A Survey of Online Advertising Click-Through Rate Prediction Models
Xinfei Wang
Abstract
In recent years, online advertising sales have been the main economic sources of Internet companies such as Google, Facebook, Snap, Pinterest, and Baidu. Advertising click-through rate measures the ratio of users who click an advertisement to the total users who view the advertisement. The click-through rate is very important for Internet companies' online advertisements quality. The click-through rate of online advertising is related to many factors, including gender, age, type of advertisement, and the timely and effective prediction of the click-through rate of online advertising as well as advertisement text. In recent years, the click-through rate of online advertising has become one of the hot areas of research in industry and academia. Advertising prediction models are generally divided into two categories: shallow learning models and deep learning models. This paper surveys Click-Through Rate (CTR) prediction models, discusses the problems in the current advertising click rate prediction models, and points out future research trends.