Software development effort estimation modeling using a combination of fuzzy-neural network and differential evolution algorithm

Abstract

Software cost estimation has always been a serious challenge lying ahead of software teams that should be seriously considered in the early stages of a project. Lack of sufficient information on final requirements, as well as the existence of inaccurate and vague requirements, are among the main reasons for unreliable estimations in this area. Though several effort estimation models have been proposed over the recent decade, an increase in their accuracy has always been a controversial issue, and researchers' efforts in this area are still ongoing. This study presents a new model based on a hybrid of adaptive network-based fuzzy inference system (ANFIS) and differential evolution (DE) algorithm. This model tries to obtain a more accurate estimation of software development effort that is capable of presenting a better estimate within a wide range of software projects compared to previous works. The proposed method outperformed other optimization algorithms adopted from the genetic algorithm, evolutionary algorithms, meta-heuristic algorithms, and neuro-fuzzy based optimization algorithms, and could improve the accuracy using MMRE and PRED (0.25) criteria up to 7%.