用回归模型基于用户故事点预测敏捷开发工作量，精度显著提升。
Agile Software Effort Estimation using Regression Techniques
- 采用LASSO与弹性网络回归，结合网格搜索优化参数。
- LASSO在21个真实项目上达到8%误差率，平均相对误差仅4.91%。
- 适合敏捷团队做开发预估，尤其关注高精度工作量估算的项目。
软件开发工作量估算对项目成败至关重要。本研究基于用户故事点，利用LASSO和弹性网络回归技术构建敏捷工作量估算模型。实验基于六家企业的21个真实软件项目，采用默认参数与网格搜索结合5折交叉验证进行训练。结果表明，LASSO回归表现更优：PRED(8%)与PRED(25%)均为100.0，MMRE为0.0491，MMER为0.0551，MdMRE为0.0593，MdMER为0.063，MSE为0.0007。性能优于现有相关研究。
原文摘要 · Abstract (English)
Software development effort estimation is one of the most critical aspect in software development process, as the success or failure of the entire project depends on the accuracy of estimations. Researchers are still conducting studies on agile effort estimation. The aim of this research is to develop a story point based agile effort estimation model using LASSO and Elastic Net regression techniques. The experimental work is applied to the agile story point approach using 21 software projects collected from six firms. The two algorithms are trained using their default parameters and tuned grid search with 5-fold cross-validation to get an enhanced model. The experiment result shows LASSO regression achieved better predictive performance PRED (8%) and PRED (25%) results of 100.0, MMRE of 0.0491, MMER of 0.0551, MdMRE of 0.0593, MdMER of 0.063, and MSE of 0.0007. The results are also compared with other related literature.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。