Research on advertising click-through rate prediction model based on Taobao big data

Abstract

Ad click-through rate prediction is a key problem in the field of computational advertising. In this paper, LR model, Random Forest model, GDBT model and LightGBM model are used to predict ad click-through rate respectively. In this paper, we adopt the Stacking-based LR and GDBT fusion model and the BP neural network model for deep learning prediction. The experimental results on the real dataset show that the deep learning based BP neural network model performs better than other models.