See the relationships every other attribution tool misses.
NodeNarrative models the journey as a knowledge graph, so the relationships between touchpoints survive the maths.
Built for agencies, merchants, data teams and freelancers.
10 places · 40% off for 12 months · launching when our connector approvals clear
By subscribing you agree to our Privacy Policy. Unsubscribe at any time.
Connects with your stack
Relationships become numbers you can defend.
The graph above carries numbers. Scored by Shapley values, the same journey pays out very differently: the touch that opens the journey takes the largest share, and last-click gave it 0.00, because it never closes anything.
All seven models run on the same graph. First-Click · Last-Click · Linear · U-Shaped · Time-Decay · Shapley Values · Markov Chain
Shapley Values
Imagine removing one channel from every possible journey combination. The average change in conversion rate across all those combinations is that channel’s Shapley value, its true marginal contribution to the outcome.
Markov Chain
The model maps all observed journeys as transition probabilities between channels. It then removes each channel one at a time and measures the drop in overall conversion rate, the "removal effect". A larger drop means a more critical channel.
Deterministic, not generative
Every number above comes from deterministic ML and Bayesian methods computed over the knowledge graph, never from a generative or token-derived model. A number produced by a deterministic model can't be hallucinated, it can only be recomputed and checked.
- meta.paid
- klaviyo
- direct
The five dimensions are what the platform reports for every channel. Attribution and position come from the journey above; the other three are illustrative. The comparison is between the shapes rather than any value on an axis.
Two channels can earn the same credit and be nothing alike.
The first touch of that journey and the last one score within a few points of each other on attribution. On the other four dimensions they are opposites: one is wide, early and slow, and starts most of the journeys it appears in. The other is narrow, late, and starts almost none of them.
Judge them on the attribution column alone and you cannot tell them apart, so the channel that opens journeys looks like the one that closes them. NodeNarrative reports all five per channel, which is what makes the difference visible before you cut the wrong one.
10 places · 40% off for 12 months · launching when our connector approvals clear
Privacy by Architecture, Not by Policy
Every competitor treats privacy as a compliance checkbox buried in their footer. We built it into the knowledge graph. A full consent banner ships with the pixel, two of these capabilities are unique to NodeNarrative, and our cookieless mode works without fingerprinting.
Consent-per-identifier
Every identifier in your customer graph carries its own consent status. Email consent is tracked separately from cookie consent and device identifiers. Attribution models only use consented data paths.
GDPR cascading erasure
When a customer exercises their right to be forgotten, deletion cascades through every connected touchpoint in the graph automatically. No manual cleanup, no orphaned records.
Cookieless by default
Full attribution accuracy without any cookies. No fingerprinting, no workarounds. First-party server-side collection with graph-based identity resolution.
- GDPR compliant
- CCPA compliant
- Automatic PII detection
- Consent banner included
- No fingerprinting
Founding Partner Offer
40% off for 12 months, for the first 10 stores.
Any plan, locked at that rate. Founding partners shape the roadmap by talking directly to the person building it, and keep the discount when we launch.
Ready to see the whole picture?
See which channels are doing the work your last-click report cannot see.
10 places · 40% off for 12 months · launching when our connector approvals clear
By subscribing you agree to our Privacy Policy. Unsubscribe at any time.