Q:
Recommending items based on global popularity can (check all that apply):
Q:
Recommending items using a classification approach can (check all that apply):
Q:
Recommending items using a simple count based co-occurrence matrix can (check all that apply):
Q:
Recommending items using featurized matrix factorization can (check all that apply):
Q:
Normalizing co-occurrence matrices is used primarily to account for:
Q:
A store has 3 customers and 3 products. Below are the learned feature vectors for each user and product. Based on this estimated model, which product would you recommend most highly to User #2? User ID Feature vector 1 (1.73, 0.01, 5.22) 2 (0.03, 4.41, 2.05) 3 (1.13, 0.89, 3.76) Product ID Feature vector 1 (3.29, 3.44, 3.67) 2 (0.82, 9.71, 3.88) 3 (8.34, 1.72, 0.02)
Q:
For the liked and recommended items displayed below, calculate the recall and round to 2 decimal points. (As in the lesson, green squares indicate recommended items, magenta squares are liked items. Items not recommended are grayed out for clarity.) Note: enter your answer in American decimal format (e.g. enter 0.98, not 0,98)
Q:
For the liked and recommended items displayed below, calculate the precision and round to 2 decimal points. (As in the lesson, green squares indicate recommended items, magenta squares are liked items. Items not recommended are grayed out for clarity.) Note: enter your answer in American decimal format (e.g. enter 0.98, not 0,98)
Q:
Based on the precision-recall curves in the figure below, which recommender would you use?
Subscribe
0 Comments
Find Questions in This Page: "CTRL+F"
