Technology

BigQuery ML

Train and run machine learning models directly on your petabyte-scale data using standard GoogleSQL, eliminating data movement and democratizing AI.

BigQuery ML is the integrated machine learning service that empowers data analysts (SQL practitioners) to build, train, and evaluate models directly within the data warehouse: no Python or external ML frameworks required. You execute model creation and prediction using simple GoogleSQL statements, like `CREATE MODEL` and `ML.PREDICT`. This approach keeps your data in BigQuery, accelerating development and model iteration for core use cases like Linear Regression, K-Means Clustering, and Time Series forecasting (ARIMA). For advanced needs, it integrates seamlessly with Vertex AI, allowing for MLOps management and access to powerful remote models like DNNs and Boosted Trees.