计算广告中的点击率与转化率是广告效果的重要指标，具有重要意义。随着深度神经网络的广泛应用，传统基于机器学 习算法的点击率与转化率预测模型逐渐被深度学习模型取代。基于深度神经网络的模型能够从多源信息中提取用户的兴趣特 征和时延关系，进而对用户的未来行为做出预测，进一步预测广告效果。本文将总结分析点击率和转化率预测相关研究进展， 并总结介绍我们最新的研究成果。

The click‑through rate and conversion rate in an computational advertisement is an important indicator of the effectiveness of the advertisement, which is of great significance. With the widespread application of deep neural networks, traditional click‑through rate and conversion rate prediction models based on machine learning algorithms are gradually being replaced by deep learning models. The model based on deep neural network can extract the user′s interest characteristics and time delay relationship from multi‑source information, and then make predictions on the user′s future behavior, and further predict the effect of advertising. This article will summarize and analyze the research progress related to click‑through rate and conversion rate prediction, and summarize our latest research results.