How to choose more suitably the personalized product recommendation feature between Intelligent Selling Services for SAP Commerce Cloud and SAP Emarsys Customer Engagement Web Recommender?
Personalized product recommendations driven by AI not only enhance customer experience but also reduce total cost of ownership & increase revenue for enterprises. As both Intelligent Selling Services (ISS) for SAP Commerce Cloud and SAP Emarsys Customer Engagement (SAP Emarsys) Web Recommender provide this intuitive feature, the question rises: how to choose more suitably? The below table shows the differences by recommendation logic, placement on websites and configurable methods.
|ISS for SAP Commerce Cloud logic name||ISS for SAP Commerce Cloud logic notes||Suggested placement||SAP Emarsys logic name||SAP Emarsys logic notes||Suggested placement|
|Trending Products||Logic defined by Influencer List e.g.Frequently-ordered products, underperforming products||
|No equivalent out-of-box logic, yet having similar feature with extensibility via Email channel through Relational Data/ Personalization rules||This can be defined further by the client using their own Relational Data template/token or custom product filter||N/A|
|Related Products||Depending on user exploration patterns, recommendations typically show alternative products and, to a lesser extent, complementary products.||-Product Page||RELATED||RELATED reacts to visitor interest in a specific product by offering a selection of related or similar items calculated based on product views by other visitors. It will be the quickest to learn, and will be ready to use in live operation within a matter of days.||Best practice for RELATED is in the top scroll zone, near the original product image being viewed.|
|Personalized Products||1-to-1 personalized products based on their browsing history. Notes for displaying: If you can’t see the products and the title of a carousel when adding Intelligent Selling Services product carousel to the page, it means that there are no product views captured by Intelligent Selling Services. The empty carousel component is still editable.||
-Search Results Page
|HOME or PERSONAL||1-to-1 personalized products based on their browsing history. Notes for displaying: HOME will not display products that have already been viewed or purchased by the visitor.In the case of unknown visitors (first-time visit), HOME will simply display most trending product categories and products.||
HOME: on home page.
PERSONAL: can act as a replacement for HOME on a home page that’s limited in available screen real-estate. It can also be used as a secondary widget on category pages, and in general, on all pages where no dedicated widgets are used.
|Complementary Products||It determines the products most frequently bought together in the store by using deep learning to analyze previous purchases of the users.||
|ALSO_BOUGHT||It works exclusively from purchase data, it is our “slow learner” logic， because it can only establish the ALSO_BOUGHT relationship when different customers purchased the same product together with another one at least 3 times. Furthermore, it may not always return recommendations.||On the bottom of the product page, below the product details block.|
|/||/||/||CART||CART reacts to a visitor’s strong interest in one or multiple products by offering a selection of complementary items, calculated based on purchases made by other visitors.||Best practice is to display a CART widget below the list of cart contents, before the delivery or purchase options block (if any).|
|Recently Viewed Products||Recommendations of up to 25 user’s last viewed products.This recommendation doesn’t show different variants of the same product. For example, if the user views three colors of the same product, the recently viewed products list shows only the last color of this product.||
|/||/||/||CATEGORY||It reacts to a visitor’s interest in the current category, so it takes trending products from the category and combines this information with the visitor’s known personal browsing behavior to offer best-matching items from the category.||On top of the category listing, highlighting best-matching items from the list that follows.|
|/||/||/||DEPARTMENT||It guesses the product categories that are most likely to interest the visitor based on past browsing behavior, suggesting relevant subcategories and listing personally relevant and trending products within each of these categories.It will not display products that have already been viewed or purchased by the visitor.||Best practice is to display multiple widgets inserted between existing top category page content.|
|/||/||/||SEARCH||It reacts to the search term, looking up the product catalog to find items that match. It will also take into consideration the information available about the visitor’s recent browsing interest to offer best matching items.||Best practice is to display the SEARCH widget on top of the search results page, highlighting best matching items from the list that follows.|
|/||/||/||POPULAR||A simple list of top-selling products. This list is determined based on views instead of sales data, so the top-selling items are the most frequently viewed ones.||On category pages as an optional complement to the CATEGORY recommender|
Both with reporting capability to track the performance & outcomes, ISS for SAP Commerce Cloud has more flexibility in recommendation rule settings like the “Trending Products” logic on Web channel while SAP Emarsys offers out-of-the-box Web recommender logics yet with personalization capability in more channels like the Personalization Rules/Relational Data feature in Email channel. However, there are still other factors can be taken into the choosing decision like performance check, other features including in the same license package and etc., which can be explored further. If you have any question/feedback, you can simply drop a comment to this blog post and I’d be happy to get in touch with you soon!
An overview of Emarsys Web Recommender logics
Types of recommendations on ISS for SAP Commerce Cloud