Machine Learning Algorithms in Software Defect Prediction Analysis
Prasanth Yalla1, Pasam Meghana2, Regula Chaitanya Sravanthi3, Venkata Naresh Mandhala4
1Prasanth Yalla, Professor, Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Guntur(Dist), India.
2Pasam Meghana, Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Guntur (Dist), India.
3Regula Chaitanya Sravanthi, Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Guntur (Dist), India.
4Venkata Naresh Mandhala, Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Guntur (Dist), India.
Manuscript received on 30 June 2019 | Revised Manuscript received on 05 July 2019 | Manuscript published on 30 July 2019 | PP: 2699-2702 | Volume-8 Issue-9, July 2019 | Retrieval Number: I8979078919/19©BEIESP | DOI: 10.35940/ijitee.I8979.078919
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Programming deformity forecast assumes a vital job in keeping up great programming and decreasing the expense of programming improvement. It encourages venture directors to assign time and assets to desert inclined modules through early imperfection identification. Programming imperfection expectation is a paired characterization issue which arranges modules of programming into both of the 2 classifications: Defect– inclined and not-deformity inclined modules. Misclassifying imperfection inclined modules as not-deformity inclined modules prompts a higher misclassification cost than misclassifying not-imperfection inclined modules as deformity inclined ones. The machine learning calculation utilized in this paper is a blend of Cost-Sensitive Variance Score (CSVS), Cost-Sensitive Laplace Score (CSLS) and Cost-Sensitive Constraint Score (CSCS). The proposed Algorithm is assessed and indicates better execution and low misclassification cost when contrasted and the 3 algorithms executed independently.
Keywords: Cost-Sensitive learning, feature selection, Software defect prediction.
Scope of the Article: Artificial Intelligence and Machine Learning