As enterprises strive to harness the power of data, Machine Learning (ML) has emerged as a key technology for enabling intelligent automation and predictive insights. Within the SAP ecosystem, SAP Leonardo offers a comprehensive platform that integrates advanced machine learning capabilities with business processes. This guide walks you through the step-by-step process of working with Machine Learning models in SAP Leonardo, helping you understand how to build, deploy, and manage ML solutions that drive innovation.
SAP Leonardo is designed to make machine learning accessible and practical by embedding it into enterprise applications and workflows. It offers pre-built ML services, APIs, and tools that cover a wide range of use cases, from demand forecasting to image recognition.
The typical machine learning workflow in SAP Leonardo involves data preparation, model selection, training, evaluation, deployment, and monitoring — all supported by SAP’s Business Technology Platform (BTP).
Before diving into ML models, clearly define the business problem you want to solve. Examples include:
A well-defined use case guides data selection, model choice, and evaluation criteria.
Quality data is the foundation of any successful ML project. In SAP Leonardo, you typically gather data from:
Use SAP Data Intelligence or SAP HANA to cleanse, transform, and enrich your data. Ensure your dataset includes labeled examples if you are working with supervised learning models.
SAP Leonardo offers a range of pre-built machine learning models categorized by use case:
Alternatively, you can build custom models using SAP Leonardo’s integration with tools like TensorFlow or SAP Data Intelligence.
Training involves feeding your prepared data into the model to enable it to learn patterns. In SAP Leonardo:
The system will iterate over data until the model converges to an optimal performance.
Assess how well your model performs using standard metrics:
SAP Leonardo provides built-in tools and dashboards to visualize these metrics. If the model does not meet expectations, consider refining the dataset or tuning parameters.
Once satisfied with model performance:
ML models can degrade over time due to changing data patterns (concept drift). SAP Leonardo supports continuous monitoring:
This ongoing process ensures the model remains relevant and valuable.
Machine learning within SAP Leonardo empowers businesses to embed intelligence into everyday processes, driving efficiency and innovation. By following this step-by-step guide, SAP professionals can systematically approach ML model development — from identifying the right use case to deploying and refining intelligent applications. As SAP Leonardo evolves, integrating ML will become an essential capability for unlocking business transformation in the digital age.