The Second European Conference on Data Analysis (also marking the 38th Annual Meeting of the German Classification Society – GfKl) was hosted by Jacobs University Bremen from July 2nd to July 4th, 2014. This year’s conference has been organised in co-operation with the Italian Statistical Society Classification and Data Analysis Group (SIS-Cladag), Vereniging voor Ordinatie en Classificatie (VOC), Sekcja Klasyfikacji i Analizy Danych PTS (SKAD), and the International Association for Statistical Computing (IASC).
A total of 193 participants from 27 countries gathered for three intense days to discuss 153 scientific presentations in eight thematic fields:
- Statistics and Data Analysis
- Machine Learning and Knowledge Discovery
- Data Analysis in Marketing
- Data Analysis in Finance and Economics
- Data Analysis in Medicine and the Life Sciences
- Data Analysis in the Social, Behavioural, and Health Care Sciences
- Data Analysis in Interdisciplinary Domains
- Classification and Subject Indexing in Library and Information Science (LIS’2014).
A total of ten invited key notes have been given:
- Themis Palpanas, Universite ́ Paris-Descartes, Do It Yourself: Exploratory Analysis of Very Large Scientific Data
- Rebecca Nugent, Carnegie-Mellon University, Solving the Identity Crisis: Large- Scale Clustering with Distributions of Distances and Applications in Record Linkage
- Zhi-Hua Zhou, Nanjing University, Learning with Big Data by Incremental Optimization of Performance Measures
- Roberta Siciliano, University Federico II, Naples, The Speed-Interpretability- Accuracy Trade-Off in Decision Tree Learning
- Adam Sagan, University of Economy Cracow, Latent Variables and Marketing Theory – the Paradigm Shift
- Pedro Pereira Rodrigues, University of Porto, How uncertainty simultaneously drives and hinders knowledge discovery from health data
- Alfred Inselberg, Tel Aviv University, Visualization and Data Mining for High- Dimensional Data
- Joaquin Vanschoren, Eindhoven University of Technology, OpenML: Open science in machine learning
- Andreas Geyer-Schulz, KIT, On a Decision Maker without Preference
- Friedhelm Schwenker, University of Ulm, Partially supervised learning algorithms in classification and clustering.
Moreover, as in previous years, some members of the program committee organized special sessions to highlight and discuss the state-of.the-art and recent trends for some selected topics.
This year, a total of six such invited sessions had been organized:
- High-dimensional data: using all dimensions organised by Christian Hennig
- Recent Advances in Mixture Modelling organised by Roberto Rocci
- Data analysis in human.computer interaction scenarios organised by Friedhelm Schwenker
- Health technology assessment of community interventions for active healthy ageing organised by Berthold Lausen
- SVM Large Scale Learning organised by Claus Weihs
- Predictions with classification models organised by Jozef Pociecka.
A panel discussion highlighted the current challenges for the publication strategy of the classification societies: In this discussion, in particular, the discussion was concerned with the question of how the GfKl can secure an attractive, high-quality, open-access, and highly visible proceedings publication for its annual conference.
Thursday late afternoon was as usual reserved for the social program in which the participants had the opportunity to learn about Bremen’s history during a guided tour through the city center. In small groups we were led from the town hall with the statue of Roland in front of it, to the Town Musicians, the Dome, the Boettcher Street and the Schnoor-Viertel, to the river Weser.
There, we embarked the Gräfin Emma, which brought us down the river to Bremen-Vegesack, where the evening ended with the conference dinner.
Right now, preparations for the ECDA 2015 have already started and we look forward to meeting many of you at ECDA 2015 at University of Essex in Colchester, UK, from September 02-04, 2015.