Classification overview

A common use case for machine learning is classifying new data by using a model trained on similar labeled data. For example, you might want to predict whether an email is spam, or whether a customer product review is positive, negative, or neutral.

You can use any of the following models in BigQuery ML to perform classification:

• Logistic regression models: use logistic regression by setting the MODEL_TYPE option to LOGISTIC_REG.
• Boosted tree models: use a gradient boosted decision tree by setting the MODEL_TYPE option to BOOSTED_TREE_CLASSIFIER.
• Random forest models: use a random forest by setting the MODEL_TYPE option to RANDOM_FOREST_CLASSIFIER.
• Deep neural network (DNN) models: use a neural network by setting the MODEL_TYPE option to DNN_CLASSIFIER.
• Wide & Deep models: use wide & deep learning by setting the MODEL_TYPE option to DNN_LINEAR_COMBINED_CLASSIFIER.
• AutoML models: use an AutoML classification model by setting the MODEL_TYPE option to AUTOML_CLASSIFIER.