Predictive and auto-learning algorithm for fault Introduction collateral to software modification

As modern software is getting more complex, it is of great importance to ensure software reliability. Up to now, the most practical way of building high-reliable software is via a huge amount of testing and debugging. Therefore, software defect prediction, a technique to predict defects in software artifacts, has gained popularity by lessening the burden of developers to prioritize their testing and debugging efforts. In this project, we propose to develop a predictive and auto-learning algorithm that is able to predict potential software faults in a software program when a part of the program is modified. We will use a Bidirectional Encoder Representations from Transformers (BERT) based model (or rather, a further developed version of BERT called CodeBERT) for the prediction.

Faculty Supervisor:

Kin-Choong Yow

Student:

Partner:

Nokia Canada Inc (ON)

Discipline:

Engineering

Sector:

Information and cultural industries; Manufacturing; Professional, scientific and technical services

University:

University of Regina

Program: