Analysts, data scientists, and developers can manage the features, target and algorithms attempted for their dataset via Auger’s easy to use model manager.

How to use AutoML?

  1. Create a new experiment.
  2. Select a data source for your business problem. It can be in the form of CSVs, time-series, etc. AutoML automatically infers the type of ML problem, classification, or regression.
  3. AutoML pre-processes the data and lists all the features with their respective statistics. Choose the features you wish to include in the training. Also, select the target class in case of a classification problem.
  4. Set training configurations, such as a number of trials, ML algorithms, values of hyperparameters, etc. Default values work just as well for your convenience.
  5. Hit “Run” to initiate training. AutoML trains various ML models, searching across a number of algorithms and hyperparameters and comes up with a summary of best performing models with their respective performance metrics. Choose the model of your choice to download and deploy as an endpoint.

If Accuracy Doesn’t Matter, You Don’t Need Machine Learning. Just Guess!

In this example we ran Auger against other leading AutoML tools using Microsoft’s own 89 datasets chosen to highlight their accuracy. Auger’s error rate on these difficult classification problems was less than 20%, reducing errors from Azure and Google’s AutoML by more than 20%. On more representative datasets the advantage is larger.

How the Auger Automated Machine Learning process works.


The user provides structured data via CSV files or relational databases.


They identify the target and contributing features and Auger determines whether it's a regression, classification or time series experiment.


Auger then preprocesses the data: imputing missing values, removing overly sparse, low variances and over-correlated features, and generating additional features using a variety of heuristics.


Auger searches through thousands of algorithms and hyperparameters to find the best performing models and creates ensembles to further improve accuracy.


The results are presented in a leaderboard in real-time for the user to view and interpret.


The user selects a winning model to deploy. Auger creates a web service prediction endpoint to generate predictions or classifications from new data encountered.

Pricing Plans

Free Trial

  • Community Support
  • Limited dataset size
  • Free model training with limited resources
  • Review and Monitor models with MLRAM
  • 1 seat



  • Standard Support
  • Up to 1GB dataset size
  • $10 per worker hour of model training
  • Review and Monitor models with MLRAM
  • Unlimited seats



  • Priority Support
  • Custom dataset size limits
  • Custom model training resources
  • Review and Monitor models with MLRAM
  • Unlimited seats

Our Partners