Software Defect Prediction Model Based on Deep Learning
Yajie Zhang · 2024
At present, under the background of the vigorous development of Internet technology and the era of the Internet of Everything, the diversification and complexity of software application scenarios are growing at an unprecedented rate. Although this trend has greatly enriched the user experience, it is also accompanied by the problem of frequent software failures. Software defects, as the key factor to weaken software reliability, are increasingly attracting extensive attention from the industry and academia. The software defect prediction model based on deep learning (DL) proposed in this article is a cutting-edge exploration in this field. This model fully utilizes the powerful ability of DL in processing large-scale and high-dimensional data, and can automatically learn complex features and patterns from historical data of software projects, achieving accurate prediction of software defects. The experimental results show that compared with traditional prediction methods, this model exhibits significant advantages in key indicators such as prediction accuracy and recall rate, effectively improving the comprehensiveness and accuracy of software defect prediction, and providing strong technical support for software testing and quality assurance work.