Grey Learning Based Software Stage-Effort Estimation

Software estimation is an important part of successful software project management. A lot of studies have investigated on whole project effort estimation. However there are only a few studies on stage-effort prediction. The stage-effort prediction can be used to dynamically adjust software project schedule, further to help make project be finished on budget. In this paper, we present a grey learning method base on GM(1,1) for stage-effort prediction during software development. We evaluate the proposed method with a large-scale industry software engineering database. The results are very encouraging and indicate the method has considerable potential.