An Effective Precision Enhancement Approach to Estimate Software Development Cost: Nature Inspired Way

Abstract

In recent years, many researchers and practitioners have explored the possibility of estimating effort and cost using nature inspired algorithms. The purpose of this paper is to investigate the relevance of bacterial foraging optimization algorithm (BFOA) for optimizing the COCOMO model coefficients to estimate the software development time. The goal of this research is to minimize the fitness function value which is the measure of the deflection of estimated time from the real time taken in the software development. Results of the experimental study conducted shows that the proposed approach produces promising results in comparison to COCOMO model and other existing approaches listed in literature. Results show that COCOMO model and other existing approaches are less accurate in comparison to BFOA with MMRE as 0.16 and PRED(25) as 0.9. Thus BFOA can help software industry in predicting accurate and reliable values for planning and maintenance of software project.