AIBugHunter
AI-driven Code Defect Prediction Technologies
This project is supported by the Australian Research Council’s Discovery Early Career Researcher Award (DECRA 2020–2023).
Read case study
Timeline
July - October 2021
Deliverables
UX Research
UI Design
Prototyping
Team members (4 People)
1X Associate Professor
1X Casual senior researcher
2X Research Assistant (Me)
INTRODUCTION
What this project?
This research project is financially supported by the Australian Research. I worked with Dr. Kla Tantithamthavorn to help contribute to the research concepts to design solutions for developers.
THE PROBLEM
Most software projects are less efficient than they could be
Nearly 70% of all critical IT projects fail to deliver on time, within budget, or within the desired scope. One of the main reasons for this is software defects, which cause developers to spend more time finding and fixing bugs during development rather than efficiently implementing new features.
To address this problem, Dr. Kla developed defect prediction technologies(AIBugHunter), i.e., an AI/ML model that is trained on historical data to predict which files/commits are likely to be defective in the future. Defect prediction technologies are widely used in many top software companies
DISCOVERY
Most software projects are less efficient than they could be
Nearly 70% of all critical IT projects fail to deliver on time, within budget, or within the desired scope. One of the main reasons for this is software defects, which cause developers to spend more time finding and fixing bugs during development rather than efficiently implementing new features.