For example: if my dataset contains (A, B), but does not contain (B, A). Then the algorithm may generate the rule A -> B, but will not generate the rule B -> A.

Is there an association rules algorithm, or variation of an algorithm, that respects the order of items in this manner?

  • $\begingroup$ Velcome to our site! $\endgroup$ – kjetil b halvorsen Jul 21 '14 at 17:14
  • $\begingroup$ Seeing as this question isn't getting much traffic here, is there a better place to ask this? Also, thank you for the welcome! $\endgroup$ – PaintingInAir Aug 4 '14 at 3:02

I think you might be looking for a sequential pattern mining algorithm, such as apriori all.

Agrawal, Rakesh, and Ramakrishnan Srikant. "Mining sequential patterns." Data Engineering, 1995. Proceedings of the Eleventh International Conference on. IEEE, 1995.

Implementation of many current algorithms for mining sequential patterns are available in SPMF.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.