A Fuzzy Approach for Software Effort Estimation

Abstract

The most significant activity in software project management is Software development effort prediction. Ubiquitous availability of COCOMO model revealed many possibilities with a perspective of optimization of cost. Cost drivers have significant influence on the COCOMO and this research investigates the role of cost drivers in improving the precision of effort estimation Fuzzy logic has been applied to the COCOMO using membership functions to represent the cost drivers. Using Trapezoidal Membership Function (TMF), a few attributes are assigned the maximum degree of compatibility when they should be assigned lower degrees. To overcome the above limitation, in this paper, it is proposed to use Gaussian Membership Function (GMF) for the cost drivers by studying the behavior of COCOMO cost drivers. It has been found that Gaussian function is performing better than the trapezoidal function, as it demonstrates a smoother transition in its intervals, and the achieved results were closer to the actual effort.