For each of these scenarios decide if you could use supervised or unsupervised techniques, or both!

Define the likelihood that an individual will contract a specific disease Supervised using KNeighborclasiffier and unsupervised using clustering

Translate a set of images into variables for modeling Unsupervised learning

An ecommerce company wants to identify power users Unsupervised

That same company wants to see shopping patterns in users Supervised learning

You want to reduce the number of variables inputting into your random forest model Unsupervosed learning using PCA