[Dbworld] EDBT 2017 Test of Time Award

EDBT 2017 Test of Time Award

In 2014, the Extended Database Technology conference (EDBT http://www.edbt.org/) began awarding the EDBT test-of-time (ToT) award, with the goal of recognising papers presented at EDBT Conferences that have had the most impact in terms of research, methodology, conceptual contribution, or transfer to practice. 

This year, covering the conferences from 1996 to 2002, the award has been given to:

Ramakrishnan Srikant, Rakesh Agrawal: Mining Sequential Patterns: Generalizations and Performance Improvements. EDBT 1996: 3-17.

This paper has made substantial contributions to data mining, and has had great influence on the work of others, as reflected by over 2900 citations on Google Scholar.

The paper formalizes a new variant of the problem of mining *sequential* patterns and develops and implements GSP, an algorithm to solve this problem. This paper extends the definition of sequence mining that was introduced by the same authors in a previous publication: Mining Sequential Patterns. ICDE 1995. The goal is to discover all sequential patterns with a user-specified minimum support from a database of sequences, where each sequence is a list of transactions ordered by transaction-time, and each transaction is a set of items. The proposed extensions are:

1. Time constraints: the authors generalised their previous definition of sequential patterns to admit max-gap and min-gap time constraints between adjacent elements of a sequential pattern.

2. Sliding windows: the authors relaxed the restriction that all the items in an element of a sequential pattern must come from the same transaction, and allowed a user-specified window-size within which the items can be present.

3. Taxonomies: the sequential patterns may include items across different levels of a taxonomy.

GSP guarantees that all rules that have a user-specified minimum support. It is shown to be much faster than the AprioriAll algorithm in the previous publication (on both synthetic and real data). GSP has been implemented as part of the Quest data mining prototype at IBM Research, and is incorporated in the IBM data mining product.


The EDBT 2017 Test of Time Award Committee consisted of Peter Triantafillou, Gustavo Alonso, Sihem Amer-Yahia, Ralf Hartmut Güting and Volker Markl.

The EDBT ToT award for 2017 will be presented during the EDBT/ICDT 2017 Joint Conference, March 21-24, in Venice, Italy (http://edbticdt2017.unive.it/).
_______________________________________________
Please do not post msgs that are not relevant to the database community at large.  Go to www.cs.wisc.edu/dbworld for guidelines and posting forms.
To unsubscribe, go to https://lists.cs.wisc.edu/mailman/listinfo/dbworld