We have a table below, and we want to apply user-based collaborative filtering to recommend music to Chan. To simplify the calculation, we are going to use the Manhattan distance as our measure. First, please calculate the distance between Chan and other users.   (1 pt) Angelica – Chan: (1 pt) Bill – Chan: (1 pt) Dan – Chan: (1 pt) Hailey – Chan: (Please continue calculating the distance between Chan and the rest of the users) (3 pts) Next, which band/artist should we recommend to Chan?

S25_436/591_Final – Please open the pdf to start. 

We apply item-item collaborative filtering to predict User 5’s rating for Movie 1. To do this, we first calculate the similarity between Movie 1 and the other movies. The Pearson correlation scores between Movie 1 and the other movies are shown on the right-hand side of the figure below. Based on these similarity scores, which two movies are most similar to Movie 1?

Refer to the document-term matrix below after applying the bag-of-words representation. Which term is the most common, and which is the rarest in the corpus

What are the two types of Hierarchical Clustering?

Define Agile Organization and give examples and advantages.

Explain the OD Cycle.

Why is packaging a trained ML model into a Docker container important for production?

What role does a “model registry” serve in an MLOps workflow?

True or False: In Spark Structured streaming, the processing logic can no longer be modified once the streaming session starts.