Machine Learning Based Approach for Software Defect Prediction using Hyperparameter

Abstract

Software Defect Prediction (SDP) is an assessment done for software or IT (Information Technology) solution. it enables stakeholders to judge its quality, functionality, scalability, reliability, information security and availability during SDLC of software. With digitalization of business and processes, its scope has multiplied since business look for reliable and good quality solutions for important application. Since most of these activities are done manually, it has been an area of research in software engineering. Researchers have been trying to predict defects from code metrics taken from PROMISE software repository dataset like CM1, JM1 and KC1. In this paper we have developed Model based on hyperparameter tuning for well accepted Machine Learning classifier to predict Software defects and found it better compared to many earlier proposed Model.