The adjusted analogy-based software effort estimation based on similarity distances

摘要: Analogy-based estimation is a widely adopted problem solving method that has been evaluated and confirmed in software effort or cost domains. The similarity measures between pairs of projects play critical role the analogy-based models. Such model calculates distance project being estimated each historical projects, then retrieves most similar for generating an estimate. Although there exist numerous models literature, little theoretical experimental works have reported on deriving estimate from adjustment reused based distance. present paper investigates effect improvement accuracy estimations when genetic algorithm to adjust distances projects. empirical results show applying suitable linear feasible approach improving estimates. It also demonstrates proposed comparable with those obtained using other methods.