The Effect of the Dataset Size on the Accuracy of Software Defect Prediction Models: An Empirical Study
The ongoing development of computer systems requires massive software projects. Running the components of these huge projects for testing purposes might be a costly process; therefore, parameter estimation can be used instead. Software defect prediction models are crucial for software quality assura...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Asociación Española para la Inteligencia Artificial
2021-10-01
|
| Series: | Inteligencia Artificial |
| Subjects: | |
| Online Access: | https://journal.iberamia.org/index.php/intartif/article/view/638 |
| _version_ | 1818902392683364352 |
|---|---|
| author | Mohammad Alshayeb Mashaan A. Alshammari |
| author_facet | Mohammad Alshayeb Mashaan A. Alshammari |
| author_sort | Mohammad Alshayeb |
| collection | DOAJ |
| description | The ongoing development of computer systems requires massive software projects. Running the components of these huge projects for testing purposes might be a costly process; therefore, parameter estimation can be used instead. Software defect prediction models are crucial for software quality assurance. This study investigates the impact of dataset size and feature selection algorithms on software defect prediction models. We use two approaches to build software defect prediction models: a statistical approach and a machine learning approach with support vector machines (SVMs). The fault prediction model was built based on four datasets of different sizes. Additionally, four feature selection algorithms were used. We found that applying the SVM defect prediction model on datasets with a reduced number of measures as features may enhance the accuracy of the fault prediction model. Also, it directs the test effort to maintain the most influential set of metrics. We also found that the running time of the SVM fault prediction model is not consistent with dataset size. Therefore, having fewer metrics does not guarantee a shorter execution time. From the experiments, we found that dataset size has a direct influence on the SVM fault prediction model. However, reduced datasets performed the same or slightly lower than the original datasets. |
| first_indexed | 2024-12-19T20:34:55Z |
| format | Article |
| id | doaj.art-8437f3a053d44ca8bd13389c3929b4b3 |
| institution | Directory Open Access Journal |
| issn | 1137-3601 1988-3064 |
| language | English |
| last_indexed | 2024-12-19T20:34:55Z |
| publishDate | 2021-10-01 |
| publisher | Asociación Española para la Inteligencia Artificial |
| record_format | Article |
| series | Inteligencia Artificial |
| spelling | doaj.art-8437f3a053d44ca8bd13389c3929b4b32022-12-21T20:06:34ZengAsociación Española para la Inteligencia ArtificialInteligencia Artificial1137-36011988-30642021-10-01246810.4114/intartif.vol24iss68pp72-88The Effect of the Dataset Size on the Accuracy of Software Defect Prediction Models: An Empirical StudyMohammad Alshayeb0Mashaan A. Alshammari1University of Ha'il, Ha'il, Saudi ArabiaKing Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia The ongoing development of computer systems requires massive software projects. Running the components of these huge projects for testing purposes might be a costly process; therefore, parameter estimation can be used instead. Software defect prediction models are crucial for software quality assurance. This study investigates the impact of dataset size and feature selection algorithms on software defect prediction models. We use two approaches to build software defect prediction models: a statistical approach and a machine learning approach with support vector machines (SVMs). The fault prediction model was built based on four datasets of different sizes. Additionally, four feature selection algorithms were used. We found that applying the SVM defect prediction model on datasets with a reduced number of measures as features may enhance the accuracy of the fault prediction model. Also, it directs the test effort to maintain the most influential set of metrics. We also found that the running time of the SVM fault prediction model is not consistent with dataset size. Therefore, having fewer metrics does not guarantee a shorter execution time. From the experiments, we found that dataset size has a direct influence on the SVM fault prediction model. However, reduced datasets performed the same or slightly lower than the original datasets.https://journal.iberamia.org/index.php/intartif/article/view/638Software Defect PredictionSupport Vector MachineFeature Selection |
| spellingShingle | Mohammad Alshayeb Mashaan A. Alshammari The Effect of the Dataset Size on the Accuracy of Software Defect Prediction Models: An Empirical Study Inteligencia Artificial Software Defect Prediction Support Vector Machine Feature Selection |
| title | The Effect of the Dataset Size on the Accuracy of Software Defect Prediction Models: An Empirical Study |
| title_full | The Effect of the Dataset Size on the Accuracy of Software Defect Prediction Models: An Empirical Study |
| title_fullStr | The Effect of the Dataset Size on the Accuracy of Software Defect Prediction Models: An Empirical Study |
| title_full_unstemmed | The Effect of the Dataset Size on the Accuracy of Software Defect Prediction Models: An Empirical Study |
| title_short | The Effect of the Dataset Size on the Accuracy of Software Defect Prediction Models: An Empirical Study |
| title_sort | effect of the dataset size on the accuracy of software defect prediction models an empirical study |
| topic | Software Defect Prediction Support Vector Machine Feature Selection |
| url | https://journal.iberamia.org/index.php/intartif/article/view/638 |
| work_keys_str_mv | AT mohammadalshayeb theeffectofthedatasetsizeontheaccuracyofsoftwaredefectpredictionmodelsanempiricalstudy AT mashaanaalshammari theeffectofthedatasetsizeontheaccuracyofsoftwaredefectpredictionmodelsanempiricalstudy AT mohammadalshayeb effectofthedatasetsizeontheaccuracyofsoftwaredefectpredictionmodelsanempiricalstudy AT mashaanaalshammari effectofthedatasetsizeontheaccuracyofsoftwaredefectpredictionmodelsanempiricalstudy |