I am looking for methods that allow for automated discovery of rules that can have temporal conditions.
The very simple example would be:
IF user activity WAS running, and now the user activity IS idle THEN user turns of tracking application
The more advanced example could be
IF user activity during last 30 minutes was running, and during last 5 minutes was idle, THEN user turns of tracking application
Do you think that some solutions from process mining techniques could be useful? Or some techniques from discovery of Markov models? I am specifically interested in rules.
@Kwan-yuet, yes it looks reasonable, as it seems to be a method used for causal rules mining (see paper attached). They use cohort study, which is type of longitudinal study. However, incorporating temporal factors into causal dependencies seems to be more complicated than you say I think. If you have any papers that tackle this issue, please link them. The solution that is close to what I need is described in the second paper attached.
Conference Paper Discovery of Temporal Dependencies between Frequent Patterns...
Article From Observational Studies to Causal Rule Mining
Sequential pattern analysis comes to mind
http://www.cs.cornell.edu/database/himalaya/SequentialPatterns/seqPatterns_main.htm
May be the Granger causality test
- Badges
- Science topic
- Similar topics
- Computer Science
- Data Mining