Feature Transformation for Improved Software Bug Detection Models

Shamse Tasnim Cynthia, Banani Roy, Debajyoti Mondal

Testing software is considered to be one of the most crucial phases in software development life cycle. Software bug fixing requires a significant amount of time and effort. A rich body of recent research explored ways to predict bugs in software artifacts using machine learning based techniques. For a reliable and trustworthy prediction, it is crucial to also consider the explainability aspects of such machine learning models. In this paper, we show how the feature transformation techniques can significantly improve the prediction accuracy and build confidence in building bug prediction models. We propose a novel approach for improved bug prediction that first extracts the features, then finds a weighted transformation of these features using a genetic algorithm that best separates bugs from non-bugs when plotted in a low-dimensional space, and finally, trains the machine learning model using the transformed dataset. In our experiment with real-life bug datasets, the random forest and k-nearest neighbor classifier models that leveraged feature transformation showed 4.25% improvement in recall values on an average of over 8 software systems when compared to the models built on original data.
Shamse Tasnim Cynthia, Banani Roy, and Debajyoti Mondal. 2022. Feature Transformation for Improved Software Bug Detection Models. 15th Innovations in Software Engineering Conference.
Copy Citation: