Recommendation engine
A recommendation engine is a system that suggests relevant products to customers based on their behavior, purchase history or similar customer preferences. It increases sales by making it easier for customers to find products they are interested in.
What is a recommendation engine?
A recommendation engine analyzes data on customer behavior and uses algorithms to suggest products that each customer is likely to be interested in. This is known from "You might also like..." or "Customers who bought this also bought..." on product pages and in emails.
Recommendation engines are responsible for a large portion of revenue in modern e-commerce. Amazon estimates that 35% of their sales are driven by product recommendations.
Types of recommendations
Collaborative filtering
Recommending products based on what similar customers have bought. "Customers who bought X also bought Y". Requires a certain volume of transactional data to work effectively.
Content-based filtering (content-based)
Recommends products with similar characteristics to those the customer has shown interest in. If a customer has looked at black running shoes, other black running shoes or sports shoes are displayed.
Popular-based recommendations
Shows the most popular or best-selling products. Simple but effective for new visitors where there is no personal data to build on.
Context-based recommendations
Recommend based on the current context - e.g. season, weather, time of day or the page the customer is on.
Where do recommendations appear?
- Product pages: "You might also like..." or "Others also bought..." below the product description.
- Cart/checkout: "Complete your purchase with..." - Perfect for accessories and complementary products.
- Front page: "Recommended products for you" for returning customers.
- Search results: Supplement search results with recommended products.
- Emails: Personalized product recommendations in newsletters and order confirmations.
- Abandoned cart emails: Show the products the customer abandoned plus related alternatives.
The impact of product recommendations
- Increased average order value (AOV): Customers who click on recommendations typically add more products to the cart.
- Better conversion rate: Relevant recommendations help customers find the right product faster.
- Increased engagement: Customers spend more time in the store and see more products.
- Improved customer experience: Personalization makes the store feel relevant and attentive.
Product recommendations in Shoporama
Shoporama supports product recommendations through Shoporama:
- Related products: You can manually associate related products via parent-child relationships.
- Landing pages: Dynamic product lists based on categories, labels and rules - acts as automated recommendations.
- Email recommendations: Shoporama's newsletter system has dedicated product blocks that display products from selected categories or landing pages.
- Order confirmation recommendations: Dedicated template for product recommendations in post-purchase emails.
Best practices
- Relevance over quantity: 3-4 relevant recommendations beats 20 random ones. Quality is more important than quantity.
- A/B test placement: Test whether recommendations perform best under the product description, in a sidebar, or after "Add to cart".
- Avoid recommending the same product: Don't show the product the customer already sees in the recommendations.
- Show images and prices: Product recommendations with images and prices convert significantly better than just text links.
We know online marketing in Shoporama
We've been working with online marketing ourselves for decades. As the only shop system in the country, we have spoken multiple times at conferences such as Marketingcamp, SEOday, Shopcamp, Digital Marketing, E-commerce Manager, Ecommerce Day, Web Analytics Wednesday and many more.