Software Defect Prediction

Impressive Code tool set includes IC-DePress (Defect Prediction in Software Systems)

Defect Prediction in Software Systems (DePress) Extensible Framework allows building workflows in graphical manner. DePress is based on the KNIME project. The main aim of the DePress Framework is support for empirical software analysis. It allows you to collect, combine and analyse data from various data sources like software repositories or software metrics.


  1. A collection of datasets MJ12A

If you use this collection of datasets please cite:

Lech Madeyski, Marian Jureczko, “Which Process Metrics Can Significantly Improve Defect Prediction Models? An Empirical Study.”, Software Quality Journal, vol. 23, no. 3, pp. 393–422, 2015. DOI:10.1007/s11219-014-9241-7


See my publications.

Technical reports

Marian Jureczko, Lech Madeyski, “Open source project descriptions”, Tech. Rep., Wroclaw University of Technology, URL
Marian Jureczko, Lech Madeyski, “Software product metrics used to build defect prediction models”, Tech. Rep., Wroclaw University of Technology, URL