Combining correlation-based feature selection with genetic algorithm tuning on random forest achieves 88.40% accuracy for software fault prediction, an 18% gain over baselines without selection or tuning.
A promethee based evaluation of software defect predictors,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Feature-Driven Framework for Software Fault Prediction
Combining correlation-based feature selection with genetic algorithm tuning on random forest achieves 88.40% accuracy for software fault prediction, an 18% gain over baselines without selection or tuning.