Efficiently Summarising Event Sequences with Rich Interleaving Patterns

Discovering the key structure of a database is one of the main goals of data mining. In pattern set mining we do so by discovering a small set of patterns that together describe the data well. The richer the class of patterns we consider, and the more powerful our description language, the better we will be able to summarise the data. In this paper we propose SQUISH, a novel greedy MDL-based method for summarising sequential data using rich patterns that are allowed to interleave. Experiments show SQUISHis orders of magnitude faster than the state of the art, results in better models, as well as discovers meaningful semantics in the form patterns that identify multiple choices of values.

[1]  Dimitrios Gunopulos,et al.  Discovering frequent arrangements of temporal intervals , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[2]  J. Rissanen.  A UNIVERSAL PRIOR FOR INTEGERS AND ESTIMATION BY MINIMUM DESCRIPTION LENGTH , 1983 .

[3]  Nikolaj Tatti,et al.  Ranking episodes using a partition model , 2015, Data Mining and Knowledge Discovery.

[4]  P. S. Sastry,et al.  A fast algorithm for finding frequent episodes in event streams , 2007, KDD '07.

[5]  Charles A. Sutton,et al.  A Subsequence Interleaving Model for Sequential Pattern Mining , 2016, KDD.

[6]  Heikki Mannila,et al.  Discovery of Frequent Episodes in Event Sequences , 1997, Data Mining and Knowledge Discovery.

[7]  Boris Cule,et al.  Mining closed episodes with simultaneous events , 2011, KDD.

[8]  Toon Calders,et al.  Mining Compressing Sequential Patterns , 2012, Stat. Anal. Data Min..

[9]  Jiawei Han,et al.  BIDE: efficient mining of frequent closed sequences , 2004, Proceedings. 20th International Conference on Data Engineering.

[10]  Philip S. Yu,et al.  Discovering Frequent Closed Partial Orders from Strings , 2006, IEEE Transactions on Knowledge and Data Engineering.

[11]  Ming Li,et al.  An Introduction to Kolmogorov Complexity and Its Applications , 2019, Texts in Computer Science.

[12]  Jorma Rissanen,et al.  Minimum Description Length Principle , 2010, Encyclopedia of Machine Learning.

[13]  Boris Cule,et al.  Mining closed strict episodes , 2010, Data Mining and Knowledge Discovery.

[14]  J. Rissanen,et al.  Modeling By Shortest Data Description* , 1978, Autom..

[15]  Nikolai K. Vereshchagin,et al.  Kolmogorov's structure functions and model selection , 2002, IEEE Transactions on Information Theory.

[16]  Carla E. Brodley,et al.  KDD-Cup 2000 organizers' report: peeling the onion , 2000, SKDD.

[17]  Jilles Vreeken,et al.  Slim: Directly Mining Descriptive Patterns , 2012, SDM.

[18]  Raajay Viswanathan,et al.  Discovering injective episodes with general partial orders , 2011, Data Mining and Knowledge Discovery.

[19]  Tao Li,et al.  Skopus: Mining top-k sequential patterns under leverage , 2015, Data Mining and Knowledge Discovery.

[20]  Jilles Vreeken,et al.  Keeping it Short and Simple: Summarising Complex Event Sequences with Multivariate Patterns , 2015, KDD.

[21]  Jilles Vreeken,et al.  Krimp: mining itemsets that compress , 2011, Data Mining and Knowledge Discovery.

[22]  Jilles Vreeken,et al.  The long and the short of it: summarising event sequences with serial episodes , 2012, KDD.

[23]  Rakesh Agarwal,et al.  Fast Algorithms for Mining Association Rules , 1994, VLDB 1994.