Analysis: The application of different Machine Learning Techniques for Software effort Estimation: Examining the use of machine learning for software effort estimation

Abstract

The purpose of providing estimates in software projects is to aid professionals in makingmore accurate predictions about the costs of software development, which in turn affects the efficacy ofthe software process's preparatory and operational activities. However, software developmentorganizations sometimes struggle to provide estimates that accurately reflect the true work required tocarry out the tasks associated with a software project. Despite the fact that methods for estimating laborhave been presented in the literature, doing so remains difficult. Machine learning (ML) methods haverecently been used to address this issue. With the use of ML methods, datasets containing the results ofpreviously completed projects may be used to generate more accurate estimates. In this research, wehave explored the application of machine learning methods to the problem of estimating the timerequired to develop software. The need for software projects is growing, necessitating the constantevolution of both computer software and hardware. Competition among businesses to provide highqualitygoods in a timely manner at a reasonable price has intensified as demand for software projectshas grown. The purpose of this study is to carefully examine ML models by looking at them from fourdifferent angles ML method, estimate accuracy, model comparison, and estimation context.Researchers will find this paper's review of effort estimate using machine learning methods helpful incharting the course of future work on the use of machine learning to the estimation of softwaredevelopment efforts.