Identifying Talented Software Engineering Students through Data-driven Skill Assessment

TL;DR

This paper presents a data-driven approach using an Agile Project Management platform to identify talented software engineering students based on a wide range of skills beyond programming, demonstrated through a study of student teams.

Contribution

It introduces the HASE online APM tool and demonstrates its effectiveness in assessing diverse skills of students in real-world project settings.

Findings

Successful identification of talented students using multi-skill data

Potential for improving software engineering education and recruitment

Feasibility of data-driven skill assessment in practice

Abstract

For software development companies, one of the most important objectives is to identify and acquire talented software engineers in order to maintain a skilled team that can produce competitive products. Traditional approaches for finding talented young software engineers are mainly through programming contests of various forms which mostly test participants' programming skills. However, successful software engineering in practice requires a wider range of skills from team members including analysis, design, programming, testing, communication, collaboration, and self-management, etc. In this paper, we explore potential ways to identify talented software engineering students in a data-driven manner through an Agile Project Management (APM) platform. Through our proposed HASE online APM tool, we conducted a study involving 21 Scrum teams consisting of over 100 undergraduate software engineering students in multi-week coursework projects in 2014. During this study, students performed over 10,000 ASD activities logged by HASE. We demonstrate the possibility and potentials of this new research direction, and discuss its implications for software engineering education and industry recruitment.