On the Effectiveness of Feature Selection Techniques in the Context of ML-Based Regression Test Prioritization
Bibliographic record
Abstract
Regression testing is essential for maintaining software functionality in continuous integration (CI) systems, but it can become increasingly costly as software complexity grows. Machine learning-based Regression Test Prioritization (RTP) techniques have been developed to prioritize test cases based on their likelihood of failure, aiming to detect failures early and optimize resource use. However, the features used in the current state-of-the-art for training machine learning (ML) models often vary widely across different datasets, highlighting the need for further research to identify effective feature sets for RTP. Furthermore, the feature selection techniques are frequently biased toward specific features based on the dataset. Hence, we explored an ensemble technique to utilize three ML-based feature selection techniques in this study to identify and refine key features that enhance test case prioritization. These techniques were applied across four tree-based ML models using data from 15 large-scale open-source software projects. Our analysis identified the most compelling features for predicting failures and assessed their impact on RTP. The results showed that using a refined subset of features could achieve similar or up to a 10% increase in RTP performance, using only one-third of the original feature set. We also empirically evaluated the cost considerations when choosing the three methods and reported the ML models’ performance with the refined feature sets. This underscores the potential of integrating advanced feature selection methods into RTP processes.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".