Authors | Year | Focus Area | Techniques/ Models/Methods | Key Findings/Contributions |
Thota et al. [14] | 2020 | Software Defect Prediction | Soft computing-based machine learning techniques | Proposed an efficient approach using soft computing-based machine learning for optimized feature prediction in high-cost software development. |
Ning Li et al. [15] | 2020 | Unsupervised Learning Techniques | Fuzzy C-Means (FCM) and Fuzzy SOMs (FSOMs) in software defect prediction | Identified concerns in research and demonstrated the comparable performance of unsupervised models, particularly FCM and FSOMs, to supervised models in software defect prediction. |
Matloob et al. [16] | 2021 | Ensemble Learning for SDP | Random forest, boosting, bagging methods; Analysis of papers from ACM, IEEE, Springer Link, Science Direct | Revealed commonly employed ensemble methods, highlighted promising frameworks, and emphasized the importance of feature selection in software defect prediction. |
Akimova et al. [17] | 2021 | Deep Learning Techniques | Survey on software defect prediction using deep learning | Highlighted unresolved issues and new trends while examining recent advances in deep learning for software defect prediction. |
Gong et al. [18] | 2021 | Software Dependency Network Analysis | Metrics extracted using Social Network Analysis (SNA) | Identified the impact of Software Dependency Network Analysis (SNA) metrics on software defect prediction models. |
Khan et al. [19] | 2022 | Artificial Neural Networks | Systematic literature review on software defect prediction using ANNs | Analyzed trends and critical aspects of using ANNs in defect prediction, emphasizing the increasing demand for high-quality software systems. |
Goyal [20] | 2022 | Support Vector Machines | Novel filtering technique (FILTER) for imbalanced datasets | Presented a brand-new filtering method to improve Support Vector Machine (SVM)-based defect prediction. |
Uddin et al. [21] | 2022 | Bidirectional Long Short-Term Memory | Bidirectional Long Short-Term Memory networks (BiLSTM) and BERT-based semantic features | Proposed an innovative software defect prediction model (SDP-BB) utilizing BiLSTM and BERT-based semantic features for improved performance. |
Zhao et al. [22] | 2023 | Just-in-Time Software Defect Prediction | Systematic survey on JIT-SDP | Summarized best practices, performed meta-analysis, and suggested future research directions for Just-in-Time Software Defect Prediction (JIT-SDP). |
Giray et al. [23] | 2023 | Deep Learning In SDP | Examination of deep learning in software defect prediction | Proposed recommendations for future research in deep learning for defect prediction. |
Stradowski and Madeyski [24] | 2023 | Business-Driven Mapping Study | Business-driven mapping study on machine learning in SDP | Provided insights into past and potential future research opportunities for businesses in machine learning software defect prediction. |
Hernández-Molinos et al. [25] | 2023 | Bayesian Approaches | Evaluation of Bayesian approaches for software defect prediction | Compared classification results and discussed the robustness of Bayesian algorithms for defect prediction. |