Automated machine learning pipeline exploration and deployment

A system comprising:

• a first one or more electronic devices to implement a cloud object storage service of a cloud provider network, the cloud object storage service to store a comma separated values (CSV) file at a storage location;
• and
• a second one or more electronic devices to implement a machine learning (ML) service of the cloud provider network, the ML service including instructions that upon execution cause the ML service to:
• receive, via use of one or more graphical user interfaces (GUIs) presented by a computing device:
• an identifier or selection of the CSV file, wherein the CSV file provides a tabular dataset, including data values arranged via a plurality of columns, to be used for automated machine learning pipeline generation, and
• a user-selected column from the plurality of columns of the CSV file, wherein the user-selected column indicates which column is to be predicted;
• determine, based on at least some of the data values and the user-selected column, a prediction type;
• select one or more ML algorithms based at least in part on use of the determined prediction type;
• generate a plurality of candidate ML model pipelines based at least in part on use of the tabular dataset, the generation including a training of multiple candidate ML models based on the selected one or more ML algorithms;
• and
• cause results associated with the training of the multiple candidate ML model pipelines to be presented via the one or more GUIs, the results including values of an objective metric for the multiple candidate ML model pipelines.

A non-transitory computer readable storage media storing instructions which, when executed by one or more processors of one or more computing devices, cause the one or more computing devices to implement an automated learning system in a cloud provider network that performs operations comprising:

• receiving, via use of one or more graphical user interfaces (GUIs) presented by a computing device:
• a comma-separated values (CSV) file or an identifier of the CSV file, wherein the CSV file provides a tabular dataset, including data values arranged via a plurality of columns, to be used for automated machine learning pipeline generation, and
• a user-selected column from the plurality of columns of the CSV file, wherein the user-selected column indicates which column is to be predicted;
• determining, based on at least some of the data values and the user-selected column, a prediction type;
• selecting one or more ML algorithms based at least in part on use of the determined prediction type;
• generating a plurality of candidate ML model pipelines based at least in part on use of the tabular dataset, the generating comprising training multiple candidate ML models based on the selected one or more ML algorithms;
• and
• causing results associated with the training of the multiple candidate ML model pipelines to be presented via the one or more GUIs, the results including values of an objective metric for the multiple candidate ML model pipelines.