Performance tuning for automotive Software Fault Prediction

Harald Altinger, Steffen Herbold, Friederike Schneemann, Jens Grabowski, Franz Wotawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Fault prediction on high quality industry grade software often suffers from strong imbalanced class distribution due to a low bug rate. Previous work reports on low predictive performance, thus tuning parameters is required. As the State of the Art recommends sampling methods for imbalanced learning, we analyse effects when under- and oversampling the training data evaluated on seven different classification algorithms. Our results demonstrate settings to achieve higher performance values but the various classifiers are influenced in different ways. Furthermore, not all performance reports can be tuned at the same time.

Original languageEnglish
Title of host publicationSANER 2017 - 24th IEEE International Conference on Software Analysis, Evolution, and Reengineering
EditorsGabriele Bavota, Martin Pinzger, Andrian Marcus
PublisherInstitute of Electrical and Electronics Engineers
Pages526-530
Number of pages5
ISBN (Electronic)9781509055012
DOIs
Publication statusPublished - 21 Mar 2017
Externally publishedYes
Event24th IEEE International Conference on Software Analysis, Evolution, and Reengineering, SANER 2017 - Klagenfurt, Austria
Duration: 21 Feb 201724 Feb 2017

Publication series

NameSANER 2017 - 24th IEEE International Conference on Software Analysis, Evolution, and Reengineering

Conference

Conference24th IEEE International Conference on Software Analysis, Evolution, and Reengineering, SANER 2017
CountryAustria
CityKlagenfurt
Period21/02/1724/02/17

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'Performance tuning for automotive Software Fault Prediction'. Together they form a unique fingerprint.

Cite this