Cross-Project Defect Prediction with Metrics Selection and Balancing Approach
In software development, defects influence the quality and cost in an undesirable way. Software defect prediction (SDP) is one of the techniques which improves the software quality and testing efficiency by early identification of defects(bug/fault/error). Thus, several experiments have been suggest...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2022-12-01
|
| Series: | Applied Computer Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/acss-2022-0015 |
| _version_ | 1811171477703098368 |
|---|---|
| author | Nevendra Meetesh Singh Pradeep |
| author_facet | Nevendra Meetesh Singh Pradeep |
| author_sort | Nevendra Meetesh |
| collection | DOAJ |
| description | In software development, defects influence the quality and cost in an undesirable way. Software defect prediction (SDP) is one of the techniques which improves the software quality and testing efficiency by early identification of defects(bug/fault/error). Thus, several experiments have been suggested for defect prediction (DP) techniques. Mainly DP method utilises historical project data for constructing prediction models. SDP performs well within projects until there is an adequate amount of data accessible to train the models. However, if the data are inadequate or limited for the same project, the researchers mainly use Cross-Project Defect Prediction (CPDP). CPDP is a possible alternative option that refers to anticipating defects using prediction models built on historical data from other projects. CPDP is challenging due to its data distribution and domain difference problem. The proposed framework is an effective two-stage approach for CPDP, i.e., model generation and prediction process. In model generation phase, the conglomeration of different pre-processing, including feature selection and class reweights technique, is used to improve the initial data quality. Finally, a fine-tuned efficient bagging and boosting based hybrid ensemble model is developed, which avoids model over -fitting/under-fitting and helps enhance the prediction performance. In the prediction process phase, the generated model predicts the historical data from other projects, which has defects or clean. The framework is evaluated using25 software projects obtained from public repositories. The result analysis shows that the proposed model has achieved a 0.71±0.03 f1-score, which significantly improves the state-of-the-art approaches by 23 % to 60 %. |
| first_indexed | 2024-04-10T17:14:34Z |
| format | Article |
| id | doaj.art-f07662aa3faf40fcbd1c33bb7db7ad37 |
| institution | Directory Open Access Journal |
| issn | 2255-8691 |
| language | English |
| last_indexed | 2024-04-10T17:14:34Z |
| publishDate | 2022-12-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Applied Computer Systems |
| spelling | doaj.art-f07662aa3faf40fcbd1c33bb7db7ad372023-02-05T18:30:18ZengSciendoApplied Computer Systems2255-86912022-12-0127213714810.2478/acss-2022-0015Cross-Project Defect Prediction with Metrics Selection and Balancing ApproachNevendra Meetesh0Singh Pradeep1Department of Computer Science & Engineering, National Institute of Technology, Raipur, IndiaDepartment of Computer Science & Engineering, National Institute of Technology, Raipur, IndiaIn software development, defects influence the quality and cost in an undesirable way. Software defect prediction (SDP) is one of the techniques which improves the software quality and testing efficiency by early identification of defects(bug/fault/error). Thus, several experiments have been suggested for defect prediction (DP) techniques. Mainly DP method utilises historical project data for constructing prediction models. SDP performs well within projects until there is an adequate amount of data accessible to train the models. However, if the data are inadequate or limited for the same project, the researchers mainly use Cross-Project Defect Prediction (CPDP). CPDP is a possible alternative option that refers to anticipating defects using prediction models built on historical data from other projects. CPDP is challenging due to its data distribution and domain difference problem. The proposed framework is an effective two-stage approach for CPDP, i.e., model generation and prediction process. In model generation phase, the conglomeration of different pre-processing, including feature selection and class reweights technique, is used to improve the initial data quality. Finally, a fine-tuned efficient bagging and boosting based hybrid ensemble model is developed, which avoids model over -fitting/under-fitting and helps enhance the prediction performance. In the prediction process phase, the generated model predicts the historical data from other projects, which has defects or clean. The framework is evaluated using25 software projects obtained from public repositories. The result analysis shows that the proposed model has achieved a 0.71±0.03 f1-score, which significantly improves the state-of-the-art approaches by 23 % to 60 %.https://doi.org/10.2478/acss-2022-0015adaboostensemblerandom forestsmote |
| spellingShingle | Nevendra Meetesh Singh Pradeep Cross-Project Defect Prediction with Metrics Selection and Balancing Approach Applied Computer Systems adaboost ensemble random forest smote |
| title | Cross-Project Defect Prediction with Metrics Selection and Balancing Approach |
| title_full | Cross-Project Defect Prediction with Metrics Selection and Balancing Approach |
| title_fullStr | Cross-Project Defect Prediction with Metrics Selection and Balancing Approach |
| title_full_unstemmed | Cross-Project Defect Prediction with Metrics Selection and Balancing Approach |
| title_short | Cross-Project Defect Prediction with Metrics Selection and Balancing Approach |
| title_sort | cross project defect prediction with metrics selection and balancing approach |
| topic | adaboost ensemble random forest smote |
| url | https://doi.org/10.2478/acss-2022-0015 |
| work_keys_str_mv | AT nevendrameetesh crossprojectdefectpredictionwithmetricsselectionandbalancingapproach AT singhpradeep crossprojectdefectpredictionwithmetricsselectionandbalancingapproach |