Grammar-based Evolutionary Approaches for Software Effort Estimation
Software effort estimation predicts resources needed for a project, including person-hours and costs, and is vital for effective planning and budgeting. This paper compares two grammar-based evolutionary algorithms: grammar-based genetic programming (GGP) and grammatical evolution (GE). Both algorithms are tested on public project datasets and compared with machine learning models such as support vector machines, artificial neural networks, and least-squares linear regression. Results demonstrate that GGP and GE outperform alternative methods across two evaluation metrics, highlighting their effectiveness in estimating software effort.
Authors
- Teresa B. Ludermir (ORCID: https://orcid.org/0000-0002-8980-6742)
- Rodrigo C. Barros (ORCID: https://orcid.org/0000-0002-0782-9482)
- Ferrante Neri (ORCID: https://orcid.org/0000-0002-6100-6532)
- Ricardo Cerri (ORCID: https://orcid.org/0000-0002-2582-1695)
- Péricles Miranda (ORCID: https://orcid.org/0000-0002-5767-7544)
- Márcio P. Basgalupp (ORCID: https://orcid.org/0000-0002-2005-1249)
Institutions
- Universidade Federal de Pernambuco (BR)
- University of Surrey (GB)
- Universidade Federal Rural de Pernambuco (BR)
Publication Details
- Published
- 2025-06-08
- DOI
- https://doi.org/10.1109/cec65147.2025.11042977
- Citations
- 2
- Primary Topic
- Software Engineering Research
- Type
- article
- Field-Weighted Citation Impact
- 6.49
Funders
- Fundação de Amparo à Pesquisa do Estado de São Paulo
- Conselho Nacional de Desenvolvimento Científico e Tecnológico