Check your understanding
Stay organized with collections Save and categorize content based on your preferences.

Why would you use recommendation systems?

Having a recommendation engine makes browsing content easier.

Plus, a great recommendation system helps users find things they wouldn't have thought to look for on their own.

You think you have to sprinkle ML on everything.

It might seem that way, but in reality, there are much better reasons to use ML.

You want to direct users to sponsored items.

Yikes, this is not a great reason to use any ML solution.

What are the primary components of a recommender system?

candidate generation, scoring, and re-ranking

Nicely done! These are the three primary components of any recommendation system.

embedding, similarity metrics, and serving

These elements are related to recommendation systems, but they are not primary components.

matrix factorization, DNN, and reranking

While re-ranking is a component, matrix factorization and DNN are types of candidate generators.