A recommender type decides whether an anchor is required, what the anchor is, and
determines the general use cases available for applying a recommender on your storefront.
Each recommender configuration is one of five recommender types. The recommender type
determines which strategies are available when you configure the recommender. An
anchor provides context about the page where the recommender applies to Einstein.
As an example, a recommender type of Product to Product needs the context of the
product id of the page being viewed sent to Einstein. Einstein uses this context to
potentially recommend products based on the product that the shopper is viewing.
| Recommender Type |
Anchor |
Description |
| Product to Product |
product id |
Given a specific product, analyze the product's similarity to other products
or the viewing or purchasing behavior of other customers to generate
recommendations.
Storefronts typically place product-to-product recommendations on the:
- Product details page (PDP)
- Cart
- Mini-cart
- Wish-list
- Checkout
|
| Products in All Categories |
none |
Generate recommendations across all categories.
Storefronts typically place products-in-all-categories recommendations on
the:
- Home page
- My Account page
- My Recommendations page
- Cart
- Checkout
- Wishlist
|
| Products in a Category |
category id |
Given a specific category, generate recommendations for products that are in
the category.
Storefronts typically place products-in-a-category recommendations on the
category page.
|
| Recently Viewed |
none |
Generate recommendations by simply including products recently viewed by the
customer.
Storefronts can place recently viewed recommendations on any page.
|
| Complete the Set |
product id |
Recommends complementary items for apparel sets, home furnishings, and
cosmetic and beauty products. |