Integrated Software Effort Estimation: A Hybrid Approach

Abstract

Risks associated with delivery of a software project and the effort spent on managing these risks are well researched topics. Very few have included this extra effort termed as risk exposure of a project, in the software effort estimate of a project. This research proposes to improve the accuracy of software effort estimates by integrating the risk exposure with the initial effort estimate of the project. A function to calculate integrated effort estimates has been defined and evolutionary algorithms ABC, PSO and GLBPSO have been used to optimize the MMRE. The approach has been tested on two datasets collected from industry, one for waterfall projects, another for agile projects. For both the datasets, integrated effort estimates were more accurate on account of MMRE, standardized accuracy, effect size and R2, than the initial effort estimates. Evolutionary algorithms also gave the optimum weight values at which the MMRE was optimal for both the datasets. These weight values determine the contribution of risk associated with each project cost factor in the risk exposure of the project. Integrated effort estimates have been found to be more accurate, reliable, and comprehensive than the initial effort estimates. Application of evolutionary algorithms help in reducing any bias in the integrated effort estimates.