Title: Developing software predictive model for examining the software bugs using machine learning
Authors: Swati Singh; Monica Mehrotra; Taran Singh Bharati
Addresses: Jamia Millia Islamia, Delhi, India ' Jamia Millia Islamia, Delhi, India ' Jamia Millia Islamia, Delhi, India
Abstract: Software faults prediction is an emerging research area in the software engineering. It is an important issue for IT industry and professionals. We need prior information of an application for faults or faulty modules in traditional approach to determine software faults. If we use machine leaching techniques then we can easily automate the models enabling application software to knowingly predict and recover the application software faults. This capability type features helps in developing the application software to execute more productively and minimise faults, cost and time. In the scenario of this research, we are considering the software appropriate models that predicted development models using subsets of artificial intelligence-based approaches. Besides, we utilise noticeable benchmark techniques for evaluation of performance for software predictive models. However, researchers and software exponents can accomplish independent perception from this research and can pick out automated tasks for their deliberated application.
Keywords: machine learning; software predictive model; software faults.
DOI: 10.1504/IJGUC.2024.136726
International Journal of Grid and Utility Computing, 2024 Vol.15 No.1, pp.44 - 52
Received: 26 Jan 2023
Accepted: 09 Jul 2023
Published online: 19 Feb 2024 *