Research on Advertising Click-Through Rate Prediction Based on CNN-FM Hybrid Model
Xiangyang She, Shaopeng Wang · 2018
Click through rate prediction is one of the hot topics in machine learning. The single structure model does not take into account the characteristics including highly nonlinear association for features. Aiming at this problem, this paper presents a click through rate prediction model based on CNN (Convolutional Neural Networks) and FM (factorization machine). This model uses CNN to extract high-impact features, and predicts and classifies them by FM, which can learn the relationship between mutually distinct feature components. The experimental results show that compared with the single structure model, the CNN-FM hybrid model can effectively improve the accuracy of advertising click through rate prediction.