Skip to content


Classifying movies is always super cool and useful. I, myself, have built at least five successful business around it, so I wanted to share an end-to-end example of how you can go from being an average Netflix rater to making millions of dollars on your skillset. In this part we are going to build the preprocessing in PySpark and then in Part 2, we will continue training awesome models that we can deploy so that millions of users can pay for the ratings.


Subscription tiers at about $29/month have worked best for me in the past.


In this tutorial we will use PySpark to run preprocessing to later use that data with TensorFlow to create a fantastic model. The model will then be deployed to a live endpoint that can serve our imaginary users through a https API.