Data mining Flashcards
1
Q
Association rules terminology. What is “support”? What is “support threshold”?
A
Support for set of items I: how many buckets I is a subset of.
Support Threshold: Number s. I is frequent if its support is s or more.
2
Q
What is “FP-Growth”?
A
A common algorithm for association rules mining.
3
Q
Difference between “content-based systems” and “collaborative filtering systems”?
A
Content-based: recommend things similar to what user used before.
Collaborative filtering: recommend things based on a similarity measure on how the user has rated things compared to how other users rated things. (i.e. you’re similar to “this” group of users so you’ll probably like what they liked).
