# A Feature-Driven Framework for Software Fault Prediction

arXiv: https://arxiv.org/abs/2605.17611 · HTML: https://mlsanity.com/paper/2605.17611/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 36 references that are in the map.
- First posted on arXiv 17 May 2026.

## Builds on (most cited first, 4 of 4)

- [Cross-validation: what does it estimate and how well does it do it?](https://mlsanity.com/paper/2104.00673/) (2021)
- [The Impact of Automated Parameter Optimization on Defect Prediction Models](https://mlsanity.com/paper/1801.10270/) (2018)
- [Tuning for Software Analytics: is it Really Necessary?](https://mlsanity.com/paper/1609.01759/) (2016)
- [From Requirements to Test Cases: An NLP-Based Approach for High-Performance ECU Test Case Automation](https://mlsanity.com/paper/2505.00547/) (2025)

## Abstract (arXiv)

Software fault prediction (SFP) is a critical task in software engineering, enabling early identification of faults in modules to improve software quality and reduce maintenance costs. This research investigates the combined effects of feature selection and parameter tuning on the performance of machine learning (ML) models for SFP. This study evaluates the interaction between feature selection methods, including correlation-based feature selection (CFS), recursive feature elimination (RFE), mutual information (MI), and L1 regularization, where hyperparameter tuning techniques such as grid search, randomized search, and genetic algorithm (GA) are used for optimization of ML algorithms, including random forest (RF), logistic regression (LR), and support vector machines (SVM) for optimized fault prediction performance. The combined application of CFS and GA yielded the highest accuracy, achieving 88.40% with RF, representing an improvement of 18% over baseline models without feature selection or tuning. Feature selection reduced dimensionality and identified critical attributes such as weighted methods per Class (WMC) and coupling between objects (CBO), while iterative parameter tuning optimized model alignment to these feature sets. Notably, the proposed methods demonstrated robustness, with minimal cross-validation variability (+-1.0%), and efficiency, reducing training times in univariate methods such as L1 regularization.