Challenge 4 - Building Machine Learning in Power BI

Prerequisites

  1. Challenge 3 - Working with Cognitive Services should be done successfully.

Introduction

The Adventure Works business users have loved all the additional insights they’ve been getting form the text analytics features added to the model. They’d love to take their advanced analytics to the next level by trying to predict outcomes. Adventure Works makes most of it’s income off of selling big ticket items like bikes, in order to try and increase bike sales marketing has acquired a list of prospective customers. The marketing team would like to assess which of these customers is most likely to buy a bike so they can send a targeted mailing to a select group of customers.

Success Criteria

  1. Leverage the existing customer data to train a model to predict buying a bike
  2. Score the list of prospective customers for their propensity to buy a bike
  3. In Power BI build one or more reports to highlight which customers are most likely to buy a bike
  4. Generate the model performance report so see metrics about the model created by Auto ML

Hints

  1. Have a closer look at the columns in BikeBuyerTraining and Prospective Buyer. What is different about these two tables? Are there any differences that could be preventing you from using your model?

Learning resources

   
Description Links
Automated Machine Learning in Power BI https://docs.microsoft.com/en-us/power-bi/service-machine-learning-automated
Tutorial: Build a Machine Learning model in Power BI https://docs.microsoft.com/en-us/power-bi/service-tutorial-build-machine-learning-model
Age Calculation in Power BI using Power Query https://radacad.com/age-calculation-in-power-bi-using-power-query

Next challenge (Building Models in Azure Machine Learning - AutoML) >