Prediksi Effort Pada Scrum Project dengan COSMIC Functional Size Menggunakan Huber Regression

• HERI NURCAHYO
• 14210159

---

ABSTRAK

ABSTRAK

Nama              : Heri Nurcahyo

NIM                  : 14210159

Program Studi : Ilmu Komputer

Fakultas           : Teknologi Informasi

Jenjang            : Strata Dua (S2)

Konsentrasi      : Software Engineering

Judul              : “Prediksi Effort Pada Scrum Project dengan COSMIC Functional Size Menggunakan Huber Regression”

Pengembangan perangkat lunak dengan kualitas yang bagus tentu membutuhkan biaya pengembangan yang cukup tinggi, sehingga dibutuhkan cara yang efektif untuk meminimalkan sumber daya seperti orang, waktu, dan anggaran yang dibutuhkan. Prediksi awal perangkat lunak dapat membantu pengembang perangkat lunak dalam mengalokasikan sumber daya yang tersedia dalam mengembangkan perangkat lunak yang efektif dan memiliki kualitas yang tinggi. Saat ini pengembang perangkat lunak sudah mulai menerapkan metode Agile dalam melakukan pengembangan perangkat lunak, yang sebelumnya menggunakan metode waterfall. Pendekatan metode Agile yang sering digunakan dalam pengembangan perangkat lunak adalah metode scrum. Salah satu metode yang cukup baik untuk mengukur dan memperkirakan ukuran fungsional user story pengembangan perangkat lunak adalah metode COSMIC functional size. Metode COSMIC functional size telah banyak digunakan untuk melakukan estimasi effort pada pengembangan perangkat lunak tetapi belum terverifikasi secara baik dalam konteks scrum project. Penelitian ini melakukan investigasi prediksi effort pengembangan perangkat lunak dalam konteks kerangka scrum dengan tanpa menggunakan COSMIC functional size serta Huber Regression. Kesimpulan dari penelitian ini, dengan menggunakan COSMIC Functional Size sebagai atribut independen dapat meningkatkan prediksi effort dalam scrum project dan Metode Huber Regression memberikan hasil prediksi terbaik dengan nilai MAE dataset dengan COSMIC 1.3644, dan tanpa COSMIC 1.3946, nilai RMSE dengan COSMIC 1.8577 dan RMSE tanpa COSMIC 1.8838, nilai MSE dataset dengan COSMIC 3.8782 dan MSE tanpa COSMIC 3.9373, sedangkan nilai R2 dataset dengan COSMIC - 0.0552 dan R2 tanpa COSMIC - 0.0654. Huber Regression bisa digunakan sebagai salah satu algoritma untuk mengatasi dataset dengan data outlier.

KATA KUNCI

Prediksi Effort,Metode scrum,Cosmic Functional Size,Huber Regression

---

DAFTAR PUSTAKA

DAFTAR REFERENSI

[1] D. Tomar and S. Agarwal, “Prediction of Defective Software Modules Using Class Imbalance Learning,” Appl. Comput. Intell. Soft Comput., vol. 2016, pp. 1–12, 2016, doi: 10.1155/2016/7658207.

[2] Z. Sakhrawi, A. Sellami, and N. Bouassida, “An Improved Prediction of Software Enhancement Effort using Correlation-Based Feature Selection and M5P ML Algorithm,” Proc. IEEE/ACS Int. Conf. Comput. Syst. Appl. AICCSA, vol. 2020-Novem, 2020, doi: 10.1109/AICCSA50499.2020.9316495.

[3] M. Fernández-Diego, E. R. Méndez, F. González-Ladrón-De-Guevara, S. Abrahão, and E. Insfran, “An update on effort estimation in agile software development: A systematic literature review,” IEEE Access, vol. 8, no. September, pp. 166768–166800, 2020, doi: 10.1109/ACCESS.2020.3021664.

[4] S. Abdalhamid and A. Mishra, “Adopting of agile methods in software development organizations: Systematic mapping,” TEM J., vol. 6, no. 4, pp. 817–825, 2017, doi: 10.18421/TEM64-22.

[5] M. Arora, S. Verma, Kavita, and S. Chopra, “A Systematic Literature Review of Machine Learning Estimation Approaches in Scrum Projects,” Adv. Intell. Syst. Comput., vol. 1040, no. January, pp. 573–586, 2020, doi: 10.1007/978- 981-15-1451-7_59.

[6] J. Choudhari and U. Suman, “Story Points Based Effort Estimation Model for Software Maintenance,” Procedia Technol., vol. 4, no. December 2012, pp. 761–765, 2012, doi: 10.1016/j.protcy.2012.05.124.

[7] Z. Sakhrawi, “Support vector regression for enhancement effort prediction of Scrum projects from COSMIC functional size Support vector regression for enhancement effort prediction of Scrum,” Innov. Syst. Softw. Eng., no. March, 2022, doi: 10.1007/s11334-021-00420-8.

[8] “COSMIC Measurement Manual for ISO 19761 Part 1?:,” no. February, pp. 1– 17, 2021.

[9] Sklearn.linear_model, “HuberRegressor.” https://scikitlearn.org/stable/modules/generated/sklearn.linear_model.HuberRegressor.html (accessed Jul. 22, 2023).

[10] J. Sutherland, Scrum handbook, Scrum Trai. Inst, 2010.

[11] H. Takeuchi and I. Nonaka, The new new product development game. J. Prod. Innov. Manag, 1986.

[12] Scrum.org, “What is Scrum.” https://www.scrum.org/resources/what-is-scrum.

[13] S. Di Martino, F. Ferrucci, C. Gravino, and F. Sarro, “Assessing the effectiveness of approximate functional sizing approaches for effort estimation,” Inf. Softw. Technol., vol. 123, 2020, doi: 10.1016/j.infsof.2020.106308.

[14] H. T. Jiawei Han, JIan Pei, Data Mining Concepts and Techniques, Fourth. Katey Birtcher, 2023.

[15] S. E. Herni Yulianti, Oni Soesanto, and Yuana Sukmawaty, “Penerapan Metode Extreme Gradient Boosting (XGBOOST) pada Klasifikasi Nasabah Kartu Kredit,” J. Math. Theory Appl., vol. 4, no. 1, pp. 21–26, 2022, doi: 10.31605/jomta.v4i1.1792.

[16] S. Nurdiati and M. K. Najib, “Comparing Five Machine Learning-Based Regression Models for Predicting the Study Period of Mathematics Students at IPB University,” JTAM (Jurnal Teor. dan Apl. Mat., vol. 6, no. 3, p. 530, 2022, doi: 10.31764/jtam.v6i3.8408.

[17] R. E. Cahyono, J. P. Sugiono, and S. Tjandra, “Analisis Kinerja Metode Support Vector Regression (SVR) dalam Memprediksi Indeks Harga Konsumen,” JTIM 57 J. Teknol. Inf. dan Multimed., vol. 1, no. 2, pp. 106–116, 2019, doi: 10.35746/jtim.v1i2.22.

[18] N. D. Maulana, B. D. Setiawan, and C. Dewi, “Implementasi Metode Support Vector Regression (SVR) Dalam Peramalan Penjualan Roti (Studi Kasus?: Harum Bakery),” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 3, no. 3, pp. 2986–2995, 2019.

[19] H. Gong, Y. Sun, X. Shu, and B. Huang, “Use of random forests regression for predicting IRI of asphalt pavements,” Constr. Build. Mater., vol. 189, pp. 890– 897, 2018, doi: 10.1016/j.conbuildmat.2018.09.017.

[20] I. A. Rahmi, F. M. Afendi, and A. Kurnia, “Metode AdaBoost dan Random Forest untuk Prediksi Peserta JKN-KIS yang Menunggak,” Jambura J. Math., vol. 5, no. 1, pp. 83–94, 2023, doi: 10.34312/jjom.v5i1.15869.

[21] J. A. Et. al., “Prediction of House Price Using XGBoost Regression Algorithm,” Turkish J. Comput. Math. Educ., vol. 12, no. 2, pp. 2151–2155, 2021, doi: 10.17762/turcomat.v12i2.1870.

[22] R. Andonie, “Hyperparameter optimization in learning systems,” J. Membr. Comput., vol. 1, no. 4, pp. 279–291, 2019, doi: 10.1007/s41965-019-00023-0.

[23] O. Karal, “Performance comparison of different kernel functions in SVM for different k value in k-fold cross-validation,” Proc. - 2020 Innov. Intell. Syst. Appl. Conf. ASYU 2020, pp. 0–4, 2020, doi: 10.1109/ASYU50717.2020.9259880.

[24] B. G. Marcot and A. M. Hanea, “What is an optimal value of k in k-fold crossvalidation in discrete Bayesian network analysis?,” Comput. Stat., vol. 36, no. 3, pp. 2009–2031, 2021, doi: 10.1007/s00180-020-00999-9.

[25] T. O. Hodson, “Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not,” Geosci. Model Dev., vol. 15, no. 14, pp. 5481–5487, 2022, doi: 10.5194/gmd-15-5481-2022.

[26] Z. Sakhrawi, A. Sellami, N. Bouassida, and S. Tunisie, “Software Enhancement Effort Estimation using Machine Learning Regression Methods,” vol. 12, pp. 412–423, 2020.

[27] M. Gultekin and O. Kalipsiz, “Story Point-Based Effort Estimation Model with Machine Learning Techniques,” Int. J. Softw. Eng. Knowl. Eng., vol. 30, no. 1, pp. 43–66, 2020, doi: 10.1142/S0218194020500035.

[28] Z. Abdelali, H. Mustapha, and N. Abdelwahed, “Investigating the use of random forest in software effort estimation,” Procedia Comput. Sci., vol. 148, pp. 343– 352, 2019, doi: 10.1016/j.procs.2019.01.042.

[29] Z. Sakhrawi, A. Sellami, and N. Bouassida, “Software enhancement effort estimation using correlation-based feature selection and stacking ensemble method,” Cluster Comput., vol. 25, no. 4, pp. 2779–2792, 2022, doi: 10.1007/s10586-021-03447-5.

[30] M. Salmanoglu, T. Hacaloglu, and O. Demirors, “Effort estimation for agile software development: Comparative case studies using COSMIC functional size measurement and story points,” ACM Int. Conf. Proceeding Ser., vol. Part F1319, no. October, pp. 41–49, 2017, doi: 10.1145/3143434.3143450.

[31] A. G. Priya Varshini, K. Anitha Kumari, and V. Varadarajan, “Estimating software development efforts using a random forest-based stacked ensemble approach,” Electron., vol. 10, no. 10, pp. 1–19, 2021, doi: 10.3390/electronics10101195.