Learn

How to A/B test a Shopify store

To A/B test a Shopify store: pick one page with steady traffic, write one clear change (headline, offer or product page section), split visitors between it and your current page with an app or Shopify Rollouts, count real orders per version, and run until each version has enough visits to trust the result.

Updated October 28, 2026 by Baneet Singh, founder of Luria.

1. Pick the page

Start with the product pages and home page that get most of your traffic. A page with fewer than a few thousand visits a month will take a long time to give an answer.

2. Pick one change worth testing

Test the things that change a buyer's mind: the headline and first screen, the offer (bundle, free shipping threshold, guarantee), reviews placement, the product page photo order. One change per test so you know what worked. See what to test first.

3. Choose how to run it

• Shopify Rollouts: free, native, tests a whole theme or checkout setting on eligible plans. Good for redesigns. (Rollouts vs testing apps.)
• A testing app you run: Intelligems, Shoplift or Visually let you build section, price and template tests.
• Done-for-you: Luria writes the version, runs the test and keeps the winner. See Shopify A/B testing apps compared.

4. Track real orders

Make sure each order is tied to the version the shopper saw. On Shopify that means a web pixel plus order webhooks, not a click on Add to cart. Refunds and cancelled orders should come out of the count.

5. Run it long enough

Run at least one full week and until each version has the visits your conversion rate needs (sample size table). Do not change prices, ads or the theme in the middle of a test.

6. Read the result and keep going

Keep the winner only if it beats your current page with high certainty (95% is the usual bar). A tie is an answer too: keep the simpler page and test a bigger change next.

Questions