Effective ML model development continues to become an easier and more democratic activity. From embedded AI in apps to AutoML in Power BI Dataflows, data analysis professionals (and even business users) have multiple options to build their own models without complex developments.
In Azure AutoML we find a fine combination of flexibility for software experts and ease of use for non-tech users. With this service we can create full ML pipelines with a few or even no lines of code, covering diverse ML scenarios: from risk classification to forecasting demand, all following best practices and testing multiple models and data transformations to find good and robust models.

In this session we'll go through different options offered in Azure AutoML, including the Python SDK and the no-code interface.