The Frequently Bought Together algorithm is an AI algorithm that looks at each customer’s purchase history. It finds items that are often bought together. It is commonly used in e-commerce to suggest complementary products to customers.
Use this algorithm to recommend items often purchased with a specific product. This not only personalizes the shopping experience but also enhances opportunities for up-selling and cross-selling, ultimately boosting revenue.
How does it work?
The algorithm analyzes customers' purchase histories to find patterns of frequently bought products. It uses artificial intelligence techniques to find patterns, and then it gives recommendations that the customer intends to buy together. Techniques include association rule mining, collaborative filtering, and clustering.
Supported Rule Types
- Global
- Home Page
- Product
- Cart
AI Algorithm Context Awareness
The widget changes based on input parameters.
If you don't provide product IDs, it will show recommendations based on your recent views. To rank the recommendations, we'll observe how customers behave during their session. You will provide the products that will form the basis of the FBT recommendations.
Customers' likelihood to buy them will determine the rankings of the recommendations. To figure this out, we look at how customers behave when they buy products you share with the AI algorithm. Remember to always pass the user ID to the AI algorithm.
Note: You always need to pass the user ID to the AI algorithm.
Recommended Placements
While you can add this widget to any page, we recommend the following placements for it:
- Product Page: Items Frequently Bought Together for this product
- Cart: Item Frequently Bought Together for products in the cart
- Home: You can recommend products on the home page, like Customer Also Bought (generic).
Behavior for Non-Logged-in User
FBT: Behavior for Home Page, Category, Product, Search, Cart, Checkout or Pages
- The system gives FBT widget recommendations if the user has interacted with products. The context-awareness logic generates the recommendations.
- If the user is brand new and has not browsed any products,
- If “FALLBACK” is not enabled, hide the widget when users are not logged in.
- If the user is on the product page, you will see suggestions for getting started with the product.
- If the user is on the home page, it will not show any suggestions because there is no browsing history.
- If you enable the "FALLBACK" algorithm, a widget will display alternative algorithm products.
- If the user is on the product page, you'll see suggestions to get started with the product. Users can use the fallback button to fill in empty spots.
- When the user is on the home page and has no browsing history, suggestions will not be available. Instead, Fallback will show the products to help with the cold-start problem.
Behavior for Logged-in User
FBT: Behavior for Home Page, Category, Product, Search, Cart, Checkout or Pages
- Suppose the user has had some interactions in the session. If that happens, the system will recommend products that the FBT widget has viewed. The context-awareness logic forms the basis for the suggestions.
- If the user is brand new and has not browsed any products,
- If “FALLBACK” is not enabled, hide the widget when users are not logged in.
- On the product page, users will find suggestions to help them get started with the product.
- If the user is on the home page, it will not show any suggestions because there is no browsing history.
- If you enable the "FALLBACK" algorithm, it will display a widget with fallback algorithm products.
- On the product page, users will see suggestions for getting started with the product. They can use the fallback button to fill in empty spots.
- When the user is on the home page, there are no suggestions due to the absence of browsing history. Instead, we will only display products from Fallback to address the cold-start problem.
When should you use this algorithm?
This algorithm helps e-commerce businesses boost sales by suggesting related products to customers.
Businesses that sell products that complement each other or are used together are more likely to be successful. The algorithm checks what other items someone bought with a laptop online. You might find that many of them also bought a laptop bag and a wireless mouse. The algorithm recommends these items to customers, making them more likely to buy more.
Example
Here is an example of how the Frequently Bought Together algorithm could be used in Experro
- A shopper visits an e-commerce website and views a product page for a chair.
- Experro uses the Frequently Bought Together algorithm, which analyzes items frequently purchased with chairs to identify popular products.
- The algorithm can tell that people who purchase chairs also buy side chair, chest chair, bar chair, dining side chair, and other types of chairs. This increases the chance of more purchases and improves satisfaction.
- It displays a list of Frequently Bought Together products for the shopper on the product page.
To create or learn more about widgets, go to our Widget Configurator article and get started.