Re: Sequential Pattern Mining vesus "Sequential Pattern Mining"
Date: October 30, 2018 09:11PM
Hi,
There might be some similarities but I think there are some important differences between sequential pattern mining and lag sequence analysis.
Lag sequence analysis (LS):
- it is used to analyse time series (sequences of numbers) and find if there is some correlation between what happen at at time T with what happened at a time T + lag where lag is a parameter.
Sequential pattern mining (SPM):
- is used to analyse sequences of symbols and find subsequences of symbols that appear frequently in a set of sequences.
Differences:
- SPM is for a set of sequences of symbols. LS is for a time series (a sequence of number). T
- In time series, the time interval between consecutive values is assumed to always be the same. In sequences, this may not be true.
- SPM find patterns that appear in many sequences but there is no concept of lag. In LS there is a concept of lag.
Similarties
- You could always convert a time series to sequences of symbols to find sequential patterns in a time series. But there is still no concept of lag.
- You could always use both techniques to do some predictions.
I think that periodic pattern mining is closer to lag sequence analysis than sequential pattern mining.
Just my opinion ;-)
Edited 1 time(s). Last edit at 10/30/2018 09:12PM by webmasterphilfv.