Risk assessment of credit field based on PSO-SVM

摘要

With the advent of the era of big data and the application of machine learning, user credit risk assessment in the credit process has gradually changed from traditional manual assessment to intelligent algorithm recognition. This paper proposes a support vector machine combination model based on particle swarm optimization and applies the model to user credit risk assessment. The paper first uses a support vector machine (SVM) with a radial basis function core (RBF core) as the core function as a verification algorithm, and then uses a particle swarm optimization algorithm (PSO) to optimize the parameters of the SVM, and establishes a particle swarm algorithm based Support vector machine combination model (PSO-SVM), finally compare the model with the original SVM, neural network, random forest, naive Bayes and other models on the UCI data set, and use Recall, Precision, Accuracy and F-score to evaluate Model performance. Empirical analysis proves that the model proposed in this paper has a good predictive classification effect.