Predicting Software Quality by Optimized BP Network Based on PSO

The prediction model of software quality is the key technology in the software quality evaluation system, which can be used to evaluate software quality characteristics that users care about. Prediction models are often used to find the nonlinear relationship between metric data and quality factors. The paper predicted the relationship between metric data and quality factors with historical data by using the optimized BP network based on PSO. According to the algorithm, 28 groups of data are adopted in the experiment, and compared with the results by using BP network. Experiments show that the algorithm has a better performance than the BP network algorithm and perfectly solve the problem of slow convergence and easily getting into local minimum.