Hybrid Model for Improving the Accuracy of Software Development Team Effort Estimation with Genetic Algorithm-Optimized Regression Ensembles

• Wilamis Kleiton Nunes da Silva Cesar School

Resumo

This thesis plan aims to propose a Hybrid Model for Software Development Team Effort estimation by integrating Regression Ensembles and GA. The methodology will consist of an experimental evaluation of the proposed machine learning model using multiple datasets from the PROMISE repository, employing the evaluation metrics MAE, RMSE, MdMRE, PRED(25), and R2 score to analyze predictive performance.

Referências

Abnane, I., Idri, A., Chlioui, I., and Abran, A. (2023). Evaluating ensemble imputation in software effort estimation. Empirical Software Engineering, 28(2):56.

Beesetti, K. K., Bilgaiyan, S., and Mishra, B. S. P. (2023). Software effort estimation through ensembling of base models in machine learning using a voting estimator. International Journal of Advanced Computer Science and Applications, 14(2).

Boston Consulting Group (2024). Software projects don’t have to be late, costly, and irrelevant. [link]. Acesso em: 26 jan. 2025.

de Barcelos Tronto, I. F., da Silva, J. D. S., and Sant’Anna, N. (2006). Uma investigação de modelos de estimativas de esforço em gerenciamento de projeto de software. In Anais do XX Simpósio Brasileiro de Engenharia de Software, pages 224–238. SBC.

Easterbrook, S., Singer, J., Storey, M.-A., and Damian, D. (2008). Selecting empirical methods for software engineering research. Guide to advanced empirical software engineering, pages 285–311.

Friedman, M. (1992). The use of ranks to avoid the assumption of normality implicit in the analysis of variance. In KOTZ, S. and JOHNSON, N. L., editors, Breakthroughs in Statistics: Methodology and Distribution, pages 205–227. Springer, New York.

Goyal, S. (2022). Effective software effort estimation using heterogenous stacked ensemble. In 2022 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems (SPICES), volume 1, pages 584–588. IEEE.

Hameed, S., Elsheikh, Y., and Azzeh, M. (2023). An optimized case-based software project effort estimation using genetic algorithm. Information and Software Technology, 153:107088.

Khan, M. S., Jabeen, F., Ghouzali, S., Rehman, Z., Naz, S., and Abdul, W. (2021). Metaheuristic algorithms in optimizing deep neural network model for software effort estimation. IEEE Access, 9:60309–60327.

Mohsin, Z. R. (2021). Application of artificial neural networks in prediction of software development effort. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(14):4186–4202.

Rajput, Y., Razi, M. H., and Sharma, A. K. (2025). A comparative analysis of different machine learning techniques used in software effort estimation. In 2025 2nd International Conference on Computational Intelligence, Communication Technology and Networking (CICTN), pages 385–393. IEEE.

Reddy, S. H. V. and Thinakaran, K. (2022). Novel software effort estimation method using naive bayes technique. In 2022 3rd International Conference on Smart Electronics and Communication (ICOSEC), pages 1600–1602. IEEE.

Silva, W. K. N. d., Nascimento, B. R. d., Miranda, P., and Vicente, E. P. (2025). Predictive regression models of machine learning for effort estimation in software teams: An experimental study. In Anais do 27th International Conference on Enterprise Information Systems (ICEIS 2025), pages 219–226, Setúbal, Portugal. SciTePress.

STANDISH GROUP (2020). Chaos report 2020: Beyond infinity. Disponível em: [link]. Acesso em: 26 jul. 2025.

Wen, J., Li, S., Lin, Z., Hu, Y., and Huang, C. (2012). Systematic literature review of machine learning based software development effort estimation models. Information and Software Technology, 54(1):41–59.

Wilcoxon, F. (1992). Individual comparisons by ranking methods. In KOTZ, S. and JOHNSON, N. L., editors, Breakthroughs in Statistics: Methodology and Distribution, pages 196–202. Springer, New York.