Support vector regression for predicting the productivity of higher education graduate students from individually developed software projects. Issue 5 (1st October 2017)

• Record Type: Journal Article
• Authors: López-Martín, Cuauhtémoc; Ulloa-Cazarez, Rosa Leonor; García-Floriano, Andrés
• Is Part Of: IET software. Volume 11:Issue 5(2017)
• Page Start: 265
• Page End: 270
• Publication Date: 2017-10-01
• Subjects: support vector machines -- regression analysis -- further education -- computer science education -- training -- data mining -- statistical testing -- Java -- C++ language -- software engineering; support vector regression -- higher education graduate student prediction -- higher education graduate student productivity -- software engineer productivity prediction -- software engineering education -- software engineering training -- data mining technique -- SVR -- statistical regression model -- neural networks -- Wilcoxon statistical test -- linear kernel -- programming language experience -- software projects -- Java -- C++ programming languages -- academic environments; Computer software -- Periodicals; Software engineering -- Periodicals; 005.1
• DOI: 10.1049/iet-sen.2016.0304
• Languages: English
• ISSNs: 1751-8806

Abstract

Abstract : Productivity prediction of a software engineer is necessary to determine whether corrective actions are needed and to identify improvement options to produce better results. It can be performed from abstraction levels such as organisation, team project, individual project, or task. Software engineering education and training has approached its efforts at individual level. In this study, the authors propose the application of a data mining technique named support vector regression (SVR) to predict the productivity of individuals (i.e. graduate students). Its prediction accuracy was compared with that of a statistical regression model, and with those of two neural networks. After applying a Wilcoxon statistical test, results suggest that an SVR with linear kernel using new and changed lines of code, and programming language experience as independent variables, could be used for predicting the individual productivity of a higher education graduate student, when software projects coded in either Java or C++ programming languages, have been developed by following a disciplined process specifically proposed for academic environments.