ML-Powered Test Case Prioritisation: Leveraging Code Changes for Optimal Testing
Al Sardy L, Markert N, German R (2026)
Publication Type: Conference contribution
Publication year: 2026
Journal
Publisher: Springer Science and Business Media Deutschland GmbH
Book Volume: 16868 LNCS
Pages Range: 365-380
Conference Proceedings Title: Lecture Notes in Computer Science
Event location: Valencia
ISBN: 9783032348661
DOI: 10.1007/978-3-032-34867-8_23
Abstract
The increasing number of test cases and limited time frames often prevent the execution of complete regression test suites following software changes. This paper addresses this challenge in an industrial software testing context, focusing on daily system tests at Siemens Healthineers. We propose a machine learning-based approach for test case prioritisation that ranks test cases according to their relevance to recent source code changes. Two models, a neural network and a random forest, are developed and evaluated using a dataset comprising over 10,000 test case executions. The experimental results show that both models outperform traditional prioritisation techniques, achieving up to a 50% reduction in the number of test cases required to detect all defects. The random forest model consistently delivers superior prioritisation performance compared to conventional methods. The findings demonstrate that machine learning can significantly improve regression test prioritisation in industrial environments, with feature engineering and model selection emerging as key performance factors. Although evaluated in a single industrial setting, the proposed approach is architecture-independent and applicable across diverse software systems and domains.
Authors with CRIS profile
Loui Al Sardy
Computer Science 7 (Computer Networks and Communication Systems)
Reinhard German
Computer Science 7 (Computer Networks and Communication Systems)
How to cite
APA:
Al Sardy, L., Markert, N., & German, R. (2026). ML-Powered Test Case Prioritisation: Leveraging Code Changes for Optimal Testing. In Elena Troubitsyna, David de Andrés, Friedemann Bitsch (Eds.), Lecture Notes in Computer Science (pp. 365-380). Valencia, ES: Springer Science and Business Media Deutschland GmbH.
MLA:
Al Sardy, Loui, Niklas Markert, and Reinhard German. "ML-Powered Test Case Prioritisation: Leveraging Code Changes for Optimal Testing." Proceedings of the 45th International Conference on Computer Safety, Reliability and Security, SAFECOMP 2026, Valencia Ed. Elena Troubitsyna, David de Andrés, Friedemann Bitsch, Springer Science and Business Media Deutschland GmbH, 2026. 365-380.
BibTeX: Download