Using the model in predictions

We have been through almost all of the steps of the resource-consumption-estimation project, but the last step is to prepare a comfortable way of making predictions to users. Let's reflect on which parameters the model depends:

  • A customer can be Private or Corporate
  • A customer can live in a small, mid-sized, or big city
  • We can predict incoming (I) or outgoing (O) actions
  • We make the prediction for a point in the future (the end of a predicted month)
  • We are predicting voice calls (min) or text messages (pc)

This list is also a description of all parameters needed to calculate and return a predicted value to a user.

The most comfortable and secure option for making predictions is to develop ...

Get Hands-On Data Science with SQL Server 2017 now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.