On an optimal analogy-based software effort estimation

被引:20
作者
Phannachitta, Passakorn [1 ]
机构
[1] Chiang Mai Univ, Coll Arts Media & Technol, 239 Suthep, Chiang Mai 50200, Thailand
关键词
Software effort estimation; Analogy; Effort adaptation; Hyperparameter optimization; Ensemble; Empirical experiments; COST ESTIMATION; ADAPTATION TECHNIQUES; PREDICTION; REGRESSION; OPTIMIZATION; VALIDATION; SYSTEMS;
D O I
10.1016/j.infsof.2020.106330
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Context: An analogy-based software effort estimation technique estimates the required effort for a new software project based on the total effort used in completing past similar projects. In practice, offering high accuracy can be difficult for the technique when the new software project is not similar to any completed projects. In this case, the accuracy will rely heavily on a process called effort adaptation, where the level of difference between the new project and its most similar past projects is quantified and transformed to the difference in the effort. In the past, attempts to adapt to the effort used machine learning algorithms; however, no algorithm was able to offer a significantly higher performance. On the contrary, only a simple heuristic such as scaling the effort by consulting the difference in software size was adopted. Objective: More recently, million-dollar prize data-science competitions have fostered the rapid development of more powerful machine learning algorithms, such as the Gradient boosting machine and Deep learning algorithm. Therefore, this study revisits the comparison of software effort adaptors that are based on heuristics and machine learning algorithms. Method: A systematic comparison of software effort estimators, which they all were fully optimized by Bayesian optimization technique, was carried out on 13 standard benchmark datasets. The comparison was supported by robust performance metrics and robust statistical test methods. Conclusion: The results suggest a novel strategy to construct a more accurate analogy-based estimator by adopting a combined effort adaptor. In particular, the analogy-based model that adapts to the effort by integrating the Gradient boosting machine algorithm and a traditional adaptation technique based on productivity adjustment has performed the best in the study. Particularly, this model significantly outperformed various state-of-the-art effort estimation techniques, including a current standard benchmark algorithmic-based technique, analogy-based techniques, and machine learning-based techniques.
引用
收藏
页数:11
相关论文
共 50 条
[41]   Global Optimization of Analogy-Based Software Cost Estimation with Genetic Algorithms [J].
Milios, Dimitrios ;
Stamelos, Ioannis ;
Chatzibagias, Christos .
ARTIFICIAL INTELLIGENCE APPLICATIONS AND INNOVATIONS, PT II, 2011, 364 :350-+
[42]   Fuzzy C-mean Missing Data Imputation for Analogy-based Effort Estimation [J].
AlMutlaq, Ayman Jalal ;
Jawawi, Dayang N. A. ;
Arbain, Adila Firdaus Binti .
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2021, 12 (08) :628-640
[43]   Estimation of Software Effort with Market Approach Based on Analogy Evaluation [J].
Chen Yuanli ;
Shao Jungang .
MOT2009: PROCEEDINGS OF ZHENGZHOU CONFERENCE ON MANAGEMENT OF TECHNOLOGY, VOLS I AND II, 2009, :207-210
[44]   LEMABE: a novel framework to improve analogy-based software cost estimation using learnable evolution model [J].
Dashti, Maedeh ;
Gandomani, Taghi Javdani ;
Adeh, Dariush Hasanpoor ;
Zulzalil, Hazura ;
Sultan, Abu Bakar Md .
PEERJ COMPUTER SCIENCE, 2022, 8
[45]   Analogy-based effort estimation: a new method to discover set of analogies from dataset characteristics [J].
Azzeh, Mohammad ;
Nassif, Ali Bou .
IET SOFTWARE, 2015, 9 (02) :39-50
[46]   Improving Analogy-based Software Cost Estimation through Probabilistic-based Similarity Measures [J].
Phannachitta, Passakorn ;
Keung, Jacky ;
Monden, Akito ;
Matsumoto, Ken-Ichi .
2013 20TH ASIA-PACIFIC SOFTWARE ENGINEERING CONFERENCE (APSEC 2013), VOL 1, 2013, :541-546
[47]   Comparing Stacking Ensemble and Deep Learning for Software Project Effort Estimation [J].
Hoc, Huynh Thai ;
Silhavy, Radek ;
Prokopova, Zdenka ;
Silhavy, Petr .
IEEE ACCESS, 2023, 11 :60590-60604
[48]   Heterogeneous Ensemble Imputation for Software Development Effort Estimation [J].
Abnane, Ibtissam ;
Idri, Ali ;
Hosni, Mohamed ;
Abran, Alain .
PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PREDICTIVE MODELS AND DATA ANALYTICS IN SOFTWARE ENGINEERING (PROMISE '21), 2021, :1-10
[49]   Effort estimation using analogy [J].
Shepperd, M ;
Schofield, C ;
Kitchenham, B .
PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, 1996, :170-178
[50]   Evaluating ensemble imputation in software effort estimation [J].
Abnane, Ibtissam ;
Idri, Ali ;
Chlioui, Imane ;
Abran, Alain .
EMPIRICAL SOFTWARE ENGINEERING, 2023, 28 (02)