AutoML Tables uses AI to complete the data prep, feature engineering, model selection and hyperparameter tuning steps of a data science workflow. It allows your entire team to automatically build and deploy state-of-the-art machine learning models on structured data to predict numerical or categorical outcomes. Using this Block, Looker developers can add these advanced analytical capabilities right into new or existing Explores, no data scientists required.
Using this Block, you can integrate Looker with BigQuery ML and AutoML Tables to get the benefit of advanced analytics without needing to be an expert in data science. Start with your problem: What is the outcome you want to achieve? What kind of data is the target column? Depending on your answers, this Block will create an auto-classification or auto-regression model to solve your use case:
- A binary classification model predicts a binary outcome (one of two classes). Use this for yes or no questions, for example, predicting whether a customer will make a purchase.
- A multi-class classification model predicts one class from three or more discrete classes. Use this to categorize things, like segmenting defect types in a manufacturing process.
- A regression model predicts a continuous value. Use this to predict customer spend or future return rates.
This Block gives business users the ability to make predictions (categorical or numerical) from a new or existing Explore. Explores created with this Block can be used to create multiple classification and regression models, evaluate them, and access their predictions in dashboards or custom analyses.
Learn more in the associated AutoML Tables Beginner's Guide.
This Block can be installed via the Looker Marketplace.