AutoML Studio

Train, evaluate, and deploy machine learning models through a unified no-code interface.

​

Overview

AutoML is a Domino extension that enables data scientists and domain experts to build, evaluate, and deploy machine learning models through a streamlined, no-code interface. Powered by AutoGluon, AutoML automates the end-to-end model training pipeline - from data profiling and feature engineering through model selection, hyperparameter tuning, and ensembling - so you can go from raw data to a production-ready model in minutes. AutoML primarily provides a Model Training workflow. This allows you to configure and run an AutoGluon training job that automatically trains multiple model types, ranks them on a leaderboard, and produces deployment-ready artifacts. You can access AutoML from the left navigation sidebar of any Domino project under the Extensions section.

​

Get started

​

Prerequisites

• A Domino project with the AutoML extension enabled.
• A dataset in CSV or Parquet format stored in a Domino Dataset.
• Permission to launch Domino Jobs if you plan to train models or run Data Exploration as a Domino Job.

​

Installation

An administrator installs AutoML Studio from the Admin panel. See Install Domino Official Extensions. The AutoML_Extension repository holds the source and manual install instructions for reference.

​

Access AutoML

1. Navigate to your Domino project.
2. In the left sidebar, scroll down to the Extensions section.
3. Click AutoML.

The AutoML landing page displays all existing training jobs. From here you can start a new training job.

​

AutoML model training

AutoML model training uses AutoGluon to automatically train, tune, and rank multiple machine learning models. The training job wizard guides you through four steps: selecting your data source, choosing a model type, configuring training parameters, and reviewing your settings before launch. To begin, click New training job from the AutoML landing page.

​

Step 1: Select a data source

Select a file in the dataset you want to use for training. Once your file is loaded, click Continue to proceed. You can also click the shortcut in the dataset picker to open the project’s Domino Dataset area in a new browser tab so you can upload files before starting the run.

​

Step 2: Select a model type

Choose the AutoGluon predictor that best fits your use case. Two model types are currently available: Problem Type (Optional) For tabular jobs, AutoGluon can auto-detect the problem type from your target column, but you can also specify it explicitly: Click Continue to proceed to configuration.

​

Step 3: Configure training

The configuration step lets you define your training job’s name, target column, and AutoGluon-specific settings.

​

Basic configuration

For time series jobs, this step also includes:

• Time Column: The timestamp field used to order observations.
• ID Column (optional): A grouping key for multi-series forecasting.
• Prediction Length: The forecast horizon.

​

AutoGluon settings

​

Advanced configuration

Click Advanced Configuration to access fine-grained controls for AutoGluon training.

​

Step 4: Review and launch

Review all your selected settings on the summary screen. If everything looks correct, click Start Training to launch the job. You are taken to the training run’s overview page where you can monitor progress in real time.

​

Training results

Once a training job is launched, its results page provides comprehensive information about the run’s progress and outputs.

​

Data exploration

Accessible via the dataset link in the Training Results view, the Data Exploration tool lets you analyze data quality, distributions, and correlations, and prepare transformations for subsequent model training. Data Preview The Data Preview tab shows a sample of your raw data in table format. You can browse columns and rows to get a quick sense of the dataset’s structure and values. If your dataset is large or takes a long time to profile, you can re-profile the data with a Domino Job using the Execution dropdown. Column Analysis The Column Analysis tab provides detailed profiling information for each column in your dataset. Correlations The Correlations tab displays a correlation matrix heatmap for all numeric columns in the dataset. Correlation values range from −1 (strong negative correlation) to +1 (strong positive correlation), with color coding to highlight the strength and direction of each relationship. Use the Min correlation slider to filter out weak correlations and focus on the strongest relationships. This view is helpful for identifying multicollinearity between features and understanding which variables are most associated with your target column. The UI also lists highly correlated column pairs below the matrix to help you quickly identify candidates for removal or further review. Data Quality The Data Quality tab gives you an at-a-glance assessment of your dataset’s readiness for model training. It includes the following sections:

• Missing Values by Column: A horizontal bar chart showing the number and percentage of missing values for each column that has any. Columns are color-coded by severity: green for less than 5% missing, orange for 5–20%, yellow for 20–50%, and red for more than 50%.
• Missing Value Pattern: A compact visual representation of where missing values occur across columns, helping you identify whether missingness is concentrated or scattered.
• Warnings: Issues that could affect training quality. For example, Small dataset – consider using best_quality preset for better results.
• Recommendations: Actionable suggestions to improve model performance. These are tagged by priority (high or medium) and category (Target, Preprocessing). Examples include:

Transformations The Transformations tab lets you define preprocessing steps that are applied to the dataset before model training. AutoML analyzes your data and suggests recommended transformations based on detected issues. Recommended transformations AutoML may recommend transformations for columns with the following issues:

• Identifier columns: Columns where all values are unique and are likely row identifiers (for example, PumpId). Recommended action: drop the column.
• High cardinality: Columns that may be identifiers due to a large number of unique values (for example, ManufacturerModel). Recommended action: review and potentially drop.
• Missing values: Columns with a significant percentage of null values (for example, OperatingYears at 19.9% missing). Recommended action: fill missing values.
• Extreme outliers: Numeric columns with extreme values detected (for example, FlowRatePSI with 6.9% outliers). Recommended action: clip or remove outliers.
• High missing rate: Columns with a high percentage of missing data (for example, WellSector at 77% missing). Recommended action: drop the column.

Transformations are included in the exported notebook and can be reviewed and modified in code.

​

Export a notebook

At any point during data exploration, you can click the Export Notebook button in the top-right corner to download a Jupyter notebook that contains all of your data profiling results and any transformations you have selected. This notebook can be opened in a Domino Workspace for further analysis or custom preprocessing.

​

Deploy a model

After training is complete, you can operationalize the best model from the Deployments tab in the Training Results view.

​

Register a model

To register your model in Domino’s Model Registry for versioning, governance, and deployment:

1. Open the completed training run.
2. Navigate to the Deployments tab.
3. In the Model Registry section, click Register Model and fill out the details.
4. Click Register to save the model to the registry.

Once registered, the model appears in Domino’s Model Registry and can be promoted into downstream deployment workflows.

​

Deploy a model API

After a model is registered:

1. In the Model API section of the Deployments tab, click the deploy link.
2. Complete the deployment dialog.

Once deployment finishes, the section shows the Model API status and, when available, a direct link back to Domino.

​

Best practices

• Review data quality for subsequent training. Use the Data Exploration tool to inspect missing values, outliers, and column types. Address high-priority recommendations (especially dropping or imputing columns with more than 30% missing data) before starting a training job.
• Use the dashboard to manage iteration cycles. Search, filter, and switch views on the AutoML landing page as your project accumulates runs. Bulk deletion is useful for clearing experimental jobs that are no longer relevant.
• Choose the right preset. The Medium Quality (Faster) preset is a good starting point for rapid iteration. Once you have identified a promising dataset and target, switch to Best Quality for production models, especially on smaller datasets where the additional training time yields meaningful improvements.
• Set an appropriate time limit. A longer time limit allows AutoGluon to train more models and explore more hyperparameter configurations. For initial exploration, 600–1800 seconds is often sufficient. For production runs, consider 3600 seconds or more.
• Exclude identifier columns. Columns with all unique values (flagged as identifiers) do not contribute meaningful signal and should be dropped before training. AutoML flags these in both Column Analysis and Recommended Transformations.
• Examine feature importance. After training, review the Feature Importance chart on the Diagnostics tab. If unimportant features dominate, consider removing them and retraining to reduce noise and improve generalization.
• Consider the prediction time trade-off. Ensemble models (for example, WeightedEnsemble_L2) typically achieve the best validation scores but may have higher inference latency. For real-time applications, compare leaderboard scores with prediction times and consider selecting a simpler model that meets your latency requirements.
• Use the exported notebook for reproducibility. Download the Training Notebook from the Outputs tab to preserve a complete record of your training configuration. This notebook can be re-run in a Domino Workspace and serves as the starting point for any custom modifications.
• Use the Deployments tab for operational follow-through. Register the model after a successful run, then create a Domino Model API from the same page when you are ready to serve predictions.