Abstract
The development of machine learning models within data warehouses can present challenges, as it may depend on the manual authoring of complex structured query language (SQL) statements. A disclosed technology relates to a visually-guided workflow for managing the machine learning model lifecycle. A graphical user interface can guide a user through processes such as dataset selection, feature configuration, and model training. A SQL synthesizer layer can translate these visual inputs into executable SQL statements. A model definition registry can also store persistent, versioned blueprints of a model's configuration as shareable resources. This approach may simplify the end-to-end process of model development, training, and deployment within a data warehouse environment, potentially improving the accessibility of in-warehouse machine learning for a broader range of users.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Nigro, Leonardo, "Unified Visual Workflow for Managing the Machine Learning Model Lifecycle in a Data Warehouse", Technical Disclosure Commons, (October 26, 2026)
https://www.tdcommons.org/dpubs_series/12418