Upload a touchpoint log and get the same conversions split six ways — last touch, first touch, linear, position-based, time-decay and a Markov removal effect — plus a straight answer on whether your channel ranking is stable or flips. Free.
Free analyses run on up to 10,000 rows. Larger files are randomly sampled to that size — sign up to analyze your full dataset.
Splitting credit across attribution models...
Sent to — credited conversions per channel under six models, the full credit matrix with ranks, the Markov removal effect, a model-disagreement table, R code, and AI insights.
Analyze another fileEach converting journey is rebuilt as an ordered path of channel touches, and one conversion of credit is split along that path six ways: all to the last touch, all to the first touch, evenly (linear), 40/20/40 across opener, middle and closer (position-based), exponentially weighted toward the closer with a 7-period half-life (time-decay), and by the Markov removal effect — a first-order transition matrix over channel states plus start, conversion and null absorbing states, where each channel's credit is proportional to the drop in conversion probability when that channel is deleted from the graph. The six credit vectors are then ranked and compared, so the report can say whether the channel ordering is stable or model-dependent.
Use it when several channels touch the same journeys and you need to know how much of your channel ranking is a property of the data rather than of the attribution rule your reporting uses.
Not a substitute for an incrementality test — none of these models measures causal lift. Not useful when every journey has a single touch (all six models collapse to the same answer), when you have fewer than 30 journeys, or when the touches of a journey cannot be put in order.
Built for: Marketers, growth leads and analysts who own channel budget and report on conversions
Typical data source: A touchpoint / click-path export from an ad platform, CRM, or web analytics tool — one row per touch
A touchpoint log — one row per touch on a customer journey:
Minimum 60 rows · Best with 500-10,000 touch rows, 200+ journeys, 3-10 channels
Standard-library analysis: every channel that touched a converting journey claims the same conversion — this splits the credit six ways and shows you whether your channel ranking survives the choice of model. Last touch, first touch, linear, position-based (40/20/40), time-decay, and a Markov removal effect computed from your own path transitions, side by side. Works on any touchpoint log: map a journey id, a channel, a touch order (date or step number), and a converted flag.
The same conversions split six different ways — channels whose bars change height between models are the ones your model choice is deciding.
Credited conversions and rank per channel under every model, so you can see at a glance which rankings hold and which move.
How much conversion probability disappears when each channel is removed from the path graph — the data-driven counterweight to the fixed-rule models.
The gap between each channel's most and least generous model — the direct cost, in conversions, of the attribution rule you use today.
Plain-English interpretation — what the numbers mean, what's significant, and what to do next.
Does my channel ranking survive the attribution model?
Map your touchpoint log. The tool splits every conversion six ways and tells you whether the same channel wins each time — or whether your budget decision is really being made by the model your reporting happens to use.
See our FAQ for details on pricing, data privacy, and how the analysis works. Every report includes a Methodology section showing the statistical test, assumptions checked, and diagnostics run.
Run any analysis on your own data — validated R analyses, interactive reports, AI insights, and PDF export.
Try Free — No Credit CardTell us what went wrong, in your own words. We capture the page you're on automatically, so no need to describe where you are.