Data Mining

ASSOCIATION RULES

1. Association rules slides - apriori, eclat, fp growth - pretty complete

2. Terms - lift, confidence

3. Paper - basic concepts and algo

Knoldus

1. Apriori

2. Association rules

3. Fp-growth

4. Fp-tree construction

APRIORI

1. Apyori tut git

2. Efficient apriori

3. One of the best known association rules algorithm - apriori in weka

4. A very good visual example of a transaction DB with the apriori algorithm step by step

5. Python 3.0 code

6. Mlxtnd tutorial

   1. Apriori

   2. Rules

   3. pgrowth

   4. fpmax

FP Growth

1. How to construct the fp-tree

2. The same example, but with a graph that shows that lower support cost less for fp-growth in terms of calc time.

3. Coursera video

4. Another clip video

5. How to validate these algorithms - probably the best way is confidence/support/lift

It depends on your task. But usually you want all three to be high.

• high support: should apply to a large amount of cases

• high confidence: should be correct often

• high lift: indicates it is not just a coincidence

1. Difference between apriori and fp-growth