Semi-Automated Approach for Evaluation of Software Defect Management Process using ML Approach

Abstract

Evaluation of the software development process is crucial for enhancing software production and product quality inside a company. Traditional methods that rely on manual qualitative evaluations (such as artifact inspection) are flawed because they are (i) time-consuming, (ii) hampered by authority limits, and (iii) frequently subjective. This research introduces a unique machine learning-based semi-automated method for software process assessment to get over these constraints. We specifically frame the issue as a sequence classification challenge that can be resolved using machine learning methods. We develop a new quantitative indicator to impartially assess the effectiveness and quality of a software process based on the framework. We use it to assess the defect management procedure used in four actual industrial software projects in order to verify the effectiveness of our methodology. Our empirical findings demonstrate the effectiveness and potential of our technique in offering a reliable, quantitative assessment of software process.