WEEK 6 lecture

Question 1

associate rule mining

Answer 1

you look for how many items occur together

Question 2

associate rule mining: equation of support

Answer 2

total numbers of times that A and B are put together / the total number of transactions.

Question 3

associate rule mining: confidence

Answer 3

if someone buys item A, how likely are they to also buy item B

Question 4

one word associate rule mining

Answer 4

frequency

Question 5

Apiori Algorithm

Answer 5

1.Start with single items, count how often they show up (support).

2.Combine into pairs, count again.

3.Combine into triples, count again.

4.Keep going, but only keep combinations that meet the minimum support threshold.

Question 6

Clustering

Answer 6

We are looking at how similar the item is with other items near. Looks at similarity.

Question 7

Classification: Neural Nets

Answer 7

• Can select more complex regions
• Can be more accurate
• Also can overfit the data – find patterns in random noise
  It can be used for clustering