Prediksi Man-Hours Menggunakan Analisis Regression dan Cyclomatic Complexity
DOI:
https://doi.org/10.26418/jp.v11i1.89462Keywords:
Software Development Effort, Cyclomatic Complexity, Man-Hours, RegressionAbstract
Estimasi effort pengembangan perangkat lunak secara akurat merupakan kunci keberhasilan proyek untuk memastikan alokasi sumber daya yang efisien dan penyelesaian tepat waktu. Ketepatan dalam menghitung estimasi effort ini sangat krusial dalam proses pengembangan sistem perangkat lunak untuk mencapai keberhasilan dan mengurangi risiko, seperti risiko reputasi dari suatu organisasi. Metode konvensional seperti expert judgement sering kali kurang konsisten dan rawan kesalahan subjektif. Untuk mengatasi keterbatasan tersebut, penelitian ini mengusulkan pendekatan prediksi man-hours berbasis static code analysis, dengan fokus pada cyclomatic complexity sebagai fitur utama dalam pemodelan machine learning yang dapat diintegrasikan dalam proses rekayasa perangkat lunak untuk mendukung pengambilan keputusan yang lebih tepat dalam perencanaan proyek. Penelitian ini menggunakan data proyek perangkat lunak pada institusi perbankan. Tahapan preprocessing meliputi encode dengan teknik one hot encoding, data cleaning, dan data partitioning. Penelitian ini memanfaatkan cyclomatic complexity dari program perangkat lunak untuk memprediksi upaya dalam variabel man-hours menggunakan model Linear Regression, Lasso Regression, dan Ridge Regression. Evaluasi model dilakukan menggunakan metrik mean absolute percentage error (MAPE), mean absolute error (MAE), mean squared error (MSE), dan R-Squared guna menilai performa prediktif. Berdasarkan pengujian, model Lasso Regression menghasilkan peforma prediktif yang unggul dengan evaluasi menggunakan metrik MAPE 22.2731%, MAE 66.9679, MSE 8538.6359, dan R-Squared 0.98521. Temuan ini menunjukan bahwa pendekatan machine learning yang memanfaatkan analisis cyclomatic complexity mampu meningkatkan akurasi estimasi upaya dibandingkan metode konvensional.References
N. Rankovic, D. Rankovic, M. Ivanovic and L. Lazic, "A New Approach to Software Effort Estimation Using Different Artificial Neural Network Architectures and Taguchi Orthogonal Arrays," IEEE Access, vol. 9, pp. 26926-26936, Feb. 2021.
S. S. Ali, J. Ren, K. Zhang, J. Wu and C. Liu, "Heterogeneous Ensemble Model to Optimize Software Effort Estimation Accuracy," IEEE Access, vol. 11, pp. 27759-27792, Mar. 2023.
P. Suresh Kumar, H. S. Behera, J. Nayak and B. Naik, “A Pragmatic Ensemble Learning Approach for Effective Software Effort Estimation,†Innovations in Systems and Software Engineering, vol.18, pp. 283-299, Jun. 2022.
M. Jawa and S. Meena, "Software Effort Estimation Using Synthetic Minority Over-Sampling Technique for Regression (SMOTER)," 2022 3rd International Conference for Emerging Technology (INCET), pp. 1-6, 2022.
M. Rahman, H. Sarwar, M. A. Kader, T. Gonçalves and T. T. Tin, "Review and Empirical Analysis of Machine Learning-Based Software Effort Estimation," IEEE Access, vol. 12, pp. 85661-85680, May 2024.
L. Cao, "Estimating Efforts for Various Activities in Agile Software Development: An Empirical Study," IEEE Access, vol. 10, pp. 83311-83321, Aug. 2022.
P. Rai, D. K. Verma and S. Kumar, “A Hybrid Model for Prediction of Software Effort Based on Team Size,†IET Software, vol. 15, no. 6, pp. 365–375, Jun. 2021.
A. Jadhav, S. K. Shandilya, I. Izonin and M. Gregus, "Effective Software Effort Estimation Leveraging Machine Learning for Digital Transformation," IEEE Access, vol. 11, pp. 83523-83536, Jul. 2023.
V. V. Hai, H. L. T. K. Nhung, Z. Prokopova, R. Silhavy, and P. Silhavy, “A New Approach to Calibrating Functional Complexity Weight in Software Development Effort Estimation,†Computers, vol. 11, no. 2, pp. 15, Jan. 2022.
M. Rahman, T. Goncalves, and H. Sarwar, “Review of Existing Datasets Used for Software Effort Estimation,†International Journal of Advanced Computer Science and Applications, vol. 14, no. 7, Jan. 2023.
P. V. A G, A. K. K, and V. Varadarajan, “Estimating Software Development Efforts Using a Random Forest-Based Stacked Ensemble Approach,†Electronics, vol. 10, no. 10, pp. 1195, May 2021.
H. D. P. De Carvalho, R. Fagundes and W. Santos, "Extreme Learning Machine Applied to Software Development Effort Estimation," IEEE Access, vol. 9, pp. 92676-92687, Jun. 2021.
P. V. Terlapu, K. K. Raju, G. K. Kumar, G. J. Rao, K. Kavitha and S. Samreen, "Improved Software Effort Estimation Through Machine Learning: Challenges, Applications, and Feature Importance Analysis," IEEE Access, vol. 12, pp. 138663-138701, Sep. 2024.
L. Lavazza, A. Locoro and R. Meli, "Using Machine Learning and Simplified Functional Measures to Estimate Software Development Effort," IEEE Access, vol. 12, pp. 142505-142523, Oct. 2024.
N. Meharunnisa, M. Saqlain, M. Abid, M. Awais and Ž. Stević, “Analysis of Software Effort Estimation by Machine Learning Techniques,†Ingénierie des Systèmes d’Information, vol. 28, no. 6, pp. 1445-1457, Dec. 2023.
A. O. Sousa et al., "Applying Machine Learning to Estimate the Effort and Duration of Individual Tasks in Software Projects," IEEE Access, vol. 11, pp. 89933-89946, Aug. 2023.
A. Bailly et al., “Effects of Dataset Size and Interactions on the Prediction Performance of Logistic Regression and Deep Learning Models,†Computer Methods and Programs in Biomedicine, vol. 213, p. 106504, Oct. 2021.
T. Javdani Gandomani, M. Dashti, H. Zulzalil and A. B. M. Sultan, "Enhancing Software Effort Estimation in the Analogy-Based Approach Through the Combination of Regression Methods," IEEE Access, vol. 12, pp. 152122-152137, Oct. 2024.
E. Yoshino, F. I. Kurniadi and B. Juarto, "Forecasting Rice Production in Indonesia using Regression Techniques: A Comparative Analysis of Support Vector Machine, Linear Regression, and XGBoost Regression," 2023 10th International Conference on ICT for Smart Society (ICISS), pp. 1-5, 2023.
A. Kaushik, P. Kaur, N. Choudhary and Priyanka, “Stacking Regularization in Analogy-Based Software Effort Estimation,†Soft Computing, vol. 26, no. 3, pp. 1197–1216, Jan. 2022.
M. Sharma, R. Chauhan, S. Devliyal and K. R. Chythanya, "House Price Prediction Using Linear and Lasso Regression," 2024 3rd International Conference for Innovation in Technology (INOCON), pp. 1-5, 2024.
H. Liu, X. Gong, L. Liao and B. Li, "Evaluate How Cyclomatic Complexity Changes in the Context of Software Evolution," 2018 IEEE 42nd Annual Computer Software and Applications Conference (COMPSAC), pp. 756-761, 2018.
P. Haindl and G. Weinberger, "Does ChatGPT Help Novice Programmers Write Better Code? Results From Static Code Analysis," IEEE Access, vol. 12, pp. 114146-114156, Aug. 2024.
M. K. Dahouda and I. Joe, "A Deep-Learned Embedding Technique for Categorical Features Encoding," IEEE Access, vol. 9, pp. 114381-114391, Aug. 2021.
X. Lyu, C. Ren, W. Ni, H. Tian, R. P. Liu and E. Dutkiewicz, "Optimal Online Data Partitioning for Geo-Distributed Machine Learning in Edge of Wireless Networks," IEEE Journal on Selected Areas in Communications, vol. 37, no. 10, pp. 2393-2406, Oct. 2019.
H. A. Vidada, E. M. Yuniarno, S. M. S. Nugroho, and U. L. Yuhana, “Prediction of Students’ Ability to Difficulty Level of Problem Based on Linear Method,†JEEE-U (Journal of Electrical and Electronic Engineering-UMSIDA), vol. 5, no. 2, pp. 139–155, Oct. 2021.
S. S. Gautam and V. Singh, "Adaptive Discretization Using Golden Section to Aid Outlier Detection for Software Development Effort Estimation," IEEE Access, vol. 10, pp. 90369-90387, Aug. 2022.
A. Mandre, D. R. Hebbar, J. S. Rao, A. Keshav, S. Kamal and T. Rao, "Early Forest-Fire Detection by Linear Regression, Ridge Regression and Lasso Regression," 2023 International Conference on Computational Intelligence for Information, Security and Communication Applications (CIISCA), pp. 273-277, 2023.
Al-Khowarizmi, S. Efendi, M. K. Nasution and M. Herman, "The Role of Detection Rate in MAPE to Improve Measurement Accuracy for Predicting FinTech Data in Various Regressions," 2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE), pp. 874-879, 2023.
P. Silhavy, R. Silhavy and Z. Prokopova, "Categorical Variable Segmentation Model for Software Development Effort Estimation," IEEE Access, vol. 7, pp. 9618-9626, Jan. 2019.
J. Qi, J. Du, S. M. Siniscalchi, X. Ma and C. -H. Lee, "On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression," IEEE Signal Processing Letters, vol. 27, pp. 1485-1489, Aug. 2020.
