Building an Ensemble for Software Defect Prediction Based on Diversity Selection

Petrić, Jean; Bowes, David; Hall, Tracy; Christianson, Bruce; Baddoo, Nathan

doi:10.1145/2961111.2962610

Cited by 37 publications

(54 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One possible solution is to use stacking ensemble, which uses an additional classifier to make the final prediction. The effectiveness of the stacking ensemble is verified in some of previous CPDP studies . However, a substantial amount of future work is needed to design effective stacking ensemble–based methods, which will fully exploit our findings in this article.…”

Section: Resultssupporting

confidence: 64%

Do different cross‐project defect prediction methods identify the same defective modules?

Chen

Qu³

et al. 2019

J Software Evolu Process

View full text Add to dashboard Cite

Cross‐project defect prediction (CPDP) is needed when the target projects are new projects or the projects have less training data, since these projects do not have sufficient historical data to build high‐quality prediction models. The researchers have proposed many CPDP methods, and previous studies have conducted extensive comparisons on the performance of different CPDP methods. However, to the best of our knowledge, it remains unclear whether different CPDP methods can identify the same defective modules, and this issue has not been thoroughly explored. In this article, we select 12 state‐of‐the‐art CPDP methods, including eight supervised methods and four unsupervised methods. We first compare the performance of these methods in the same experiment settings on five widely used datasets (ie, NASA, SOFTLAB, PROMISE, AEEEM, and ReLink) and rank these methods via the Scott‐Knott test. Final results confirm the competitiveness of unsupervised methods. Then we perform diversity analysis on defective modules for these methods by using the McNemar test. Empirical results verify that different CPDP methods may lead to difference in the modules predicted as defective, especially when the comparison is performed between the supervised methods and unsupervised methods. Finally, we also find there exist a certain number of defective modules, which cannot be correctly identified by any of the CPDP methods or can be correctly identified by only one CPDP method. These findings can be utilized to design more effective methods to further improve the performance of CPDP.

show abstract

Section: Resultssupporting

confidence: 64%

Do different cross‐project defect prediction methods identify the same defective modules?

Chen

Qu³

et al. 2019

J Software Evolu Process

View full text Add to dashboard Cite

show abstract

“…Ensemble techniques have been used recently in the context of predictive modeling in order to overcome the limitation of single estimation techniques, showing mixed results. In particular, research community focused their attention on the use of ensemble techniques for bug prediction,() change prediction() and effort estimation. ()…”

Section: Related Workmentioning

confidence: 99%

“…Petric et al built a Stacking ensemble technique starting from four families of classifiers in the cross‐project bug prediction. Results show how their approach performed better than other ensemble techniques.…”

Section: Related Workmentioning

confidence: 99%

“…Despite several studies have been carried out in the context of bug prediction() or effort estimation,() only a few studies analyzed the extent to which ensemble techniques might be useful in the context of change prediction. () In particular, Kumar et al performed an empirical study on the role of source code metrics in change prediction: In this context, they built ten models, adopting eight standard ML algorithms and two ensemble techniques.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An extensive evaluation of ensemble techniques for software change prediction

Catolino

Ferrucci

2019

J Software Evolu Process

View full text Add to dashboard Cite

Predicting the areas of the source code having a higher likelihood to change in the future represents an important activity to allow developers to plan preventive maintenance operations.For this reason, several change prediction models have been proposed. Moreover, research community demonstrated how different classifiers impact on the performance of devised models as well as classifiers tend to perform similarly even though they are able to correctly predict the change proneness of different code elements, possibly indicating the presence of some complementarity among them. In this paper, we deeper investigated whether the use of ensemble approaches, ie, machine learning techniques able to combine multiple classifiers, can improve the performances of change prediction models. Specifically, we built three change prediction models based on different predictors, ie, product-, process-metrics-, and developer-related factors, comparing the performances of four ensemble techniques (ie, Boosting, Random Forest, Bagging, and Voting) with those of standard machine learning classifiers (ie, Logistic Regression, Naive Bayes, Simple Logistic, and Multilayer Perceptron). The study was conducted on 33releases of 10 open-source systems, and the results showed how ensemble methods and in particular Random Forest provide a significant improvement of more than 10% in terms of F measure. Indeed, the statistical analyses conducted confirm the superiority of this ensemble technique. Moreover, the model built using developer-related factors performed better than the other models that exploit product and process metrics and achieves an overall median of F measure around 77%.

show abstract

“…The ensemble machine learning model is created from individual models in a heterogeneous (which integrates various types of individual models) or homogenous (which integrates the same types of individual model) fashion. A number of ensemble models have been investigated in relation to the problem of software defect prediction to improve their accuracy performance over individual models: voting feature intervals [18]; combined defect predictor [19]; average probability ensemble [20]; bagging and boosting [21]; stacking [22]; and adaptive selection of classifiers in bug prediction [23]. Heterogeneous ensemble models have been proposed to increase accuracy prediction over individual models, such as a software maintainability evaluation model based on combining multiple classifiers [24].…”

Section: Introductionmentioning

confidence: 99%

Application of Ensemble Techniques in Predicting Object-Oriented Software Maintainability

Alsolai

Roper

2019

Proceedings of the Evaluation and Assessment on Software Engineering

View full text Add to dashboard Cite

While prior object-oriented software maintainability literature acknowledges the role of machine learning techniques as valuable predictors of potential change, the most suitable technique that achieves consistently high accuracy remains undetermined. With the objective of obtaining more consistent results, an ensemble technique is investigated to advance the performance of the individual models and increase their accuracy in predicting software maintainability of the object-oriented system. This paper describes the research plan for predicting object-oriented software maintainability using ensemble techniques. First, we present a brief overview of the main research background and its different components. Second, we explain the research methodology. Third, we provide expected results. Finally, we conclude summary of the current status.

show abstract

Building an Ensemble for Software Defect Prediction Based on Diversity Selection

Cited by 37 publications

References 31 publications

Do different cross‐project defect prediction methods identify the same defective modules?

Do different cross‐project defect prediction methods identify the same defective modules?

An extensive evaluation of ensemble techniques for software change prediction

Application of Ensemble Techniques in Predicting Object-Oriented Software Maintainability

Contact Info

Product

Resources

About