 812,294₫734,623₫–881,017₫ | 18-2.2 to 38.5 | 45,198₫Unbounded across the component range; see cost and buyers separately. |
| Underpowered · fixed24 / 24 runs retained | 3,237,651₫3,069,622₫–3,445,069₫ | 45.82.9 to 72.1 | 70,691₫42,552₫–1,182,161₫ · component envelope |
| Underpowered · adaptive24 / 24 runs retained | 670,947₫608,760₫–742,918₫ | 18.3-19.3 to 41.8 | 36,619₫Unbounded across the component range; see cost and buyers separately. |
-2,453,200₫ follow-up cost / 1,000Paired range: -2,609,789₫ to -2,280,058₫
-25.1 additional buyers / 1,000Paired range: -38.5 to -10.1
Adaptive conversion is lower across the reported repeated-seed range. Adaptive uses less follow-up cost per 1,000 trialists across the reported range.
-2,566,704₫ follow-up cost / 1,000Paired range: -2,798,746₫ to -2,351,606₫
-27.5 additional buyers / 1,000Paired range: -63 to 1.2
The repeated-seed range does not establish a conversion advantage for either policy. Adaptive uses less follow-up cost per 1,000 trialists across the reported range.
Cost per incremental buyer = sum of cost across all runs / sum of incremental buyers across all runs. Zero and negative-lift runs remain in both sums. A ratio range is unbounded when its incremental-buyer component range reaches zero; the component envelope is not a calibrated 95% confidence interval. These are simulated repeatability ranges, not real-world results.