Personalized Recommendation
Trains and deploys a machine learning model over a website visitor's browsing history and item attributes, and serves next-item, similar-item, smart-search and user-affinity recommendations from it over a REST API.
Personalized Recommendation trains a machine learning model on a visitor's browsing history and an item's attributes, then calls that model to answer four kinds of request: next-item recommendations for what a user is likely to pick next, similar-item recommendations for alternatives to what is being viewed, smart-search results that personalise a text query with interaction history and categorical features, and user-affinity recommendations reflecting a user's past interactions. SAP calls it "a generic reusable service" meant to apply "across a wide range of business scenarios". SAP removed it from the list of Eligible Cloud Services as of 1 April 2026 and it is not available for renewal; SAP directs existing users to their account manager and points to a SAP Community post on Tabular AI.
Where it sits
Who is behind it
In the atlas: maintains 137, wrote 14@SAPmaintainer
What it declares
Every artifact
- Type
- Service
- Origin
- By SAP
As a service
- Plans
- 2
- Regions
- 15
- Support component
- CA-ML-PR
Connections
Training, deploying and calling predictive models on tabular data
Download
What’s New
from SAP Help Portal, readService Removal
Scenario Parameters for Offline Next-Item Recommendations
Overall Improvements
Overall Improvements
Support for X.509 Authentication
Overall Improvements
Offline (Scenario) Recommendations
Offline (Scenario) Recommendations
Overall Improvements
Overall Improvements
Complementary Next-Item Recommendations
Inference Options - Exclude Past Items and Ratings
SAP Business Accelerator Hub
Overall Improvements
Overall Improvements
Overall Improvements
Content-based Recommendations to Enhance Onboarding Experience
Overall Improvements
Tutorials
ML Explainability
Accessibility Features
Overall Improvements
Others providing
Compare all 2 on the Predictive models page →- Data Attribute RecommendationData Attribute RecommendationTrains and deploys machine learning models that classify records such as products or users into categories and predict a missing numerical attribute from free text, numbers and categories, over a REST API.sap official, btpML models that classify records and predict attributes
Details
Sources
Sources are graph entities: the same page may back several entries, and an unreachable source flags every row that rests on it.
Compatibility and provenance
History in the atlas
- First seen.
For your agent
- Ref
artifact:btp-personalized-recommendation- JSON
- /artifacts/btp-personalized-recommendation.json
- MCP
- Connecting an agent