Perbandingan Metode Untuk Meningkatkan Akurasi COCOMO II Dalam Proyek Perangkat Lunak
Abstract
Cost estimation is a key factor influencing the success of software development projects. Although COCOMO II is commonly adopted due to its ability to generate reasonably accurate estimates, considerable gaps between predicted and actual costs are still often observed. This research evaluates the performance of COCOMO II when combined with several optimization approaches, including BCO and GWO, based on the Turkish dataset. Estimation accuracy is measured using the MMRE metric. The experimental results indicate that the hybrid COCOMO II–GWO–PSO approach outperforms the other methods, achieving an MMRE reduction of up to 29.33%. These outcomes suggest that incorporating optimization techniques into COCOMO II can significantly enhance cost estimation accuracy and offers valuable potential for both academic studies and practical software project management.
References
A. Rahman, “IT PROJECT MANAGEMENT FRAMEWORKS: EVALUATING BEST PRACTICES AND METHODOLOGIES FOR SUCCESSFUL IT PROJECT MANAGEMENT,” ACADEMIC JOURNAL ON SCIENCE, TECHNOLOGY, ENGINEERING & MATHEMATICS EDUCATION, vol. 1, no. 01, pp. 57–76, Oct. 2024, doi: 10.69593/ajaimldsmis.v1i01.128.
S. S. Ali, J. Ren, and J. Wu, “Framework to improve software effort estimation accuracy using novel ensemble rule,” Journal of King Saud University - Computer and Information Sciences, vol. 36, no. 9, Nov. 2024, doi: 10.1016/j.jksuci.2024.102189.
A. A. D. P., L. Azizah, and Y. U.L., “Analisis Ekonomi Perangkat Lunak Dalam Pengembangan Sistem Informasi Pondok Pesantren Islamic Center Elkisi (SIP-E),” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 9, pp. 12–22, May 2022.
A. L. I. Oliveira, P. L. Braga, R. M. F. Lima, and M. L. Cornélio, “GA-based method for feature selection and parameters optimization for machine learning regression applied to software effort estimation,” Inf Softw Technol, vol. 52, no. 11, pp. 1155–1166, 2010, doi: 10.1016/j.infsof.2010.05.009.
V. Khatibi Bardsiri, D. N. A. Jawawi, S. Z. M. Hashim, and E. Khatibi, “A PSO-based model to increase the accuracy of software development effort estimation,” Software Quality Journal, vol. 21, no. 3, pp. 501–526, 2013, doi: 10.1007/s11219-012-9183-x.
S. Chalotra, S. K. Sehra, Y. S. Brar, and N. Kaur, “Tuning of COCOMO Model Parameters by using Bee Colony Optimization,” Indian J Sci Technol, vol. 8, no. July, 2015, doi: 10.17485/ijst/2015/v8i14/70010.
H. L. T. K. Nhung, V. Van Hai, R. Silhavy, Z. Prokopova, and P. Silhavy, “Parametric Software Effort Estimation Based on Optimizing Correction Factors and Multiple Linear Regression,” IEEE Access, vol. 10, pp. 2963–2986, 2022, doi: 10.1109/ACCESS.2021.3139183.
I. C. Suherman, “Implementation of Random Forest Regression for COCOMO II Effort Estimation,” IEEE, pp. 476–481, 2020, doi: 10.1109/iSemantic50169.2020.9234269.
X. Cao, C. Gu, D. Luo, and H. Fu, “Function Optimization of Two Improved Particle Swarm Algorithms,” International Core Journal of Engineering, vol. 11, p. 2025, doi: 10.6919/ICJE.202512_11(12).0020.
I. Journal and I. Computing, “Hybrid gray wolf and particle swarm optimization for feature selection,” vol. 16, no. 3, pp. 831–844, 2020, doi: 10.24507/ijicic.16.03.831.
Full Text: PDF