Adstock
A transformation that models marketing's lagged effect — exposure today drives conversions over many days, not just immediately.
Last updated: 2026-05-04
Definition
Adstock applies a decay function (Geometric or Weibull) to today's spend so the model sees the residual effect of past weeks. Geometric adstock has one parameter (decay rate) and an exponential decline; Weibull has two and can model an S-shaped delay (peak effect 2-5 days after exposure, then decay). Brand campaigns typically have longer half-lives (14-30 days) than performance campaigns (1-3 days). Without adstock the model attributes all of a campaign's lift to the day spend hit, which under-credits brand work.
How it applies in India
No India-specific behavior.
Frequently asked questions
Geometric vs Weibull adstock — which should I use?
Geometric is simpler + faster to fit. Use Weibull only when you have evidence of a delayed peak (typically TV / OOH / longer-consideration B2B). Performance channels (Meta / Google) almost always fit fine with Geometric.
Related terms
- Saturation CurveA transformation that models diminishing returns — doubling spend doesn't double conversions; the curve flattens.
- Marketing Mix Modeling (MMM)A statistical method that quantifies how each marketing channel contributes to a sales outcome over time, using historical spend + revenue + exogenous variables.
- Adstock Half-LifeThe number of days for an ad's effect to decay to 50% of its initial impact.
Try WatEase free
Run your WhatsApp commerce on the platform built for India — Cloud API, GST invoices, UPI checkout, opt-in tracking, and a Free Forever plan.
Start Free Today