Skip to main content

Human-Centric Defect Prediction: Predict and explain human-impacting defects

Primary supervisor

Chakkrit Tantithamthavorn

Co-supervisors

Research area

Software Engineering

Defect prediction has been developed for more than four decades. Yet, a multitude of human aspects (i.e., both developers and end-users) have been rarely considered and incorporated. Thus, this project aims to focus on inventing theories and approaches for human-centric defect prediction to efficiently predict and explain non-functional requirement defects (e.g., accessibility issues and usability issues in Mobile Apps) that have the largest impact on end-users and humanity. Finally, this project will leverage a multi-objective optimisation approach to find a set of optimal QA prioritisation strategies using a meta-heuristic technique (e.g., genetic programming) to generate a large number of candidate solutions, and search for the ones that are optimal with respect to a number of objectives. The search is guided simultaneously by multiple contrasting objectives: maximising the QA resources on software modules that are risky, severe, and affect a large number of end-users, while minimising the cost of fixing defects and the workload among software engineers.

This project is aligned with Prof John Grundy (2019 ARC Laureate Fellow, Human-Centric Model-Driven Requirement Engineering) and Dr Chakkrit Tantithamthavorn (2020 ARC DECRA Fellow, Practical and Explainable Analytics to Prevent Future Software Defects).

Required knowledge

- Industrial experience

- Machine learning backgrounds


Learn more about minimum entry requirements.