Deployed · cadence-pricedCertifiedPredict what's next
Conversion Propensity
“Which prospects or sessions are most likely to convert next?”
Every existing customer, scored and ranked on how likely they are to buy again within a defined window.
01
What you receive
Every prospect and session, ranked to convert
Visual placeholderRanked list · scoredEvery prospect and session, ranked to convert
Every prospect, session and open account, scored and ranked on how likely each is to complete the conversion you define, within a window you set. The full scored list is delivered to your data environment on release; the page carries the ranked, population-level shape. It scores the whole funnel, not only the leads in it.
02
The question it answers
Bring it in plain language.
- “Which trial accounts are most likely to convert to paid this month?
- “Which sessions are genuinely close to buying, not just browsing?
- “Who is going to convert anyway, and who actually needs the push?
What it does not do
- Explain why an individual scores high
- Claim causal or uplift effects
- Explain why aggregate conversion rates shifted between periods
- Attribute conversion credit to marketing channels or spend
- Show per-record scores in the app
Record-level activity events with dates, and the conversion event you want scored. Roughly two years of history. No modelling work on your side.
03
How it earns trust
Graded in the open, before you see it.
Proven on our published instrument. Re-certified on your data before anything releases.
Certified
Scores are certified out-of-time on your own history before anything ships — measured on records the model never saw, and refused below a data floor.
Trained on past, tested on future
The model is scored on rolling windows of your own history — trained on the past, tested on the future it hadn't seen.
Beats a baseline, and tracks reality
Ranking skill must beat a naive baseline and the scores must track observed frequency. The model earns its grade on both, or it doesn't publish.
Refused below the floor
Below a minimum of observed events, the run stops rather than certifies. A weak score is never shipped dressed as a strong one.
Rigour you can inspect is worth more than rigour you're asked to trust.
A deployed model, priced per brand on the page.See pricing →