What is BigQuery ML?

BigQuery ML (BQML) enables data analysts to create and execute machine learning models using standard SQL queries directly in BigQuery, without exporting data or using Python. Create a model: CREATE MODEL dataset.my_model OPTIONS(model_type='logistic_reg') AS SELECT label, feature1, feature2 FROM training_table;. Evaluate: SELECT * FROM ML.EVALUATE(MODEL dataset.my_model). Predict: SELECT * FROM ML.PREDICT(MODEL dataset.my_model, (SELECT ... FROM prediction_table)). Supported model types: logistic regression, linear regression, K-means clustering, matrix factorization, deep neural networks (via TensorFlow), XGBoost, and importing pre-trained models from Vertex AI. BQML democratizes ML — analysts who know SQL can train models on petabytes of data already in BigQuery without data engineering pipelines.