Towards an Intelligent Fault Prediction Code Editor to Improve Software Quality Using Deep Learning



Journal Title

Journal ISSN

Volume Title


Association for Computing Machinery


Software quality assurance has become the pillar for success in software companies. High quality, low maintenance programs can be achieved if fault-prone modules can be identified early in the development lifecycle. In this paper, we propose a new intelligent Integrated Development Environment (IDE) which seamlessly allow programmers to test their code for faults using prior source code databases. Our IDE is built upon deep learning models for making recommendations. The editor also gives scores to programmers on their program design. We evaluate and validate our approach using famous NASA code repositories.


Full text access from Treasures at UT Dallas is restricted to current UTD affiliates (use the provided Link to Article).


Learning, Deep, Quality assurance, Computer software—Quality control, Character sets (Data processing), Computer programming, Integro-differential equations, United States. National Aeronautics and Space Administration, Learning models (Stochastic processes), Computer software industry


©2018 The Author