Summary

In this chapter, we've built our unsupervised machine learning model. After a brief introduction of the business scenario, we've discovered what unsupervised machine learning is and used the K-Means clustering algorithm to group similar observations within the same clusters.

Before diving into the development of the machine learning models, we applied some data quality checks to our dataset and selected the fields to use as features of our machine learning models.

During the training stage, we trained two different machine learning models to learn how to create a K-Means clustering model.

Then, we evaluated the two models, leveraging BigQuery ML SQL syntax and the functionalities available in the BigQuery UI.

In the last step, we tested our machine learning model to cluster the taxi drivers available in the dataset according to their features and into the clusters generated by the K-Means model.

Finally, we've also created a list of drivers belonging...