Fuzzy Logic Based Framework for Software Development Effort Estimation

Software development effort estimation is among one of the most challenging jobs that software developers need to perform. Due to the lack of information during the early stages of software development, the developers often express their inability to estimate accurately the effort, cost and schedule of the software under consideration. This inaccuracy in estimation leads to monetary losses as well delay in delivery of the product. In this paper, a soft computing based technique is explored to overcome the problems of uncertainty and imprecision resulting in improved process of software development effort estimation. In doing so, fuzzy logic is applied to different parameters of Constructive Cost Model (COCOMO) II. Results shows that the value of MMRE (Mean of Magnitude of Relative Error) and pred obtained by means of applying fuzzy logic is much better than of MMRE of algorithmic model. The validation of results is carried out on COCOMO dataset.