A systematic literature review on software defect prediction using artificial intelligence: Datasets, Data Validation Methods, Approaches, and Tools

Pachouly, Jalaj; Ahirrao, Swati; Kotecha, Ketan; Selvachandran, Ganeshsree; Abraham, Ajith

doi:10.1016/j.engappai.2022.104773

Cited by 94 publications

(21 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Batool & Khan (2022) and Pachouly et al (2022) published two SLR papers on the use of ML and DL for SDP. Both include studies published between 2010 and 2021 (both papers were submitted to a journal before the end of 2021).…”

Section: Related Workmentioning

confidence: 99%

“…The SLR by Batool & Khan (2022) covers 11 primary studies focusing on DL. Pachouly et al (2022) did not report the number of primary studies particularly using DL; they rather mention that they include 146 primary studies in total. On the other hand, their analysis covers only DBN, CNN, RNN/LSTM, and MLP excluding other types of DL approaches such as encoder-decoder architectures, GAN, and hybrid DL models.…”

Section: Related Workmentioning

confidence: 99%

“…Compared to these two SLRs, this study reflects the state-of-the-art of the use of DL for SDP by analyzing 102 primary studies. Batool & Khan (2022) and Pachouly et al (2022) provided information on the datasets, evaluation metrics, and ML/DL approaches used in SDP. Additionally, Pachouly et al (2022) provided an analysis on the tools/frameworks and challenges related to datasets, such as class imbalance.…”

Section: Related Workmentioning

confidence: 99%

“…Batool & Khan (2022) and Pachouly et al (2022) provided information on the datasets, evaluation metrics, and ML/DL approaches used in SDP. Additionally, Pachouly et al (2022) provided an analysis on the tools/frameworks and challenges related to datasets, such as class imbalance. This study includes analyses on these items except tools and frameworks and additionally presents information on the representation of source code, granularity level of prediction, validation approaches, and reproducibility package.…”

Section: Related Workmentioning

confidence: 99%

“…This study includes analyses on these items except tools and frameworks and additionally presents information on the representation of source code, granularity level of prediction, validation approaches, and reproducibility package. Finally, this study includes a qualitative analysis on the challenges and proposed solutions on the whole aspects of SDP unlike the analysis of Pachouly et al (2022) focusing on the challenges related to datasets.…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

On the use of deep learning in software defect prediction

Giray¹,

Bennin

Köksal

et al. 2023

Journal of Systems and Software

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

On the use of deep learning in software defect prediction

Giray¹,

Bennin

Köksal

et al. 2023

Journal of Systems and Software

View full text Add to dashboard Cite

Strategic management of employee churn: Leveraging machine learning for sustainable development and competitive advantage in emerging markets

Agrawal,

Ghangale,

Dhar

et al. 2024

Bus Strat Dev

View full text Add to dashboard Cite

Employee churn or attrition presents significant challenges, especially in emerging markets, where it can disrupt business operations and inflate recruitment costs. This research leverages machine learning techniques to predict employee churn, focusing on developing sustainable and inclusive retention strategies that enhance business competitiveness. By analyzing a range of predictive algorithms and key variables associated with churn, the study identifies the most effective models for predicting attrition. A comprehensive exploratory data analysis was conducted using an indigenous machine learning model, offering practical insights for human resource management in emerging markets. The findings align with the sustainable development goals (SDGs), promoting decent work, and economic growth. This study contributes to business strategy by proposing data‐driven solutions for workforce stability and sustainable development.

show abstract

Neighbor cleaning learning based cost‐sensitive ensemble learning approach for software defect prediction

Li,

Su,

Zhao

2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThe class imbalance problem in software defect prediction datasets leads to prediction results that are biased toward the majority class, and the class overlap problem leads to fuzzy boundaries for classification decisions, both of which affect the model's prediction performance on the dataset. A neighbor cleaning learning (NCL) is an effective technique for defect prediction. To solve the class overlap problem and class imbalance problem, the NCL‐based cost‐sensitive ensemble learning approach for software defect prediction (NCL_CSEL) model is proposed. First, the bootstrap resampled data are trained using the base classifier. Subsequently, multiple classifiers are integrated by a static ensemble to obtain the final classification results. As the base classifier, the Adaptive Boosting (AdaBoost) classifier combining NCL and cost‐sensitive learning is proposed, and the class overlap problem and class imbalance problem are solved by balancing the proportion of overlap sample removal in NCL and the size of the cost factor in cost‐sensitive learning. Specifically, the NCL algorithm is used to initialize the sample weights, while the cost‐sensitive method is employed to update the sample weights. Experiments based on the NASA dataset and AEEEM dataset show that the defect prediction model can improve the bal value by approximately 7% and the AUC value by 9.5% when the NCL algorithm is added. NCL_CSEL can effectively solve the class imbalance problem and significantly improve the prediction performance compared with existing methods for solving the class imbalance problem.

show abstract

A systematic literature review on software defect prediction using artificial intelligence: Datasets, Data Validation Methods, Approaches, and Tools

Cited by 94 publications

References 87 publications

On the use of deep learning in software defect prediction

On the use of deep learning in software defect prediction

Strategic management of employee churn: Leveraging machine learning for sustainable development and competitive advantage in emerging markets

Neighbor cleaning learning based cost‐sensitive ensemble learning approach for software defect prediction

Contact Info

Product

Resources

About