MLCOST-13: Use automated machine learning

Use automated data analyzer systems when building a model. These systems experiment with and select the best algorithm from the list of high-performing algorithms. They automatically test different solutions and parameter settings to achieve optimal models. The automated system speeds up the process, while eliminating manual experimentation and comparisons.

Implementation plan

• Use Amazon SageMaker Autopilot - Amazon SageMaker Autopilot automates key tasks of an automatic machine learning (AutoML) process. Autopilot explores your data, selects the algorithms relevant to your problem type, and prepares the data to facilitate model training and tuning. Autopilot applies a cross-validation resampling procedure automatically to all candidate algorithms. It tests the ability of these algorithms to predict using data they have not been trained on. It ranks all of the optimized models tested by their performance. Autopilot finds the best performing model that you can deploy at a fraction of the time normally required.

Blogs

• Amazon SageMaker Autopilot – Automatically Create High-Quality Machine Learning Models with Full Control and Visibility

• Customizing and reusing models generated by Amazon SageMakerAutopilot

Videos

• Automatically Build, Train, and Tune ML Models with Amazon SageMaker Autopilot

• Use Autopilot to automate and explore the machine learning process

Examples

• Customer Churn Prediction with Amazon SageMaker Autopilot

• SageMaker Autopilot