Built for agencies · Refreshed before every QBR

From orders,
to tested wins.

Drop a client’s order history in. Affinsy mines the association rules, ranks the highest-revenue test hypotheses, and hands you the customer audience for each one, ready for Klaviyo, CSV, API, or MCP.

The new standard for CRO hypothesis generation.

Affinsy Mine: association rules ranked by lift, confidence, and revenue impact
How we get in · three moves

From a client’s CSV to a ranked test backlog, in two minutes.

Three moves from kickoff to QBR. No app install on the client’s store, no dev review, no analyst time burned on data prep.

client_orders.csv
100%
Auto-detected
order_idcustomer_idproduct_skuqty
01
Onboard

CSV upload or read-only API key. No app install on the client's store, no dev review, no IT ticket. You can have a dataset flowing before the kickoff call ends.

Hypothesis · #1 of 12Validated
Bundle Cleanser + Toner at PDP
Lift
2.3×
Confidence
78%
Audience
1,847
Expected uplift+$4.3k / 30d
02
Validate

Hypotheses come back ranked, each one scored against the client's actual orders. Expected lift, audience size, confidence band. Math you can defend without disclaimers, not gut calls dressed up as strategy.

Schedule · MonthlyAuto-rerun
Mar 2812 hypotheses
Apr 2818 hypotheses
May 28Queued
03
Repeat

Schedule the rerun. Every month a fresh batch of validated hypotheses lands automatically, so the next QBR is already half-written and your retainer compounds instead of resetting from a blank deck.

Inside the report

Everything else the report ships with.

The Mine, Hypothesize, and Activate panels above are the interactive surface. The report also packs an executive summary, a movers view showing what’s heating up versus cooling off, and product-level diagnostics so you walk into the meeting with the full picture.

Affinsy report — executive summary KPIs: total opportunity, missed orders, rule concentration, basket footprint
01 · Executive summary

The headline numbers, up front.

Total opportunity sized against current store revenue. Missed orders, rule concentration, basket footprint, and the confidence spread — all on the first page so the next conversation starts with what you're acting on.

Open on the live report
Affinsy report — biggest lift changes split into rising and falling rules
02 · Movers

What's heating up, what's cooling off.

Rules whose lift shifted by 10%+ versus the previous 30-day window, split into risers and fallers. Feature the rising ones before the trend matures, investigate the falling ones before retiring them — the temporal signal you don't get from a single-snapshot report.

Open on the live report
Affinsy report — product popularity table with sparkline trends, orders, buyers, revenue, rules
03 · Product popularity

Which products are pulling weight.

Every catalog item sorted by orders, with the number of rules it appears in, what it substitutes for, and a week-by-week trend sparkline. Useful for the moment a client asks why their best-seller stopped lifting the basket.

Open on the live report
Frequently asked

The questions we hear most.

How CRO and retention agencies (and the merchants we work with) typically use Affinsy. Quick, honest answers.

Still have a question? Email us
Affinsy is built for the way agencies actually work. Drop in a client’s order CSV (or wire it up via webhook/API on Agency) and within two minutes you get back ranked test hypotheses, each with the backing association rules and a customer audience for each. Walk into every QBR with a fresh, statistically-backed test backlog instead of rebuilding spreadsheets the night before. One dataset per client, rerun on your cadence.
Before the next QBR

Walk in with a ranked test backlog.

Drop a client’s order history in. Affinsy returns the rules, the hypotheses, and the audience for each one.

No credit card · Refreshed in under two minutes