Abstract:
Software defect prediction is a critical part of development, identifying mismatches between expected and actual outcomes as detected by developers or end users. The main purpose of agile defect prediction is identifying defects in timely manner. Because it helps teams to prioritize tasks, allocate the resources such as time, effort and personnel to the riskiest parts of the code, enhance the sprint planning and improve the software quality by supporting continuous development. But the iterative and fast paced nature of agile environments raises few challenges for the defect prediction such as handling code changes, managing limited development time and addressing the dynamic and evolving project requirements. So, there is a notable gap related to the research studies of agile defect prediction. Traditional defect prediction methods frequently struggle to identify dynamic and complex data patterns. This study proposes a solution by using deep learning models so agile teams can use them to detect defects early, optimize testing and improve real-time software quality of the projects. For the research, Convolutional Neural Network (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) and Deep Belief Network (DBN) models are used which can identify complex data patterns and relationships by extracting the meaningful features automatically. Jira defect dataset was used and cleaned using data pre-processing and feature selection techniques, and the processed dataset was divided into training and testing sets. The trained models were evaluated using metrics like accuracy, precision, recall and f1-score. The study exposes LSTM outperforms other models with 76% accuracy, handling long-term dependencies and processing historical defect logs. The findings of the research emphasize the effectiveness of using deep learning models in agile software defect prediction for high-quality, reliable real-world agile development practices.
