Saved in:
Bibliographic Details
Main Authors: Plyusnin, Pavel, Antonov, Aleksey, Ermakov, Vasilii, Khaybriev, Aleksandr, Kikot, Margarita, Alimova, Ilseyar, Moiseev, Stanislav
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.10279
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915492006985728
author Plyusnin, Pavel
Antonov, Aleksey
Ermakov, Vasilii
Khaybriev, Aleksandr
Kikot, Margarita
Alimova, Ilseyar
Moiseev, Stanislav
author_facet Plyusnin, Pavel
Antonov, Aleksey
Ermakov, Vasilii
Khaybriev, Aleksandr
Kikot, Margarita
Alimova, Ilseyar
Moiseev, Stanislav
contents In modern software development change-based testing plays a crucial role. However, as codebases expand and test suites grow, efficiently managing the testing process becomes increasingly challenging, especially given the high frequency of daily code commits. We propose Targeted Test Selection (T-TS), a machine learning approach for industrial test selection. Our key innovation is a data representation that represent commits as Bags-of-Words of changed files, incorporates cross-file and additional predictive features, and notably avoids the use of coverage maps. Deployed in production, T-TS was comprehensively evaluated against industry standards and recent methods using both internal and public datasets, measuring time efficiency and fault detection. On live industrial data, T-TS selects only 15% of tests, reduces execution time by $5.9\times$, accelerates the pipeline by $5.6\times$, and detects over 95% of test failures. The implementation is publicly available to support further research and practical adoption.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10279
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Targeted Test Selection Approach in Continuous Integration
Plyusnin, Pavel
Antonov, Aleksey
Ermakov, Vasilii
Khaybriev, Aleksandr
Kikot, Margarita
Alimova, Ilseyar
Moiseev, Stanislav
Software Engineering
Machine Learning
In modern software development change-based testing plays a crucial role. However, as codebases expand and test suites grow, efficiently managing the testing process becomes increasingly challenging, especially given the high frequency of daily code commits. We propose Targeted Test Selection (T-TS), a machine learning approach for industrial test selection. Our key innovation is a data representation that represent commits as Bags-of-Words of changed files, incorporates cross-file and additional predictive features, and notably avoids the use of coverage maps. Deployed in production, T-TS was comprehensively evaluated against industry standards and recent methods using both internal and public datasets, measuring time efficiency and fault detection. On live industrial data, T-TS selects only 15% of tests, reduces execution time by $5.9\times$, accelerates the pipeline by $5.6\times$, and detects over 95% of test failures. The implementation is publicly available to support further research and practical adoption.
title Targeted Test Selection Approach in Continuous Integration
topic Software Engineering
Machine Learning
url https://arxiv.org/abs/2509.10279