Purchase Likelihood Targeting

Some visitors land on your site ready to buy. Others are just browsing. Right now, you can't tell the difference until they've already started acting, by which point you've missed your chance to shape their experience.

Likelihood to Purchase targeting changes that. It's a new audience, built from the moment a visitor lands, that estimates how likely they are to convert, before they've clicked, scrolled, or added anything to a cart.

What it is

Purchase Likelihood sorts every visitor into one of three tiers, relative to your own store's traffic:

Tier	Who's in it
Higher	Your top 20% of visitors, by predicted purchase probability
Medium	The middle 50%
Lower	The bottom 30%

These tiers are calculated against your traffic, not some global benchmark. A "Higher" visitor on your store is compared to your other visitors, not to visitors on a store with a completely different customer base or price point. That's what makes the tiers meaningful no matter what you sell or how your store typically converts.

A note on what these labels mean: they're relative, not absolute. A "Higher" visitor is more likely to buy than your other visitors, not necessarily likely to buy in any absolute sense. Depending on your store, even your top tier might convert in the single digits to around 10%. Treat the tiers as a ranking of your traffic, not a prediction that any individual visitor will or won't purchase.

Where you'll find it

Right now, Likelihood to Buy is available as a targeting audience, in both personalizations and tests:

• Eligibility, for deciding who can be included in a test or personalization based on their tier

• Group assignment in tests, where the tier can also help determine which test group a visitor sees by using Advanced targeting

• A results breakdown isn't available yet, but it's coming: an audience table showing metrics broken down by tier. It will only appear on tests that target at least one Purchase Likelihood bucket, so it won't clutter results for tests that don't use it.

Supported test types today: Merchandising, Shipping, Checkout, and Post-Purchase.

Not yet supported: Content and Pricing tests. If you're running one of those, Likelihood to Buy won't show up as a targeting option yet. Please let us know if this is something you are interested in.

What data it uses

Purchase Likelihood is built entirely from signals available the moment a visitor lands, so it never needs to wait and see how they behave:

• Device type — mobile, desktop, or tablet

• Country

• Whether it's their first visit to your store

• Referring source — where the visitor came from

• Landing page

• Day of week and time of day

• Your store's industry and sub-industry

• Your store's typical conversion rate and average order value

No scrolling, clicking, or cart activity required. Everything above is available at the instant a visitor arrives, which is what lets the tier be assigned on the first page view.

What to know before you start

• It's a signal, not a guarantee. A "Higher" visitor converts at a meaningfully higher rate than a "Lower" one, but it's still a probability, not a promise. Treat it the way you'd treat any other audience: a starting point for a hypothesis, not a certainty.

• It's built for testing, not for skipping testing. Use Likelihood to Buy to decide who sees a test, not to decide what the outcome will be. Let your results tell you whether a different experience for your Higher-tier visitors actually moves profit per visitor.

• It's in closed beta. Likelihood to Buy isn't generally available yet. See below for how to request access.

Try it

Likelihood to Purchase is currently in closed beta. If you'd like to be included, let us know here: Request access