Abstract
Software engineering is a competitive field in education and practice. Software projects are key elements of software engineering courses. Software projects feature a fusion of process and product. The process reflects the methodology of performing the overall software engineering practice. The software product is the final product produced by applying the process. Like any other academic domain, an early evaluation of the software product being developed is vital to identify the at-risk teams for sustainable education in software engineering. Guidance and instructor attention can help overcome the confusion and difficulties of low performing teams. This study proposed a hybrid approach of information gain feature selection with a J48 decision tree to predict the earliest possible phase for final performance prediction. The proposed technique was compared with the state-of-the-art machine learning (ML) classifiers, naïve Bayes (NB), artificial neural network (ANN), logistic regression (LR), simple logistic regression (SLR), repeated incremental pruning to produce error reduction (RIPPER), and sequential minimal optimization (SMO). The goal of this process is to predict the teams expected to obtain a below-average grade in software product development. The proposed technique outperforms others in the prediction of low performing teams at an early assessment stage. The proposed J48-based technique outperforms others by making 89% correct predictions.
Highlights
Quality education is one of the foremost goals of sustainable development, as approved by the United Nations Forum (2015) [1]
This study focuses on the development of a successful J48 decision tree-based technique for predicting student grades for software product development in software engineering courses
Incomplete, inconsisRtaewnt,daantda aamrebtirgaunosufosrimnfeodrminattoionusiesfruelmdoavtaeduisnintgheddaatatapprreepprroocceessssiinngg apphpasroe.acThheeso. uIntccoommepolefte, daitnacpornespisrtoecnets,sainngdiasmclbeiagnudoautsa.inNfoUrmLLatvioanluiessraerme oovbesedrvinedthiendthaetadpiffreeprernotcefiseslidnsgopfhthaseer.aTwhedoatuatcsoemt. e Anofimdaptoartparnetparsopceecsstionfgdiastcaleparnepdraotcae.sNsiUngLLinvvaolluveess dareealoinbsgewrviethd ministhsiengd/inffuelrlevnatlfuieelsd. sNoufltlhvearluawes dinata SEsTeAt.PAdnaitma paorertcaanttearesdpebcyt ofiflldinagtatphreeapvroercaegsseinvgaliunevsoolvf eths edeaattlrinibguwteist.hHmoiwsseinvge/rn, iufltlhvealvuaelus.eNs uolfllvoaclaules teainmSsEaTreAdPecdlaatraedaraes cNaUteLreLdfobrytfhileliirngglothbealavvaerriaagbelevsa, ltuheesy oafrethreepaltatcreibdubteys0. .if the values of local teams are declared as NULL for their global variables, they are replaced by 0
Summary
Quality education is one of the foremost goals of sustainable development, as approved by the United Nations Forum (2015) [1]. Providing an environment that helps students complete their academics with better opportunities for resolving difficulties is the primary parameter for Education for Sustainable Development (ESD) [3]. Significant feedback is associated with the early prediction of student performance, such as modeling the learning behavior of students, adjusting and improving the academic environment, catering to students’ issues, and engaging in decision-making practices based on data analysis [4]. The predictive analysis based on AI is a significant trait for the development of the sustainable conceptual framework for engineering projects. It is challenging and more difficult to predict the performance of students in the project-based learning of engineering fields. In these fields, students work as teams in projects located locally or globally. These credentials increase the difficulties in assessing teams, eventually making early predictions more thought-provoking [9]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
