文章基本信息

标题：Analogy-based model for software project effort estimation
本地全文：下载
作者：Ardiansyah Ardiansyah ; Murein Miksa Mardhia ; Sri Handayaningsih 等
期刊名称：IJAIN (International Journal of Advances in Intelligent Informatics)
印刷版ISSN：2442-6571
电子版ISSN：2548-3161
出版年度：2018
卷号：4
期号：3
页码：251-260
DOI：10.26555/ijain.v4i3.266
语种：English
出版社：Universitas Ahmad Dahlan
摘要：Accurate effort estimation of software development plays an important role to predict how much effort should be prepared during the works of a software project so that it can be completed on time and budget. Some sectors, e.g. banking sectors, were renowned fields of software projects, not only due to its huge size of project, but also extremely expensive and takes a long time to completion. Project estimation is essential for software development project able to run on time and budget with maximum quality. This study aims to investigate the accuracy of software project effort estimation with the Analogy method using three parameters: Euclidean, Manhattan and Minkowski distance. Analogy based estimation consists several stage included similarity measure, analogy adaptation, estimation calculation and model evaluation. The results showed that the best combination of Analogy methods was using Manhattan distance with an accuracy of 50% MMRE, 28% MdMRE and Pred(25) 48%. Thus, we can concluded that this model can be used to predict accurately.
关键词：Analogy estimation;Effort estimation;Software project;Similarity distance;Machine learning