Which type of metrics are useful to deal with class imbalance in software defect prediction?

Öztürk, Muhammed Maruf

doi:10.1016/j.infsof.2017.07.004

Cited by 28 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Software metric thresholds were derived to predict faults in open source softwares in (Arar and Ayan, 2016). Static code and quality metrics are compared in discussing class imbalance in (Öztürk, 2017). Evaluation of a number of ensemble methods in terms of its performance for software fault prediction is presented in (Yucalar et al , 2020).…”

Section: Resultsmentioning

confidence: 99%

Quality and reliability studies in software defect management: a literature review

Pai¹,

Joshi

Rane

2021

IJQRM

View full text Add to dashboard Cite

PurposeThis paper is focused at studying the current state of research involving the four dimensions of defect management strategy, i.e. software defect analysis, software quality, software reliability and software development cost/effort.Design/methodology/approachThe methodology developed by Kitchenham (2007) is followed in planning, conducting and reporting of the systematic review. Out of 625 research papers, nearly 100 primary studies related to our research domain are considered. The study attempted to find the various techniques, metrics, data sets and performance validation measures used by researchers.FindingsThe study revealed the need for integrating the four dimensions of defect management and studying its effect on software performance. This integrated approach can lead to optimal use of resources in software development process.Research limitations/implicationsThere are many dimensions in defect management studies. The authors have considered only vital few based on the practical experiences of software engineers. Most of the research work cited in this review used public data repositories to validate their methodology and there is a need to apply these research methods on real datasets from industry to realize the actual potential of these techniques.Originality/valueThe authors believe that this paper provides a comprehensive insight into the various aspects of state-of-the-art research in software defect management. The authors feel that this is the only research article that delves into the four facets namely software defect analysis, software quality, software reliability and software development cost/effort.

show abstract

Section: Resultsmentioning

confidence: 99%

Quality and reliability studies in software defect management: a literature review

Pai¹,

Joshi

Rane

2021

IJQRM

View full text Add to dashboard Cite

show abstract

“…Some practitioners use this metric as an indicator of the level of defect-proneness. With the evolution of programming languages, object-oriented metrics standards were developed such as Lorenz, Kidd, Chi-damber, and Kemerer [36,37]. The primary studies use software metrics as independent variables for measuring the quality of software modules.…”

Section: 2defect Prediction Metricsmentioning

confidence: 99%

A Novel Approach for Software Defect Prediction using CNN and GRU Based on SMOTE Tomek Method

Khleel

Nehéz

2022

Preprint

View full text Add to dashboard Cite

Software defect prediction (SDP) plays an important role in enhancing the quality of software projects and reducing maintenance-based risks through the ability to detect defective software components. SDP refers to the methods that use historical defect data to build the relationship between software metrics and software defects. Several prediction models such as machine learning (ML), deep learning (DL) have been developed and adopted to recognize defect in software modules and many methodologies and frameworks have been presented. One of the most difficult problems that these models face in binary classification is the classes imbalance. When the distribution of classes is unbalanced, the accuracy may be high, but the model cannot recognize data instances in the minority class, this will lead to weak classifications. So far, few research have been done in the previous studies that address the problem of class imbalance in SDP. To address the class imbalance problem, we propose a novel SDP approach based on convolutional neural network (CNN) and gated recurrent unit (GRU) combined with synthetic minority oversampling technique plus Tomek link (SMOTE Tomek). To establish the efficiency of the proposed models, the experiments have been conducted on benchmark datasets which obtained from the PROMISE repository and the experimental results have been compared and evaluated in terms of accuracy, precision, recall, f-measure, the area under the ROC curve (AUC), the area under the precision-recall curve (AUCPR), mean square error (MSE). The average accuracy of the proposed models on the original datasets were 89% for CNN and 87% for GRU, while the average accuracy of the proposed models on the balanced datasets were 94% for CNN and 92% for GRU. The results showed that the proposed models on the balanced datasets improves the average accuracy by 5% for both models compared to original datasets. This indicates the positive effects of combining ML techniques with data balancing methods on the performance of defect prediction regarding datasets with imbalanced class distributions.

show abstract

“…Han et al [36] combine code and process metrics as features and confirm that the predictive capabilities of using two features (BD_max and Pre-defects) are comparable to the results of using all 61 features. Öztürk et al [37] suggest that quality metrics are superior in predicting imbalanced data sets than static code metrics. Xia et al [38] search for the most critical software metrics and conclude that fewer than 10 metrics can better perform than utilizing 22 or more metrics.…”

Section: Software Metricmentioning

confidence: 99%

An Empirical Study of Software Metrics Diversity for Cross-Project Defect Prediction

Zhong

Song

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Cross-project defect prediction (CPDP) is a mainstream method estimating the most defect-prone components of software with limited historical data. Several studies investigate how software metrics are used and how modeling techniques influence prediction performance. However, the software’s metrics diversity impact on the predictor remains unclear. Thus, this paper aims to assess the impact of various metric sets on CPDP and investigate the feasibility of CPDP with hybrid metrics. Based on four software metrics types, we investigate the impact of various metric sets on CPDP in terms of F-measure and statistical methods. Then, we validate the dominant performance of CPDP with hybrid metrics. Finally, we further verify the CPDP-OSS feasibility built with three types of metrics (orient-object, semantic, and structural metrics) and challenge them against two current models. The experimental results suggest that the impact of different metric sets on the performance of CPDP is significantly distinct, with semantic and structural metrics performing better. Additionally, trials indicate that it is helpful for CPDP to increase the software’s metrics diversity appropriately, as the CPDP-OSS improvement is up to 53.8%. Finally, compared with two baseline methods, TCA+ and TDSelector, the optimized CPDP model is viable in practice, and the improvement rate is up to 50.6% and 25.7%, respectively.

show abstract

Which type of metrics are useful to deal with class imbalance in software defect prediction?

Cited by 28 publications

References 40 publications

Quality and reliability studies in software defect management: a literature review

Quality and reliability studies in software defect management: a literature review

A Novel Approach for Software Defect Prediction using CNN and GRU Based on SMOTE Tomek Method

An Empirical Study of Software Metrics Diversity for Cross-Project Defect Prediction

Contact Info

Product

Resources

About