Early Life Cycle Software Defect Prediction. Why? How?
arXiv:2011.13071
Abstract
Many researchers assume that, for software analytics, "more data is better." We write to show that, at least for learning defect predictors, this may not be true. To demonstrate this, we analyzed hundreds of popular GitHub projects. These projects ran for 84 months and contained 3,728 commits (median values). Across these projects, most of the defects occur very early in their life cycle. Hence, defect predictors learned from the first 150 commits and four months perform just as well as anything else. This means that, at least for the projects studied here, after the first few months, we need not continually update our defect prediction models. We hope these results inspire other researchers to adopt a "simplicity-first" approach to their work. Some domains require a complex and data-hungry analysis. But before assuming complexity, it is prudent to check the raw data looking for "short cuts" that can simplify the analysis.
arXiv comment12 pages (To appear ICSE 2021)
References in corpus (7)
- Scikit-learn: Machine Learning in Python
- SMOTE: Synthetic Minority Over-sampling Technique
- Tuning for Software Analytics: is it Really Necessary?
- How to "DODGE" Complex Software Analytics?
- Why is Differential Evolution Better than Grid Search for Tuning Defect Predictors?
- Assessing Practitioner Beliefs about Software Defect Prediction
- Defining and Conceptualizing Actionable Insight: A Conceptual Framework for Decision-centric Analytics