RT book part
T1 An Analysis of Class Imbalance Challenges in Predictive Mutation Testing
A1 Balderas Díaz, Sara
A1 Guerrero Contreras, Gabriel José
A1 Delgado Pérez, Pedro
A1 Medina Bulo, María Inmaculada
A2 Ingeniería Informática
K1 Predictive Mutation Testing
K1 class imbalance
K1 machine learning
K1 ensemble models
K1 software testing
AB This study evaluates the efficacy of Predictive Mutation Testing (PMT) models, focusing on the impact of preprocessing, class rebalancing, and model selection on predictive accuracy. By filtering unreached mutants, artificially inflated metrics caused by trivial correlations were minimized, enhancing the ability of the model to identify complex patterns. While ensemble models like CatBoost and XGBoost showed high effectiveness in detecting killed mutants, their performance in identifying survived mutants was limited, underscoring the need for refined strategies to address class imbalance. The study further identifies that previous PMT research often lacks class-specific metrics, such as the Matthews Correlation Coefficient, essential for assessing balanced performance. This oversight can yield misleading evaluations by favoring the majority class, which may falsely indicate high model reliability. Although SMOTE rebalancing improved recall for survived mutants, balancing sensitivity and precision remains challenging. The findings advocate for the development of more balanced datasets in future PMT research to enhance both accuracy and robustness in real-world testing scenarios.
PB Springer
SN 978-981-96-6004-9
YR 2025
FD 2025-04-21
LK http://hdl.handle.net/10498/37660
UL http://hdl.handle.net/10498/37660
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 07-nov-2026