Guest editors’ introduction: special issue of selected papers from ECML-PKDD 2012

Abstract

The 2012 instalment of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) was held in Bristol, United Kingdom during the week of 24–28 September 2012. ECML-PKDD is a highly successful and selective international conference series which was first organised in its present form in 2001 in Freiburg, Germany, when it joined together the hitherto separate ECML and PKDD conferences. Since then, the two strands of machine learning and data mining have been increasingly integrated in the joint conference, and today it is well-known as the only top-tier international conference which exploits the synergy between these two exciting fields. The format of the 2012 conference followed the tried-and-tested format of previous editions, with workshops and tutorials on Monday and Friday; research papers in parallel tracks on Tuesday, Wednesday and Thursday; and plenary keynote talks on each of the 5 conference days. The 105 research papers were carefully selected from 443 submitted papers (acceptance rate 23.7%) on the basis of reviews by 275 Program Committee members and 36 Area Chairs, assisted by 161 additional reviewers. The proceedings were published in two volumes of Springer’s Lecture Notes in Artificial Intelligence series (Flach et al. 2012a,b). After the conference, the authors of the four most highly evaluated data mining and knowledge discovery papers were invited to submit a significantly extended version of their paper to this special section. Submitted papers were assessed by three reviewers, some of whom had reviewed the original conference submission and some of whom had not seen the paper before. After several rounds of reviewing and revision, two of the submitted papers were selected for inclusion. We will now briefly describe the contribution that each paper makes; the papers are ordered alphabetically on title.