In this project, I work with the Bank Marketing dataset. I will use Azure to configure a cloud-based machine learning production model, deploy it, and consume it. I will also create, publish, and consume a pipeline.

In this step, I create a Service Principal account and associate it with your specific workspace.

In this step, I upload the bankmarketing_train.csv to Azure Machine Learning Studio so that it can be used when training the model. Then, I use AutoMl to generate models.

In this step, I deploy the Best Model that will me allow to interact with the HTTP API service and interact with the model by sending data over POST requests.

In this step, I enable logging so that logs can be retrieved.

In this step, I consume the deployed model using Swagger.

In this step, I use the endpoint.py script provided to interact with the trained model.

In this step, I create and publish a pipeline.

Here is a screencast showing the entire process of the working ML application.

Operationalizing Machine Learning screencast

A great future enhancement for me is to connect github with the azure mazchine learning pipeline I have created.