Content Based Filtering Quiz

Practice Quiz: Content-Based Filtering

Question 1

Vector x_u and vector x_m must be of the same dimension, where x_u is the input features vector for a user (age, gender, etc.) and x_m is the input features vector for a movie (year, genre, etc.). True or false?

• True
• False ✓

x_u and x_m do not need to be the same dimension. User features and movie features can be very different in size - for example, user features could be 1500 numbers while movie features could be just 50 numbers. Only the output vectors v_u and v_m need to be the same dimension for the dot product.

Note

Reference: From section 11 - “User features and movie features can be very different in size. For example, maybe the user features could be 1500 numbers and the movie features could be just 50 numbers. That’s okay too.”

---

Question 2

If we find that two movies, i and k, have vectors v_m^(i) and v_m^(k) that are similar to each other (i.e., ||v_m^(i) - v_m^(k)|| is small), then which of the following is likely to be true? Pick the best answer.

• We should recommend to users one of these two movies, but not both.
• The two movies are similar to each other and will be liked by similar users. ✓
• The two movies are very dissimilar.
• A user that has watched one of these two movies has probably watched the other as well.

When movie feature vectors are similar (small distance), it indicates the movies have similar characteristics and will appeal to users with similar preferences.

Note

Reference: From section 12 - “Similar items will have similar vectors. This information can be used to make recommendations… other items x^(k) with similar features will turn out to be similar to item i.”

---

Question 3

Which of the following neural network configurations are valid for a content based filtering application? Check all the options that apply:

• The user and the item networks have different architectures ✓
• The user vector v_u is 32 dimensional, and the item vector v_m is 64 dimensional
• The user and item networks have 64 dimensional v_u and v_m vector respectively ✓
• Both the user and the item networks have the same architecture ✓

Valid configurations require that v_u and v_m have the same dimensions for the dot product. The networks can have different architectures as long as their outputs are the same size. Having different dimensional output vectors (32 vs 64) would not work.

Note

Reference: From section 12 - “The user network and the movie network can hypothetically have different numbers of hidden layers and different numbers of units per hidden layer. All the output layer needs to have the same size of the same dimension.”

---

Question 4

You have built a recommendation system to retrieve musical pieces from a large database of music, and have an algorithm that uses separate retrieval and ranking steps. If you modify the algorithm to add more musical pieces to the retrieved list (i.e., the retrieval step returns more items), which of these are likely to happen? Check all that apply.

• The quality of recommendations made to users should stay the same or worsen.
• The quality of recommendations made to users should stay the same or improve. ✓
• The system’s response time might increase (i.e., users have to wait longer to get recommendations) ✓
• The system’s response time might decrease (i.e., users get recommendations more quickly)

Retrieving more items typically improves recommendation quality by giving the ranking step more options, but increases computational cost and response time.

Note

Reference: From section 13 - “During the retrieval step, retrieving more items will tend to result in better performance. But the algorithm will end up being slower.”

---

Question 5

To speed up the response time of your recommendation system, you can pre-compute the vectors v_m for all the items you might recommend. This can be done even before a user logs in to your website and even before you know the x_u or v_u vector. True/False?

• True ✓
• False

Movie vectors v_m depend only on movie features, not user features, so they can be pre-computed for all movies in advance. Only the user vector v_u needs to be computed when the user visits the site.

Note

Reference: From section 13 - “If you have computed v_m for all the movies in advance, then all you need to do is to do inference on this part of the neural network a single time to compute v_u.”