A CTR Prediction Model With Double Matrix-Level Cross-Features

A CTR Prediction Model With Double Matrix-Level Cross-Features

CTR prediction is an important task in recommender systems, which is used to estimate the likelihood of a user clicking on an advertisement.In the past, the CTR prediction model based on the deep neural network mainly obtains the implicit feature combination of the model at the bit-wise level, and t...

Full description

Bibliographic Details
Main Authors: Wei Zhang, Yahui Han, Zhaobin Kang, Kaiyuan Qu
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Click-through rate prediction
recommender systems
feature interaction
multi-head self-attention
cross network
Online Access:https://ieeexplore.ieee.org/document/9908542/

Internet

https://ieeexplore.ieee.org/document/9908542/

Similar Items