Mining Statistically Significant Sequential Patterns

Recent developments in the frequent pattern mining framework uses additional measures of interest to reduce the set of discovered patterns. We introduce a rigorous and efficient approach to mine statistically significant, unexpected patterns in sequences of item sets. The proposed methodology is bas...

Full description

Saved in:
Bibliographic Details
Main Authors: Low-Kam, Cecile, Raissi, Chedy, Kaytoue, Mehdi, Jian Pei
Format: Conference Proceeding
Language:English
Subjects:
Computational modeling
Conferences
Data mining
Electronic & video games
Entropy
Games
Hidden Markov models
Itemsets
Methodology
Mines
null model
Pattern analysis
Random variables
Sequential pattern
significance test
Strategy
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent developments in the frequent pattern mining framework uses additional measures of interest to reduce the set of discovered patterns. We introduce a rigorous and efficient approach to mine statistically significant, unexpected patterns in sequences of item sets. The proposed methodology is based on a null model for sequences and on a multiple testing procedure to extract patterns of interest. Experiments on sequences of replays of a video game demonstrate the scalability and the efficiency of the method to discover unexpected game strategies.
ISSN:1550-4786
2374-8486
DOI:10.1109/ICDM.2013.124