The Untold Impact of Learning Approaches on Software Fault-Proneness Predictions

Ahmad, Mohammad Jamil; Goseva-Popstojanova, Katerina; Lutz, Robyn R.

doi:10.2139/ssrn.4152836

Cited by 2 publications

(2 citation statements)

References 75 publications

(274 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Devine et al [58] extracted the static code metrics and Krishnan et al [14] extracted the change metrics. For the Derby release, the data was extracted by [59] and used Chidamber & Kemerer Objected Oriented CK-OO metrics as static code metrics.…”

Section: Metricsmentioning

confidence: 99%

See 1 more Smart Citation

Explore the effect of size stratification of datasets on software faults proneness prediction performance

Alshehri,

Alshehri

2023

Preprint

View full text Add to dashboard Cite

Size is one of the significant factors associated with bugs, and it has been used to predict software faults. We believe that stratifying software files based on size can play an essential role in improving prediction performance. This study explores the effect of size by stratifying our sample based on each unit’s size and distributing software units in multiple stratified groups based on an equal distribution approach. We stratified the Eclipse Europa project and Derby project files, and we reported the performance of each stratified group and compared them. We used two popular classifiers, decision tree J48 and random forest, to implement this experiment. These classifiers presented similar results on the same group of files. The results indicated that predicting faults with large files is significantly better than predicting those with small files. Furthermore, the files of large groups provide reliable and more stable performance. Finally, we resampled all the stratified groups of the two projects to explore if this can impact the performance. We found that the resampling has no impact on the performance of algorithms using the Europa dataset. However, the effect was significant when the Derby project was used.

show abstract

Section: Metricsmentioning

confidence: 99%

“…Quality data means that internal validity is not violated. This research's data was extracted by early works [14,58,59] and used in other research [2,4,20]. The confidence in the data is very high.…”

Section: Threats To Validitymentioning

confidence: 99%