Effort estimation remains a critical challenge in Agile Software Development due to the high dynamics of requirement changes and the reliance on friction factors (FF) and dynamic factors (DF) that are inherently subjective, often leading to significant deviations between estimated and actual project effort. This study aims to improve the accuracy of Agile software effort estimation by optimizing FF and DF parameters using a hybrid metaheuristic approach based on Genetic Algorithm and Ant Colony Optimization (GACO). The proposed method integrates a pheromone-based guided search mechanism from Ant Colony Optimization to generate high-quality initial populations, which are subsequently refined through the evolutionary process of Genetic Algorithm to achieve more stable and systematic parameter optimization. Experimental evaluation was conducted using two datasets, namely the Ziauddin dataset representing Agile projects and the Maxwell dataset encompassing cross-domain software projects. The results demonstrate that the GACO approach consistently outperforms the conventional Genetic Algorithm, as indicated by a substantial reduction in Mean Absolute Error from 616.38 to 354.81. Furthermore, statistical validation using the Wilcoxon Signed-Rank Test confirms that the performance difference between the two approaches is statistically significant. These findings indicate that integrating Ant Colony Optimization into Genetic Algorithm effectively enhances the accuracy, stability, and robustness of software effort estimation, thereby supporting more reliable resource planning in Agile software development.
Mahendri et al. (Fri,) studied this question.