CTR prediction is one of the main research directions of recommendation algorithm, which is widely used in e-commerce advertising recommendation and other fields. Wide&Deep Learning (WDL) model is a CTR prediction and recommendation algorithm that combine linear model with deep neural network. To solve the problem that WDL is prone to over-fitting and the proportion of Wide and Deep learning part needs to be adjusted manually in practical application, Attentional WDL(A-WDL) algorithm is based on residual network to improve the Deep part. And use the attention mechanism to automate the learning of the Wide part and the Deep learning part of the proportion. Experiments on the public dataset Criteo on Kaggle show that the A-WDL algorithm improves the performance of AUC compared with other algorithms such as WDL, and effectively avoids the problem of overfitting. In addition, the performance improvement of A-WDL is explainable.