Software development effort estimation is considered a fundamental task for software development\nlife cycle as well as for managing project cost, time and quality. Therefore, accurate estimation\nis a substantial factor in projects success and reducing the risks. In recent years, software effort\nestimation has received a considerable amount of attention from researchers and became a\nchallenge for software industry. In the last two decades, many researchers and practitioners proposed\nstatistical and machine learning-based models for software effort estimation. In this work,\nFirefly Algorithm is proposed as a metaheuristic optimization method for optimizing the parameters\nof three COCOMO-based models. These models include the basic COCOMO model and other\ntwo models proposed in the literature as extensions of the basic COCOMO model. The developed\nestimation models are evaluated using different evaluation metrics. Experimental results show\nhigh accuracy and significant error minimization of Firefly Algorithm over other metaheuristic\noptimization algorithms including Genetic Algorithms and Particle Swarm Optimization.
Loading....