Comparative Study on Defect Prediction Algorithms of Supervised Learning Software Based on Imbalanced Classification Data Sets

With the development of high complexity and high integration of software systems, the quality of software has gradually received widespread attention in scientific research and engineering. Software defect prediction technology plays an important role in improving software quality, reducing software development time, and reducing testing expenses. It has also become one of the hot issues in the field of software engineering research in recent years. As an important learning method in machine learning, supervised learning is widely used in the classification and regression prediction with annotation data because of its high accuracy, mature theory, and simple calculation. However, the imbalanced classification problem of data sets is common in practical applications and seriously affects the performance of learning algorithm. This paper analyzes the characteristics of software forecasting technology from the perspective of supervised learning, and performs balance like processing on imbalanced classification NASA data sets (JM1, KC3, MC1). NASA data sets after application processing are used to conduct experiments on LWL, C4.5, Random forest, Bagging, Bayesian Belief Network, Multilayer Feed forward Neural Network, SVM and NB-K algorithms, and experimental data is analyzed and evaluated.