Decay half-life in time-decay attribution
In time-decay attribution, credit declines exponentially the further a touchpoint is from the conversion, and the half-life is the parameter that sets how fast. A touch one half-life before the conversion gets half the credit of one at conversion time; two half-lives back, a quarter. Choosing the half-life decides how strongly recency is rewarded — a model choice, not a measured fact.
What this means
Time-decay attribution weights each touch by an exponential function of how long before the conversion it occurred. The half-life is the period over which the weight halves. With a 7-day half-life, a touch seven days before the conversion carries half the weight of a touch at conversion time; fourteen days before, a quarter; and so on.
The half-life is the single dial that controls the curve's steepness. A short half-life concentrates credit on the final days; a long one spreads it more evenly toward a near-linear shape.
Choosing it well
The right half-life depends on the sales cycle. Short cycles, where the decisive activity is recent, justify a short half-life; long, considered purchases justify a longer one so that early-but-important touches keep meaningful weight. Some tools default to a 7-day half-life, but the default is a convention, not a law.
The key honesty point: the half-life is a model parameter you choose, so the resulting credit distribution reflects that choice as much as the data. Changing the half-life changes the answer without anything about the actual journeys changing — which is why time-decay results should be reported alongside the half-life used.
- Half-life = period over which credit halves
- Shorter half-life rewards recency more aggressively
- It is a chosen parameter, so report it with results
How it appears in analytics and logs
A steep drop in credit for older touches indicates a short half-life; a gentle slope indicates a long one. The slope reflects your parameter choice, not channel performance.
Diagnostic use case
Tune the decay half-life to match how strongly recency should count for your sales cycle, knowing it is a chosen parameter that shapes the credit curve.
What WebmasterID can help detect
WebmasterID's timestamped first-party touchpoints let you reason about how different half-life choices would redistribute credit across your own paths.
Common mistakes
- Reporting time-decay results without stating the half-life used.
- Using a short half-life on a long consideration cycle.
- Treating the decay curve as measured rather than chosen.
Privacy and accuracy notes
The half-life is a mathematical parameter applied to event timestamps. It involves no personal data beyond the timing of recorded touchpoints.
Related pages
- Time-decay attribution: recent touches weigh more
Time-decay attribution weights touchpoints by recency: the closer a touch is to the conversion, the more credit it earns, usually following an exponential decay with a configurable half-life. It is a compromise between last-click and linear, but its recency bias under-credits the early demand-creating touches.
- Conversion lag (time-to-conversion)
Conversion lag is the time between an interaction and the resulting conversion. Some conversions happen minutes after a click; others take days or weeks. Because of lag, recent activity always looks under-performing at first — conversions for recent touches have not happened yet — and the lookback window must be long enough to capture them. It is a core reason attribution reports change as data matures.
- Linear attribution: equal credit to every touch
Linear attribution divides a conversion's credit equally among all touchpoints in the path. It is the simplest multi-touch model: every touch matters the same. That even-handedness avoids the single-touch extremes, but it also pretends a fleeting impression and a decisive demo are worth the same — which is rarely true.
- Attribution analytics
Timestamped first-party touchpoints for decay reasoning.
Sources and verification notes
- Google Analytics Help — Time-decay attribution modelDocuments time-decay weighting with a default half-life convention.
Last reviewed 2026-06-24. Facts are checked against primary/official sources where available; uncertain specifics are marked “Data not yet verified” rather than guessed.