Amazon SageMaker Autopilot
Automatically create machine learning models with full visibility
Amazon SageMaker Autopilot automatically builds, trains, and tunes the best machine learning models based on your data, while allowing you to maintain full control and visibility.
Building machine learning (ML) models requires you to manually prepare features, test multiple algorithms, and optimize hundreds of model parameters in order to find the best model for your data. However, this approach requires deep ML expertise. If you don’t have that expertise, you could use an automated approach (AutoML), but AutoML approaches typically provide very little visibility into the impact of your features for model predictions. As a result, you may have less trust in it because you can’t recreate it and you can’t learn how it makes predictions.
Amazon SageMaker Autopilot eliminates the heavy lifting of building ML models, and helps you automatically build, train, and tune the best ML model based on your data. With SageMaker Autopilot, you simply provide a tabular dataset and select the target column to predict, which can be a number (such as a house price, called regression), or a category (such as spam/not spam, called classification). SageMaker Autopilot will automatically explore different solutions to find the best model. You then can directly deploy the model to production with just one click, or iterate on the recommended solutions with Amazon SageMaker Studio to further improve the model quality.
How it works
Generate high quality models quickly
Amazon SageMaker Autopilot automatically identifies the best ML model for your data by optimizing hundreds of ML models and parameters. After an initial set of iterations, SageMaker Autopilot creates a leaderboard of models, ranked by performance, within SageMaker Studio. You can see which features in your data each model used and deploy the one that you feel is best suited to your use case.
Once Amazon SageMaker Autopilot automatically builds, trains, and tunes the best ML model based on your data, you can easily deploy your model into production with a single click. You can start making predictions by querying your model endpoint using REST API calls. You can also monitor your deployed model using Amazon SageMaker Model Monitor.
Maintain visibility and control
Generating models is completely transparent. You can automatically generate the Amazon SageMaker Studio Notebook for any model Amazon SageMaker Autopilot creates. Then you can dive into the details of how it was created, refine it as desired, and recreate it from the notebook at any point in the future.
Amazon SageMaker offers a comprehensive set of security features including encryption, private network connectivity, authorization, authentication, monitoring, and auditability, so your organization can meet the strict security requirements of machine learning workloads.
Automatic data pre-processing and feature engineering
You can use Amazon SageMaker Autopilot even when you have missing data. SageMaker Autopilot automatically fills in the missing data, provides statistical insights about columns in your dataset, and automatically extracts information from non-numeric columns, such as date and time information from timestamps.
Automatic ML model selection
Amazon SageMaker Autopilot automatically infers the type of predictions that best suit your data, such as binary classification, multi-class classification, or regression. SageMaker Autopilot then explores high-performing algorithms such as gradient boosting decision tree, feedforward deep neural networks, and logistic regression, and trains and optimizes hundreds of models based on these algorithms to find the model that best fits your data.
Amazon SageMaker Autopilot allows you to review all the ML models that are automatically generated for your data. You can view the list of models, ranked by metrics such as accuracy, precision, recall, and area under the curve (AUC), review model details such as the impact of features on predictions, and deploy the model that is best suited to your use case.
Automatic notebook creation
You can automatically generate a Amazon SageMaker Studio Notebook for any model Amazon SageMaker Autopilot creates and dive into the details of how it was created, refine it as desired, and recreate it from the notebook at any point in the future.
Easy integration with your applications
You can use the Amazon SageMaker Autopilot application programming interface (API) to easily create models and make inferences right from your applications, such as your data analytics and data warehousing tools.
Price prediction models are used heavily in financial services, real estate, and energy and utilities to predict the price of stocks, real estate, and natural resources. Amazon SageMaker Autopilot can predict future prices to help you make sound investment decisions based on your historical data such as demand, seasonal trends, and price of other commodities.
Customer churn is the loss of customers or clients, and every company looks for ways to eliminate it. Models automatically generated by Amazon SageMaker Autopilot help you understand churn patterns. Churn prediction models work by first learning patterns in your existing data and identifying patterns in new datasets so you can get a prediction about customers mostly likely to churn.
Risk assessment requires identifying and analyzing potential events that may negatively impact individuals, assets, and your company. Models automatically generated by Amazon SageMaker Autopilot predict risks as new events unfold. Risk assessment models are trained using your existing datasets so you can get optimized predictions for your business.
“Previously, we would simply pick two restaurants that looked similar, but now we have a true understanding of the relationships between our menu items, customers, and locations. Amazon SageMaker Autopilot, which powers Domo’s new ML capability, has been a force multiplier for our marketing and purchasing teams to try new ideas and improve our customers’ experience.”
Sean Thompson, IT Director, Freddy’s
"Sisense’s new ML service powered by Amazon SageMaker Autopilot was exactly what we needed to keep ahead of the curve in customer service during this COVID-19 pandemic. Skullcandy was able to gain deep insights into our customers’ needs, improve our issue resolution, and increase customer satisfaction scores."
Mark Hopkins, Chief Information Officer, Skullcandy Inc.
"The primary goal in demographic mapping is optimizing across both accuracy and scale. While this is generally difficult, we were able to use Amazon SageMaker Autopilot with our comprehensive training data and sophisticated features to produce better models that improved our prediction accuracy by 137%."
Anindya Datta, CEO, Mobilewalla