• Corpus ID: 233443798

Machine Learning Techniques for Software Quality Assurance: A Survey

  title={Machine Learning Techniques for Software Quality Assurance: A Survey},
  author={Safa Omri and Carsten Sinz},
Over the last years, machine learning techniques have been applied to more and more application domains, including software engineering and, especially, software quality assurance. Important application domains have been, e.g., software defect prediction or test case selection and prioritization. The ability to predict which components in a large software system are most likely to contain the largest numbers of faults in the next release helps to better manage projects, including early… 

Figures and Tables from this paper



Tree-based software quality estimation models for fault prediction

A case study from a comprehensive evaluation (with several large case studies) of currently available regression tree algorithms for software fault prediction of CART-LS, S-PLUS, and Cart-LAD, finding that these are simple and effective as software quality prediction models.

An Enhanced Fault Prediction Model for Embedded Software based on Code Churn, Complexity Metrics, and Static Analysis Results

The previous work demonstrated that the combination of code complexity metrics together with static analysis results allows accurate prediction of fault density and to build classifiers discriminating faulty from non-faulty components, and the extension presented in this paper augments this predictor and classi fier with code churn metrics.

Compressed C4.5 Models for Software Defect Prediction

Three new defect prediction models based on C4.5 model are proposed, aiming at the characteristics of the metrics mined from the open source software, which introduce the Spearman's rank correlation coefficient to the basis of choosing root node of the decision tree which makes the models better on defects prediction.

Defect prediction from static code features: current results, limitations, new approaches

It is hypothesized that the limits of the standard learning goal of maximizing area under the curve (AUC) of the probability of false alarms and probability of detection “AUC(pd, pf)” are reached, and certain widely used learners perform much worse than simple manual methods.

A similarity-based approach for test case prioritization using historical failure data

  • Tanzeem Bin NoorH. Hemmati
  • Computer Science
    2015 IEEE 26th International Symposium on Software Reliability Engineering (ISSRE)
  • 2015
The results of the study show that the proposed similarity-based quality measure is significantly more effective for prioritizing test cases compared to existing test case quality measures.

Feature Selection Using Decision Tree Induction in Class level Metrics Dataset for Software Defect Predictions

A new method for feature selection based on Decision Tree Induction is proposed which has the advantage of easy interpretability and comprehensibility and outperforms the other two feature selection techniques.

A deep tree-based model for software defect prediction

A novel prediction model is developed which is capable of automatically learning features for representing source code and using them for defect prediction, built upon the powerful deep learning, tree-structured Long Short Term Memory network which directly matches with the Abstract Syntax Tree representation of source code.

A large-scale empirical study of just-in-time quality assurance

The findings indicate that “Just-In-Time Quality Assurance” may provide an effort-reducing way to focus on the most risky changes and thus reduce the costs of developing high-quality software.

Cross-project defect prediction: a large scale experiment on data vs. domain vs. process

This paper studied cross-project defect prediction models on a large scale and identified factors that do influence the success of cross- project predictions, and derived decision trees that can provide early estimates for precision, recall, and accuracy before a prediction is attempted.

Topic-based defect prediction: NIER track

This paper uses topic modeling to measure the concerns in source code, and uses them as the input for machine learning-based defect prediction models, which have high correlation to the number of bugs (defect-proneness) and better predictive performance than existing state-of-the-art approaches.