Click Prediction for P2P Loan Ads Based on Support Vector Machine

This paper mainly contains the following three aspects of research. Firstly, this paper starts from the definition of advertisement click prediction, analyzes the distribution and characteristics of the dataset and preprocesses the dataset. On this basis, based on the understanding of advertising and the characteristics in practical application, ten different types of features were extracted. Secondly, the paper first uses SVM, naive Bayesian model, decision tree model and neural network model to predict the click-through rate and analyze their shortcomings. The experimental results show that the SVM model method used in this paper can obtain better prediction results than other methods under the same characteristics.