目录

Implicit User Awareness Modeling via Candidate Items for CTR Prediction in Search Ads

This repo is the official implementation for the WWW 2022 paper: Implicit User Awareness Modeling via Candidate Items for CTR Prediction in Search Ads.

Data format

Our released dataset CandiCTR-Pub could be found at JD JingPan with password xngmgr.

In the data files, each row corresponds to a search session. Each column in the data represents userID, queryID, label list, target items and request item queue. Each item is consist of itemID, categoryID, brandID, vendorID and priceID. All data have been desensitized.

Requirements

  • python 3.6.13
  • tensorflow 1.15.0
  • scikit-learn 0.24.2

Quick start

Create a new data folder and put the downloaded dataset into the folder. Then,

python src/main.py 
关于
46.0 KB
邀请码
    Gitlink(确实开源)
  • 加入我们
  • 官网邮箱:gitlink@ccf.org.cn
  • QQ群
  • QQ群
  • 公众号
  • 公众号

版权所有:中国计算机学会技术支持:开源发展技术委员会
京ICP备13000930号-9 京公网安备 11010802032778号