An Intelligent Approach to Software Cost Prediction
This work addresses software project management challenges for industry practitioners, but it is incremental as it builds on existing models.
The authors tackled software cost prediction by integrating neuro-fuzzy techniques with the COCOMO model, resulting in a model that greatly improves prediction accuracy compared to COCOMO, as validated with industry project data.
Good software cost prediction is important for effective project management such as budgeting, project planning and control. In this paper, we present an intelligent approach to software cost prediction. By integrating the neuro-fuzzy technique with the well-accepted COCOMO model, our approach can make the best use of both expert knowledge and historical project data. Its major advantages include learning ability, good interpretability, and robustness to imprecise and uncertain inputs. The validation using industry project data shows that the model greatly improves prediction accuracy in comparison with the COCOMO model.