Forecasting technical debt evolution in software systems:an empirical study
作者机构：Department of EngineeringUniversity of SannioBenevento 82100Italy Department of Law and EconomicsUnitelma Sapienza University of RomeRome 00161Italy
出 版 物：《Frontiers of Computer Science》 (中国计算机科学前沿（英文版）)
年 卷 期：2023年第17卷第3期
页 面：63-75页
核心收录：
学科分类：08[工学] 0835[工学-软件工程] 081202[工学-计算机软件与理论] 0812[工学-计算机科学与技术（可授工学、理学学位）]
主 题：technical debt empirical study software quality metrics machine learning
摘 要：Technical debt is considered detrimental to the long-term success of software development,but despite the numerous studies in the literature,there are still many aspects that need to be investigated for a better understanding of *** particular,the main problems that hinder its complete understanding are the absence of a clear definition and a model for its identification,management,and *** on forecasting technical debt,there is a growing notion that preventing technical debt build-up allows you to identify and address the riskiest debt items for the project before they can permanently compromise ***,despite this high relevance,the forecast of technical debt is still little *** this end,this study aims to evaluate whether the quality metrics of a software system can be useful for the correct prediction of the technical ***,the data related to the quality metrics of 8 different open-source software systems were analyzed and supplied as input to multiple machine learning algorithms to perform the prediction of the technical *** addition,several partitions of the initial dataset were evaluated to assess whether prediction performance could be improved by performing a data *** results obtained show good forecasting performance and the proposed document provides a useful approach to understanding the overall phenomenon of technical debt for practical purposes.
维普期刊数据库
同方期刊数据库