Azure - AutoML Process

Process

  1. Prepare data
  2. Train model
  3. Evaluate performance
  4. Deploy a predictive service

Prepare Data

Import data from Azure storage

  • Local files
  • SQL databases
  • Web files
  • Azure Open Datasets

Train model

  • Classification (predicting categories or classes)
  • Regression (predicting numeric values )
  • Time series forecasting (predicting numeric values at a future point in time)
  • Natural language processing
  • Computer vision

Evaluate performance

  • Cross validation
  • RMSE (Root Mean Squared Error)
  • NRMSE (Normalized Root Mean Squared Error)
  • Residual History
  • Predicted vs True chart

Deploy

  • Azure Container Instances (ACI)
  • Azure Kubernetes Service (AKS)