Skip to main content
Domo Knowledge Base

AutoML Troubleshooting

Version 2



Automated machine learning (AutoML) is the process of automating the process of applying machine learning to real-world business problems. AutoML covers the complete pipeline from the raw dataset to the deployable machine learning model. AutoML was proposed as an artificial intelligence-based solution to the ever-growing challenge of applying machine learning. The high degree of automation in AutoML allows non-experts to make use of machine learning models and techniques without requiring becoming an expert in the field first.

Automating the process of applying machine learning end-to-end additionally offers the advantages of producing simpler solutions, faster creation of those solutions, and models that often outperform hand-designed models.

Domo and AWS: A partnership for success

AWS Partnership.png

We’re thrilled to announce that machine learning is now within everyone’s grasp with our new automated machine learning (AutoML) feature included in our data science suite. In partnership with Amazon SageMaker Autopilot, we’ve created AutoML capabilities that allow you to augment your analytics with machine learning, whether you’re a data scientist or a data science novice, the feature enables you to go from data to models to outcomes—faster, while creating astute data products for the enterprise.

Amazon SageMaker Autopilot is an Amazon Web Services (AWS) solution that automatically trains and tunes ML models based on data provided by a customer. Companies can now use their data in Domo as input into Amazon SageMaker Autopilot, automatically create the highest performing model and deploy a prediction pipeline that adapts to new, incoming data. The combination of Domo and Amazon SageMaker Autopilot helps make ML accessible to more employees and propels ML-driven insights for business.

Errors and Issues  

  1. AutoML training jobs or AutoML MagicETL tiles return uninformative errors.
    1. Try selecting the task (regression, multiclass classification, etc.) when training.
    2. Ensure that your DataSet doesn’t have a high percentage of null or missing values in any of the columns.
    3. Most often, these issues need to be evaluated by Product and a Support ticket should be created. Provide the DataSet or DataFlow URL.
  2. AutoML tile drops all columns including actuals column.
    1. This is a known issue on the immediate development roadmap to fix. In the meantime, you can join your predictions DataSet to the original DataSet to restore dropped columns.
    2. If you are still experiencing unexpected behavior. Please open a Support ticket or reach out to
  3. AutoML tile schema errors.
    1. Verify that your prediction schema matches your training schema.
    2. If you retrained your DataSet after deploying, there is a known issue where the AutoML tile is unable to update. A fix will be coming in the next release, in the meantime, you can train a copy of your DataSet and deploy that training job.
    3. For all other issues, please open a Support ticket so Development can investigate.
  4. If you are able to run autoML successfully but unsure of next steps or how to interpret metrics or values.
    1. Let us know what is unclear and what we can improve by emailing
    2. Engage with our qualified services teams for training and guidance.
    3. Learn more about the Data Science process by researching these articles:
      • Data Science Problem Definition (Coming Soon)
      • Data Cleaning for Supervised Learning (Coming Soon)
      • Best Practices in Deploying ML in Domo (Coming Soon)
  5. Anything else? Please reach out to