A Hybrid Model for Improving Software Cost Estimation in Global Software Development

Accurate software cost estimation in Global Software Development (GSD) remains challenging due to reliance on historical data and expert judgments. Traditional models, such as the Constructive Cost Model (COCOMO II), rely heavily on historical and accurate data. In addition, expert judgment is required to set many input parameters, which can introduce subjectivity and variability in the estimation process. Consequently, there is a need to improve the current GSD models to mitigate reliance on historical data, subjectivity in expert judgment, inadequate consideration of GSD-based cost drivers and limited integration of modern technologies with cost overruns. This study introduces a novel hybrid model that synergizes the COCOMO II with Artificial Neural Networks (ANN) to address these challenges. The proposed hybrid model integrates additional GSD-based cost drivers identified through a systematic literature review and further vetted by industry experts. This article compares the effectiveness of the proposed model with state-of-the-art machine learning-based models for software cost estimation. Evaluating the NASA 93 dataset by adopting twenty-six GSD-based cost drivers reveals that our hybrid model achieves superior accuracy, outperforming existing state-of-the-art models. The findings indicate the potential of combining COCOMO II, ANN, and additional GSD-based cost drivers to transform cost estimation in GSD.