Inferencia estadística integrada para la estimación del esfuerzo de software basada en datos históricos incompletos.

Marco Antonio Guzmán López; René Santaolaya Salgado; Vitervo López Caballero; Blanca Dina Valenzuela Robles

doi:10.46377/dilemas.v13i3.4943

Marco Antonio Guzmán López Instituto Tecnológico y de Estudios Superiores de Monterrey https://orcid.org/0000-0002-1500-5635
René Santaolaya Salgado Centro Nacional de Investigación y Desarrollo Tecnológico https://orcid.org/0000-0003-3408-5818
Vitervo López Caballero Centro Nacional de Investigación y Desarrollo Tecnológico https://orcid.org/0000-0002-1942-9558
Blanca Dina Valenzuela Robles Centro Nacional de Investigación y Desarrollo Tecnológico https://orcid.org/0000-0002-7303-3052

DOI: https://doi.org/10.46377/dilemas.v13i3.4943

Palabras clave: estimación por analogía, selección de características, técnicas de imputación, datos faltantes, estadísticas de éxito de proyectos

Resumen

La estimación inexacta del esfuerzo en el desarrollo de software genera incumplimientos funcionales y desviaciones significativas en costo, tiempo y recursos previstos. Para atender esta problemática, el presente estudio propone un esquema novedoso de imputación de datos denominado Inferencia Estadística Integrada (ISI), el cual combina la imputación por media o moda con un método propuesto basado en información estadística de proyectos de software (ISPI). El esquema ISI permitió imputar el 29% de los datos faltantes en una muestra aleatoria del repositorio ISBSG. Adicionalmente, se desarrolló un modelo de regresión para la predicción del esfuerzo, alcanzando un valor MMRE del 14,05%, considerado aceptable en la literatura.

Citas

Abnane, I., & Idri, A. (2016). Evaluating Fuzzy Analogy on incomplete software projects data. 1-8. https://doi.org/10.1109/SSCI.2016.7849922.

Abnane, I., & Idri, A. (2018). Improved Analogy-Based Effort Estimation with Incomplete Mixed Data. 2018 Federated Conference on Computer Science and Information Systems (FedCSIS), 1015- 1024. https://ieeexplore.ieee.org/document/8511226

Amazal, F. A., Idri, A., & Abran, A. (2019). Analysis of cluster center initialization of 2FA- kprototypes analogy-based software effort estimation. Journal of Software: Evolution and Process, 31(12), e2180. https://doi.org/10.1002/smr.2180.

Azzeh, M., & Elsheikh, Y. (2017). Learning best K analogies from data distribution for case-based software effort estimation (arXiv:1703.04567). arXiv. https://doi.org/10.48550/arXiv.1703.04567.

Chinthanet, B., Phannachitta, P., Kamei, Y., Leelaprute, P., Rungsawang, A., Ubayashi, N., & Matsumoto, K. (2016). A review and comparison of methods for determining the best analogies in analogy-based software effort estimation. Proceedings of the 31st Annual ACM Symposium on Applied Computing, 1554-1557. https://doi.org/10.1145/2851613.2851974.

Ezghari, S., & Zahi, A. (2018). Uncertainty management in software effort estimation using a consistent fuzzy analogy-based method. Applied Soft Computing, 67, 540-557. https://doi.org/10.1016/j.asoc.2018.03.022.

González-Ladrón-de-Guevara, F., Fernández-Diego, M., & Lokan, C. (2016). The usage of ISBSG data fields in software effort estimation: A systematic mapping study. Journal of Systems and Software, 113, 188-215. https://doi.org/10.1016/j.jss.2015.11.040.

Hosni, M., Idri, A., & Abran, A. (2017). Investigating heterogeneous ensembles with filter feature selection for software effort estimation. Proceedings of the 27th International Workshop on Software Measurement and 12th International Conference on Software Process and Product Measurement, 207- 220. https://doi.org/10.1145/3143434.3143456.

Huang, J., Li, Y. F., Keung, J. W., Yu, Y. T., & Chan, W. K. (2017). An empirical analysis of three- stage data-preprocessing for analogy-based software effort estimation on the ISBSG data. Proceedings - 2017 IEEE International Conference on Software Quality, Reliability and Security, QRS 2017, 442- 449. https://doi.org/10.1109/QRS.2017.54.

Idri, A., Abnane, I., & Abran, A. (2016). Missing data techniques in analogy-based software development effort estimation. Journal of Systems and Software, 117, 595-611. https://doi.org/10.1016/j.jss.2016.04.058.

Iok Kuan, S. W. (2017). Factors on Software Effort Estimation. International Journal of Software Engineering & Applications, 8(1), 23-32. https://doi.org/10.5121/ijsea.2017.8103.

McConnell, S. (2006). Software estimation: Demystifying the black art. Microsoft Press.

Resmi, V., & Vijayalakshmi, S. (2019). Analogy-Based Approaches to Improve Software Project Effort Estimation Accuracy. Journal of Intelligent Systems, 29(1), 1468-1479. https://doi.org/10.1515/jisys-2019-0023.

Shah, M. A., Jawawi, D. N. A., Isa, M. A., Wakil, K., & Younas, M. (2019). MINN : A Missing Data Imputation Technique for Analogy-based Effort Estimation. International Journal of Advanced Computer Science and Applications, 10(2), 12. https://doi.org/10.14569/IJACSA.2019.0100230.

Sigweni, B. B. (2016). An investigation of feature weighting algorithms and validation techniques using blind analysis for analogy-based estimation [Thesis, Brunel University London]. http://bura.brunel.ac.uk/handle/2438/12797.

Wu, D., Li, J., & Bao, C. (2018). Case-based reasoning with optimized weight derived by particle swarm optimization for software effort estimation. Soft Computing, 22(16), 5299-5310. https://doi.org/10.1007/s00500-017-2985-9.