Component Products" (also known as "Product Components" or "Item Components") is a product recommendation technique in which a product is broken down into its components or attributes, and then products that share the same components are recommended.

For example, if a customer has purchased a TV with specific characteristics, such as screen size, resolution, connectivity, among others, you can identify the components of that TV and use them to recommend other TVs with similar characteristics.

The recommendation based on component products is useful when you do not have information on the customer's brand or model preference, or when you want to recommend products from a specific category based on the desired features. It is also useful when you want to make a recommendation of substitute or complementary products, based on the components they share with the products already purchased or viewed by the customer.

Machine learning and data mining techniques are often used to identify and analyze product components, and to build recommendation models based on them.

When the recommendation of products is not given by analyzing the components or attributes of a product but by analyzing customer purchase history information to find patterns and similarities in their preferences, it is known as "collaborative filtering".