{"ref":"capability:predictive-models","page":"/capabilities/predictive-models","json":"/capabilities/predictive-models.json","generated":"2026-10-26","drafted_with_ai":true,"entity":{"id":"predictive-models","name":"Predictive models","domain":"ai-and-agents","ecosystems":["btp"],"universal":false,"description":"Training, deploying and calling a model that predicts a value from tabular business data: a classification, a regression, a forecast. Distinct from [LLM integration](capability:llm-integration), where a language model generates text, even where both run on the same service.","short":"Training, deploying and calling predictive models on tabular data","core_coverage":{"state":"core-only","assessed_at":"2026-09-14","what_core_does":"[SAP AI Core](artifact:btp-ai-core) runs training and batch inference as pipelines on Argo Workflows and deploys trained models through serving templates that follow the KServe specification and are kept in a git repository. SAP-RPT-1, deployed on AI Core, returns classification and regression predictions from context rows sent with the request, with no training step.","where_it_stops":"At the container for anything but SAP-RPT. AI Core runs the training code and model server packaged as a Docker image, reading training data from an object store the user supplies, so the model itself and its data preparation are the user's.","sources":[{"url":"https://raw.githubusercontent.com/SAP-docs/sap-artificial-intelligence/main/docs/sap-ai-core/what-is-sap-ai-core-d029a32.md","title":"SAP AI Core — What Is SAP AI Core?","checked":"2026-09-14","quote":"It integrates with Argo Workflow and KServe, and can be embedded into other applications."},{"url":"https://raw.githubusercontent.com/SAP-docs/sap-artificial-intelligence/main/docs/sap-ai-core/predictiveAI/serving-templates-20a8667.md","title":"SAP AI Core — Serving Templates","checked":"2026-09-14","quote":"Serving templates are stored in your git repository, where you can version them as required."},{"url":"https://raw.githubusercontent.com/SAP-docs/sap-artificial-intelligence/main/docs/sap-ai-core/generativeAI/sap-rpt-1-f128f5e.md","title":"SAP AI Core — SAP-RPT-1","checked":"2026-09-14","quote":"RPT-1 solves predictive tasks such as classification and regression out-of-the-box without requiring any training or fine-tuning via in-context learning."},{"url":"https://github.com/SAP-samples/ai-core-samples","title":"SAP-samples/ai-core-samples — README","checked":"2026-09-14","quote":"Please make sure that you have access to an Object Store like AWS and a place holder or directory structure created."}],"note":"SAP's managed services train on the customer's own data: [Data Attribute Recommendation](artifact:btp-data-attribute-recommendation) classifies records or predicts a missing numerical attribute, and [Personalized Recommendation](artifact:btp-personalized-recommendation) serves next-item and similar-item predictions from browsing history. SAP-samples notebooks, workflow templates and workshops demonstrate the AI Core path, and a sample runs the same kind of prediction in SAP Databricks inside [SAP Business Data Cloud](artifact:btp-business-data-cloud); that path is sourced only from its README."},"drafted_with_ai":true,"history":[{"date":"2026-10-26","field":"core_coverage.note","from":"The repositories answering this in the batch are SAP-samples notebooks, workflow templates and workshops, which demonstrate rather than provide, so core-only reads what [SAP AI Core](artifact:btp-ai-core) ships. One of them runs the same kind of prediction in SAP Databricks...","to":"SAP's managed services train on the customer's own data: Data Attribute Recommendation ..., Personalized Recommendation ... SAP-samples notebooks, workflow templates and workshops demonstrate the AI Core path, and a sample runs the same kind of prediction in SAP Databricks...","reason":"Reassessed against the graph (check:capabilities): the note explained the state by the batch it was written from and counted repositories; it now names the kinds of SAP service that have since arrived. The state stays core-only: both are sap-official services on the btp door."}]},"sap_delivery":{"door":"btp","all":{"built_in":[],"documented_pattern":[],"announced":[],"packages":[{"ref":"artifact:btp-data-attribute-recommendation","name":"Data Attribute Recommendation","json":"/artifacts/btp-data-attribute-recommendation.json"},{"ref":"artifact:btp-personalized-recommendation","name":"Personalized Recommendation","json":"/artifacts/btp-personalized-recommendation.json"}]},"by_flavor":{}},"edges":{"use_cases":[],"shared_tasks":[],"related_tasks":[],"options":[{"ref":"artifact:btp-data-attribute-recommendation","name":"Data Attribute Recommendation","json":"/artifacts/btp-data-attribute-recommendation.json","ecosystem":"btp","origin_ring":"sap-official"},{"ref":"artifact:btp-personalized-recommendation","name":"Personalized Recommendation","json":"/artifacts/btp-personalized-recommendation.json","ecosystem":"btp","origin_ring":"sap-official"}],"samples":[{"ref":"artifact:sap-samples-ai-core-samples","name":"ai-core-samples","json":"/artifacts/sap-samples-ai-core-samples.json"},{"ref":"artifact:sap-samples-aicore-multioutput-regression-restaurant-inspections","name":"aicore-multioutput-regression-restaurant-inspections","json":"/artifacts/sap-samples-aicore-multioutput-regression-restaurant-inspections.json"},{"ref":"artifact:sap-samples-analytics-cloud-rpt15-prediction-demo","name":"analytics-cloud-rpt15-prediction-demo","json":"/artifacts/sap-samples-analytics-cloud-rpt15-prediction-demo.json"},{"ref":"artifact:sap-samples-hana-apl-apis-runtimes","name":"hana-apl-apis-runtimes","json":"/artifacts/sap-samples-hana-apl-apis-runtimes.json"},{"ref":"artifact:sap-samples-hana-ml-samples","name":"hana-ml-samples","json":"/artifacts/sap-samples-hana-ml-samples.json"},{"ref":"artifact:sap-samples-sap-rpt-samples","name":"sap-rpt-samples","json":"/artifacts/sap-samples-sap-rpt-samples.json"},{"ref":"artifact:sap-samples-hana-ml-py-codejam","name":"SAP-samples/hana-ml-py-codejam","json":"/artifacts/sap-samples-hana-ml-py-codejam.json"},{"ref":"artifact:sap-samples-teched2023-da263","name":"teched2023-DA263","json":"/artifacts/sap-samples-teched2023-da263.json"},{"ref":"artifact:sap-samples-teched2025-da261","name":"teched2025-DA261","json":"/artifacts/sap-samples-teched2025-da261.json"},{"ref":"artifact:sap-samples-teched2025-da266","name":"teched2025-DA266","json":"/artifacts/sap-samples-teched2025-da266.json"}],"explained_by":[{"ref":"content:devtoberfest-2026-tabular-foundation-models","name":"Unlocking Tabular Foundation Models: From Experimentation to Production","json":"/content/devtoberfest-2026-tabular-foundation-models.json"},{"ref":"content:devtoberfest-2026-tabular-predictions-tabpfn","name":"How We Make Tabular Predictions in 2026 with TabPFN","json":"/content/devtoberfest-2026-tabular-predictions-tabpfn.json"},{"ref":"content:sap-rpt-1-5-is-now-generally-available-more-accurate-predictions-better-explaina","name":"SAP-RPT-1.5 Is Now Generally Available: More Accurate Predictions, Better Explainability, What's New","json":"/content/sap-rpt-1-5-is-now-generally-available-more-accurate-predictions-better-explaina.json"},{"ref":"content:ac-transforming-enterprise-data-strategy-with-sap-business-data-cloud","name":"Transforming Enterprise Data Strategy with SAP Business Data Cloud","json":"/content/ac-transforming-enterprise-data-strategy-with-sap-business-data-cloud.json"},{"ref":"content:decision-logic-modernization-in-sap-integrations-using-sap-rpt-1-for-intelligent","name":"Decision Logic Modernization in SAP Integrations: Using SAP-RPT-1 for Intelligent Routing Decisions","json":"/content/decision-logic-modernization-in-sap-integrations-using-sap-rpt-1-for-intelligent.json"},{"ref":"content:ac-federated-machine-learning-with-sap-datasphere","name":"Federated Machine Learning with SAP Datasphere","json":"/content/ac-federated-machine-learning-with-sap-datasphere.json"},{"ref":"content:teched-2026-da204","name":"Unlock predictive and generative AI with your data in SAP HANA Cloud","json":"/content/teched-2026-da204.json"},{"ref":"content:teched-2026-da262","name":"Get hands on with tabular AI and forecasting models in SAP HANA Cloud","json":"/content/teched-2026-da262.json"},{"ref":"content:teched-2026-ra162","name":"SAP-RPT and TabPFN: Get started with tabular foundation models","json":"/content/teched-2026-ra162.json"},{"ref":"content:teched-2026-st103","name":"Behind the Autonomous Enterprise: SAP Knowledge Graph and SAP Domain Models","json":"/content/teched-2026-st103.json"}],"normative_context":[]}}