Tuned Data Mining (TDM) and TDMR​

logo_data_mining

NOTE 03/2017: TDMR download currently only here.

The complex, often redundant and noisy data of real-world data mining (DM) applications frequently lead to inferior results when out-of-the-box DM models are applied. Tuning of parameters is essential to achieve high-quality results. We pursue in this project an approach to tune parameters of the preprocessing and the modelling phase conjointly. We propose the new framework TDM (Tuned Data Mining) which facilitates the search for good parameters and the comparison of different tuners by using mostly generic elements which are easily applied to new tasks.

The R-package TDMR (Tuned Data Mining in R) - freely available as open-source software from CRAN - is written with the aim to facilitate the setup, training and 28921_small_christophe-papke_pixelio.de_evaluation of data mining models. It puts special emphasis on tuning these data mining models as well as simultaneously tuning certain preprocessing options. TDMR is especially designed to work with SPOT as the preferred tuner, but it offers also the possibility to use other tuners (CMA-ES, LHD, direct-search optimizers) for comparison.

See the user manual TDMR-docu.pdf (CIOP-Report [Kone12a], last update March 2015) and the TDMR Tutorial (CIOP-Report 03/2012 [Kone12b], last update March 2015) for in-depth information on usage and development of the TDMR package.

 

Project members

patrickPortrait Dr. Patrick Koch, FH Köln konen-3 Prof. Dr. Wolfgang Konen, FH Köln

 

Publications

Publications in the area of Tuned Data Mining (TDM) and TDMR:

2014

Koch, Patrick; Wagner, Tobias; Emmerich, Michael; Bäck, Thomas; Konen, Wolfgang

Efficient multi-criteria optimization on noisy machine learning problems Artikel

Applied Soft Computing, (accepted for publication) , S. 1, 2014.

Links | BibTeX

2013

Koch, Patrick; Konen, Wolfgang

Subsampling strategies in SVM ensembles Inproceedings

Hoffmann, Frank; Hüllermeier, Eyke (Hrsg.): Proceedings 23. Workshop Computational Intelligence, S. 119–134, Universitätsverlag Karlsruhe, 2013.

Links | BibTeX

Stork, Jörg; Ramos, Ricardo; Koch, Patrick; Konen, Wolfgang

SVM ensembles are better when different kernel types are combined Inproceedings

Lausen, Berthold (Hrsg.): European Conference on Data Analysis (ECDA13), (under review), 2013.

Links | BibTeX

2012

Koch, Patrick; Bischl, Bernd; Flasch, Oliver; Bartz-Beielstein, Thomas; Weihs, Claus; Konen, Wolfgang

Tuning and Evolution of Support Vector Kernels Artikel

Evolutionary Intelligence, 5 , S. 153–170, 2012.

Links | BibTeX

Konen, Wolfgang; Koch, Patrick

The TDMR Package: Tuned Data Mining in R Forschungsbericht

Research Center CIOP (Computational Intelligence, Optimization and Data Mining) Cologne University of Applied Science, Faculty of Computer Science and Engineering Science, (02/2012), 2012.

Links | BibTeX

Koch, Patrick; Konen, Wolfgang

Efficient sampling and handling of variance in tuning data mining models Inproceedings

Coello, Carlos Coello A; Cutello, Vincenzo; others, (Hrsg.): PPSN'2012: 12th International Conference on Parallel Problem Solving From Nature, Taormina, S. 195–205, Springer, Heidelberg, 2012.

Links | BibTeX

Konen, Wolfgang; Koch, Patrick

The TDMR Tutorial: Examples for Tuned Data Mining in R Forschungsbericht

Research Center CIOP (Computational Intelligence, Optimization and Data Mining) Cologne University of Applied Science, Faculty of Computer Science and Engineering Science, (03/2012), 2012.

Links | BibTeX

Konen, Wolfgang; Koch, Patrick

The TDMR Framework: Tuned Data Mining in R Forschungsbericht

Research Center CIOP (Computational Intelligence, Optimization and Data Mining) Cologne University of Applied Science, Faculty of Computer Science and Engineering Science, (02/2012), 2012.

Links | BibTeX

2011

Friese, Martina ; Zaefferer, Martin ; Bartz-Beielstein Thomasand Flasch, Oliver ; Koch, Patrick ; Konen, Wolfgang ; Naujoks, Boris

Ensemble Based Optimization and Tuning Algorithms Inproceedings

Hoffmann, Frank ; Hüllermeier, Eyke (Hrsg.): Proceedings 21. Workshop Computational Intelligence, S. 119–134, Universitätsverlag Karlsruhe, 2011.

BibTeX

Koch, Patrick; Bischl, Bernd; Flasch, Oliver; Bartz-Beielstein, Thomas; Konen, Wolfgang

On the Tuning and Evolution of Support Vector Kernels Forschungsbericht

Research Center CIOP (Computational Intelligence, Optimization and Data Mining) Cologne University of Applied Science, Faculty of Computer Scienceand Engineering Science, (04/11), 2011, ISSN: 2191-365X.

Links | BibTeX

Koch, Patrick; Konen, Wolfgang; Naujoks, Boris; Flasch, Oliver; Friese, Martina; Zaefferer, Martin; Bartz-Beielstein, Thomas

Tuned Data Mining in R Inproceedings

Hoffmann, Frank; Hüllermeier, Eyke (Hrsg.): Proceedings 21. Workshop Computational Intelligence, S. 147–160, Universitätsverlag Karlsruhe, 2011.

BibTeX

Koch, Patrick; Bischl, Bernd; Flasch, Oliver; Bartz-Beielstein, Thomas; Konen, Wolfgang

On the Tuning and Evolution of Support Vector Kernels Forschungsbericht

Research Center CIOP (Computational Intelligence, Optimization and Data Mining) Cologne University of Applied Science, Faculty of Computer Scienceand Engineering Science, (04/11), 2011, ISSN: 2191-365X.

Links | BibTeX

Konen, Wolfgang; Koch, Patrick; Flasch, Oliver; Bartz-Beielstein, Thomas; Friese, Martina; Naujoks, Boris

Tuned Data Mining: A Benchmark Study on Different Tuners Inproceedings

Krasnogor, Natalio (Hrsg.): GECCO '11: Proceedings of the 13th Annual Conference on Genetic andEvolutionary Computation, S. 1995–2002, 2011.

BibTeX

Konen, Wolfgang

Self-configuration from a Machine-Learning Perspective Forschungsbericht

Research Center CIOP (Computational Intelligence, Optimization and Data Mining) Cologne University of Applied Science, Faculty of Computer Science and Engineering Science, (05/11; arXiv: 1105.1951), 2011, ISSN: 2191-365X, (e-print published at http://arxiv.org/abs/1105.1951 and Dagstuhl Preprint Archive, Workshop 11181 "Organic Computing -- Design of Self-Organizing Systems").

Links | BibTeX

2010

Koch, Patrick; Konen, Wolfgang; Flasch, Oliver; Bartz-Beielstein, Thomas

Optimizing Support Vector Machines for Stormwater Prediction Inproceedings

Bartz-Beielstein, Thomas; Chiarandini, ; Paquete, ; Preuss, Mike (Hrsg.): Proceedings of Workshop on Experimental Methods for the Assessment of Computational Systems joint to PPSN2010, S. 47–59, TU Dortmund, 2010.

Links | BibTeX

Koch, Patrick; Konen, Wolfgang; Flasch, Oliver; Bartz-Beielstein, Thomas

Optimization of Support Vector Regression Models for Stormwater Prediction Inproceedings

Hoffmann, Frank; Hüllermeier, Eyke (Hrsg.): Proceedings 20. Workshop Computational Intelligence, S. 146–160, Universitätsverlag Karlsruhe, 2010.

BibTeX

2009

Konen, Wolfgang; Zimmer, Tobias; Bartz-Beielstein, Thomas

Optimized Modelling of Fill Levels in Stormwater Tanks Using CI-based Parameter Selection Schemes (in german) Artikel

at-Automatisierungstechnik, 57 (3), S. 155–166, 2009.

BibTeX