Comparative Analysis of COCOMO81 using Various Fuzzy Membership Functions

Software Estimation has always been one of the prompting challenges for the software engineers. Software cost estimation techniques helps in forecasting the amount of effort required to develop software. Constructive Cost Model (COCOMO) is considered to be the most widely used model for effort estimation. Cost drivers have great influence on the COCOMO and this paper investigates the role of cost drivers in improving the precision of effort estimation using different membership functions. Fuzzy logic-based estimation models are more suitable when formless and inaccurate information is to be used. The proposed fuzzy COCOMO model consists of a collection of linear submodels joined together smoothly using fuzzy membership functions. This paper focus on the comparative analysis of COCOMO81 using various fuzzy membership functions. The present work is based on COCOMO81 dataset and the experimental part of the study illustrates the approach and compares it with the standard version of the COCOMO81. It has been found that Fuzzy based COCOMO model gives better performance when compared to the COCOMO81, demonstrating a smoother transition in its intervals, and the achieved results were closer to the actual effort.