End-to-end user journey for each model

BigQuery ML supports a variety of machine learning models and a complete machine learning flow for each model, such as feature preprocessing, model creation, hyperparameter tuning, inference, evaluation, model export and so on. The machine learning flow for the models are split into the following two tables:

Model Creation Phase

Model Category Model Types Model Creation Feature Preprocessing Hyperparameter Tuning Model Weights Feature & Training Info Tutorials
Supervised Learning Linear & Logistic Regression create model Automatic preprocessing,
Manual preprocessing1
HP tuning2
ml.trial_info
ml.weights ml.feature_info
ml.training_info
Deep Neural Networks create model NA5 NA
Wide-and-Deep create model NA5 NA
Boosted Trees create model NA5 NA
AutoML Tables create model NA3 NA3 NA5 NA
Unsupervised Learning K-means create model Automatic preprocessing,
Manual preprocessing1
HP tuning2
ml.trial_info
ml.centroids ml.feature_info
ml.training_info
cluster bike stations
Matrix Factorization create model NA HP tuning2
ml.trial_info
ml.weights
PCA create model Automatic preprocessing,
Manual preprocessing1
NA ml.principal_
components
,
ml.principal_
component_info
NA
Autoencoder create model Automatic preprocessing,
Manual preprocessing1
NA NA5 NA
Time series models ARIMA+ create model Automatic preprocessing auto.ARIMA4 ml.arima_ coefficients ml.feature_info
ml.training_info
Imported Model Tensorflow Model create model Automatic preprocessing NA NA NA predict with imported model

1See TRANSFORM clause for the feature engineering tutorial.

2See use hyperparameter tuning to improve model performance tutorial.

3Automatic feature engineering and hyperparameter tuning are embedded in the AutoML Tables model training by default.

4The auto.ARIMA algorithm performs hyperparameter tuning for the trend module. Hyperparameter tuning is not supported for the entire modeling pipeline. See the modeling pipeline for more details.

5BigQuery ML doesn't support functions that retrieve the weights for Boosted Trees, DNNs, Wide-and-deep, Autoencoder, or AutoML Tables models. To see the weights of those models, you can export an existing model from BigQuery ML to Cloud Storage and then use the XGBoost library or the Tensorflow library to visualize the tree structure for the tree models or the graph structure for the neural networks. For more information, see the EXPORT MODEL syntax and the EXPORT MODEL tutorial.

Model Use Phase

Model Category Model Types Evaluation Inference AI Explanation Model Export Tutorials
Supervised Learning Linear & Logistic Regression ml.evaluate
ml.confusion_matrix1
ml.roc_curve2
ml.predict ml.explain_predict3
ml.global_explain
export model5
Deep Neural Networks NA
Wide-and-Deep NA
Boosted Trees ml.explain_predict3
ml.global_explain
ml.feature_importance4
NA
AutoML Tables NA NA
Unsupervised Learning K-means ml.evaluate ml.predict
ml.detect_anomalies
NA export model5 cluster bike stations
Matrix Factorization ml.recommend
PCA ml.predict NA
Autoencoder ml.predict
ml.detect_anomalies
ml.reconstruction_loss
NA
Time series models ARIMA+ ml.evaluate
ml.arima_evaluate6
ml.forecast
ml.detect_anomalies
ml.explain_forecast7 NA
Imported Model Tensorflow Model NA ml.predict NA export model5 predict with imported model

1ml.confusion_matrix is only applicable to classification models.

2ml.roc_curve is only applicable to binary classification models.

3ml.explain_predict is an extended version of ml.predict, see Explainable AI overview for more details.

4For the difference between ml.global_explain and ml.feature_importance, see Explainable AI overview.

5See the Export a BigQuery ML model for online prediction tutorial.

6ml.arima_evaluate is an extended version of ml.evaluate for ARIMA+.

7ml.explain_forecast is an extended version of ml.forecast, see Explainable AI overview for more details.