Sending the same product email to every subscriber is one of the fastest ways to lose their attention. Shoppers expect relevance now, and generic blasts don’t deliver it. Klaviyo product recommendations fix this by surfacing the right products for each individual, based on real behavior and purchase data.
This guide walks you through how Klaviyo’s recommendation engine works, how to set it up inside your email flows, and how to measure whether it’s moving revenue.
Summary
- What Klaviyo’s product recommendation engine does and how it pulls data from Shopify
- The five types of recommendation blocks and when to use each
- A step-by-step Klaviyo product recommendations setup guide for email templates
- Strategic placement across flows like abandoned cart, post-purchase, and welcome
- Advanced personalization techniques including segmentation and A/B testing
- Metrics to track and common mistakes to avoid
How Klaviyo Product Recommendations Actually Work
Klaviyo pulls live product data directly from your connected ecommerce store—most commonly Shopify—and uses it to populate recommendation blocks dynamically inside emails. Each subscriber sees a different set of products based on their own activity.
The data Klaviyo draws from includes browsing history, past purchases, category affinity, price point patterns, and product interaction events. This means two subscribers who open the same campaign email can see completely different product suggestions without you manually building separate templates.
The Data Sync Between Shopify and Klaviyo
For recommendations to work accurately, your Shopify catalog needs to sync properly with Klaviyo. Product titles, images, prices, inventory status, and URLs all flow into Klaviyo’s product feed. If your catalog data is incomplete or inconsistently structured, recommendations will break or show outdated information.
Before building any recommendation block, verify that your Klaviyo–Shopify integration is active, your product feed is updating in real time, and all product images and variant data are pulling correctly.
| Data Point | Why It Matters for Recommendations |
| Purchase history | Identifies categories and price ranges a customer prefers |
| Browsing events | Surfaces recently viewed or considered products |
| Category affinity | Groups interest by product type, not just individual items |
| Inventory status | Prevents recommending out-of-stock products |
| Product tags | Enables filtered or curated recommendation blocks |
The Five Types of Klaviyo Recommendation Blocks
Klaviyo offers multiple recommendation block types, each serving a different intent. Choosing the right one for the right context is what separates a high-performing email from a generic one.
Recently Viewed Products
Shows items a subscriber browsed but did not buy. Best used in browse abandonment and re-engagement flows, where the goal is to bring someone back to a product they already considered.
Best Sellers
Displays your top-performing products by sales volume. Ideal for welcome sequences and cold audiences who have little to no purchase history. Since there’s no behavioral data yet, best sellers act as a reliable fallback.
Predicted Next Purchase (AI-Powered)
Klaviyo’s machine learning model analyzes purchase patterns to predict what a customer is likely to buy next. This is the most powerful block for post-purchase flows and loyalty campaigns. It performs best on customers with at least one prior order.
Category Affinity
Recommends products from categories a customer has shown repeated interest in. Useful when you want to broaden a customer’s exposure within a category they already engage with, without repeating exact products they’ve seen.
Custom Collections
Lets you manually curate a product set and display it as a recommendation block. Useful for seasonal campaigns, new arrivals, or brand partnerships where you want editorial control over what appears.
| Block Type | Best Use Case | Data Required |
| Recently Viewed | Browse abandonment, retargeting | Browsing events |
| Best Sellers | Welcome series, new subscribers | Store-wide sales data |
| Predicted Next Purchase | Post-purchase, VIP flows | Prior purchase history |
| Category Affinity | Replenishment, cross-sell | Category interaction data |
| Custom Collections | Seasonal, curated campaigns | Manual setup |
Klaviyo Product Recommendations Setup Guide: Step by Step
This section covers the core setup process inside Klaviyo’s email template editor. Following this Klaviyo product recommendations setup guide will get you from zero to a working recommendation block in under an hour.
Step 1: Confirm Your Catalog Integration
Go to Klaviyo > Integrations and confirm your Shopify (or other platform) connection is active. Navigate to the catalog section and verify that your products are populating correctly with images, prices, and URLs intact.
Step 2: Open Your Email Template
Inside the Flows or Campaigns editor, open the email template you want to add recommendations to. Klaviyo’s drag-and-drop builder includes a “Product” block in the content panel on the left.
Step 3: Add the Recommendation Block
Drag the product block into your email layout. Click to configure it and select your recommendation type from the dropdown: Recently Viewed, Best Sellers, Predicted Next Purchase, Category Affinity, or Custom Collection.
Step 4: Configure Display Settings
Set how many products to display—three to four is standard for most email layouts. Choose between grid, carousel, or list format. Match the typography, button styles, and spacing to your brand’s existing email design.
Step 5: Set a Fallback Option
Not every subscriber will have enough behavioral data to populate a personalized block, especially new contacts. Set a fallback block—typically Best Sellers or a curated collection—so the email still displays products if personalized data is unavailable.
Step 6: Preview Across Profiles
Use Klaviyo’s preview function and switch between customer profiles to confirm that different subscribers are seeing different products. Test with a new subscriber, a returning buyer, and an existing VIP to check all fallback and personalized scenarios.
Where to Place Product Recommendations in Email Flows
Knowing where to place recommendations is as important as knowing which type to use. The flows below are where personalized product blocks drive the most measurable lift.
Abandoned Cart Emails
Include a complementary product recommendation block below the cart recovery CTA. The goal here is not to distract from the primary action (completing the cart) but to add a secondary hook in case the original items no longer appeal.
Post-Purchase Sequences
This is the strongest use case for Predicted Next Purchase blocks. Once a customer has bought, Klaviyo has enough data to make a meaningful AI-driven suggestion. Send a follow-up 3–5 days after delivery with a “you might also like” block.
Browse Abandonment Flows
Use the Recently Viewed block as the centerpiece. Show the exact product they browsed, followed by similar items from the same category. This works well with a low-friction CTA like “pick up where you left off.”
Welcome Series
New subscribers have no purchase history, so use Best Sellers in the first two emails. As they engage and browse, transition to category-affinity blocks in later emails within the same series.
Re-Engagement Campaigns
For inactive subscribers, surface trending products from categories they’ve previously shown interest in. Pair the block with a subject line that emphasizes what’s new since they last visited.
Advanced Personalization Techniques
Once basic recommendation blocks are live, these tactics push performance further.
Segment-Based Recommendation Logic
Create customer segments by lifetime value, purchase frequency, or average order value (AOV). High-LTV customers can receive premium product recommendations, while first-time buyers see entry-level options. Klaviyo’s conditional content blocks make this possible within a single template.
A/B Testing Recommendation Types
Run A/B tests to compare the click-through and conversion rates of different block types. A common test is Predicted Next Purchase vs. Category Affinity for post-purchase emails. Let data decide which drives more attributed revenue.
| Test Variable | What to Measure |
| Block type (AI vs. Category) | Click-through rate, revenue per email |
| Number of products shown | Engagement rate |
| Layout (grid vs. carousel) | Mobile click rate |
| Placement (middle vs. bottom) | Overall conversion rate |
Metrics That Tell You If It’s Working
Revenue per recipient (RPR) is the most direct metric for recommendation performance. Compare RPR for emails with recommendation blocks against those without. Beyond that, track click-through rate on the recommendation block specifically, attributed conversion rate from recommendation clicks, and AOV from orders that included a recommended product.
Personalized recommendation emails typically generate 2–3x higher click rates than static product emails. AOV improvements of 20–35% are common in post-purchase flows once AI-based recommendations have sufficient data.
Common Mistakes to Avoid
- Skipping the fallback setup. New subscribers will see an empty block without a fallback, which breaks the email layout.
- Using the same block type across every flow. Best Sellers in a post-purchase email wastes an opportunity for AI-driven suggestions. Match block type to flow intent.
- Not testing across subscriber profiles. Recommendations can fail for specific customer segments. Always test across multiple profile types before activating a flow.
- Ignoring catalog data quality. Klaviyo can only recommend what it can read. Vague product titles, missing images, or incorrect prices in the feed will surface directly in your emails.
Key Takeaways
- Klaviyo product recommendations pull live catalog and behavioral data to show each subscriber a personalized product set inside your emails.
- Match the block type to the flow: Best Sellers for new subscribers, Predicted Next Purchase for returning buyers, Recently Viewed for browse abandonment.
- Always configure a fallback product block so new or low-data subscribers still see relevant content.
- Segment your audience before deploying recommendations at scale to avoid showing premium products to price-sensitive segments and vice versa.
- Track revenue per recipient and AOV as the primary indicators of recommendation performance, not just open or click rates.
Conclusion
Most ecommerce brands send the same products to every subscriber and wonder why click rates stay flat. The right Klaviyo product recommendations setup eliminates that problem by making every email feel individually relevant. Whether you’re targeting new subscribers with bestsellers or returning buyers with AI-driven suggestions, the key is matching the block type to the context and letting real behavioral data do the work.
Ready to move beyond static email templates? Talk to Folio3’s Shopify email marketing team to get started. You can also explore our Shopify Flodesk Integration guide and Shopify mobile optimization best practices to make sure your email traffic converts once it reaches your store.
Frequently Asked Questions
What Are Klaviyo Product Recommendations?
Klaviyo product recommendations are dynamic content blocks inside email templates that automatically display products tailored to each subscriber’s browsing history, purchase behavior, or category affinity—without manual curation per send.
Do Klaviyo Product Recommendations Work Without Shopify?
Yes. Klaviyo integrates with BigCommerce, WooCommerce, Magento, and other platforms. Shopify offers the deepest native integration with real-time event tracking, but recommendations function across all supported catalogs.
How Many Products Should I Show in a Recommendation Block?
Three to four products is the standard for most email layouts. More than four tends to overwhelm mobile readers and reduce individual product click rates. For carousel formats, up to six can work if product images are strong.
Can I Control Which Products Appear in Recommendations?
Yes. Custom Collection blocks give you full editorial control. For AI-driven blocks like Predicted Next Purchase, you can filter by product tags, collections, or price ranges to prevent specific items from surfacing.
How Long Does It Take for Klaviyo Recommendations to Become Accurate?
AI-powered blocks like Predicted Next Purchase improve in accuracy as purchase and browsing data accumulates. For most stores, meaningful personalization begins after a customer has two or more interactions with the catalog.
What Is the Difference Between Category Affinity and Predicted Next Purchase?
Category Affinity recommends products from categories a customer has browsed frequently. Predicted Next Purchase uses machine learning to forecast what a customer will buy based on sequential purchase patterns. The latter is more precise but requires more behavioral data.
