Reviewing SAP Data Attribute Recommendation

This lesson introduces how the service manages training data, deploys ML models, classifies or predicts data attributes at scale, and supports multitenant applications—helping organizations automate data maintenance and improve data accuracy.

Data Attribute Recommendation applies machine learning to predict and classify data records.

Data Attribute Recommendation uses free text, numbers and categories as input to classify entities such as products, stores and users into multiple classes and also to predict the value of missing numerical attributes in your data records. You can use Data Attribute Recommendation, for example, to classify incoming product information and predict the price of commodities based on their description.

With Data Attribute Recommendation you can:

• Automate and speed up data management processes
• Reduce errors and manual efforts in data maintenance
• Increase data consistency and accuracy

• Manage training data
  • Perform tasks related to the dataset that will be used to train the machine learning model.
• Manage machine learning model
• Perform tasks related to the machine learning model that will be used to classify entities and predict the missing attributes in your data records.
• Classify data records
  • Classify data records by specifying which deployed machine learning model should be used.
• Predict data records
  • Predict the value of missing numerical attributes in your data records by specifying which deployed machine learning model should be used.
• Benefit from multitenancy support
  • Use this service in tenant-aware (multitenant) applications. Run them on a shared compute unit that can be used by multiple consumers (tenants).

This service is available in the following environments:

• Cloud Foundry environment

• Kyma environment

This service supports multitenancy. It can be used in tenant-aware applications. For information on multitenancy support, see Run the Service in a Multitenant Application.

Data Attribute Recommendation consists of the following applications:

• Data Manager: Manages training data, for example, training upload and deletion

• Model Manager: Manages machine learning models, for example, model creation, deployment and deletion

• Inference: Classifies entities or predicts the missing attributes in your data records

Take a look at possible use cases for Data Attribute Recommendation:

• Get suggestions of material class and its characteristics when creating new material requests
• Get international trade commodity code predictions when adding a new product
• Solve master data inconsistencies
• Obtain a price estimation for a product based on its description

Get an overview on the availability of Data Attribute Recommendation according to region, infrastructure provider, and release status in the SAP Discovery Center.

• Data Attribute Recommendation uses machine learning to classify entities (e.g., products, stores, users) based on text, numbers, and categories. It predicts missing numerical data attributes, automating data management, reducing errors, and improving consistency and accuracy in datasets.
• The key features are managing training data and machine learning models for classification and prediction tasks.
• The applications and use cases are applicable in scenarios like material classification, supplier data enrichment, price estimation, spend harmonization, BOM classification, contract metadata prediction, and material master cleanup in systems like SAP Ariba Procurement and SAP Spend Management.
• The benefits include enhancing efficiency in procurement and data management processes, reducing manual workload, ensuring data quality, predicting key attributes, and supporting seamless integration in multitenant environments like Cloud Foundry and Kyma.