• Stars
    star
    358
  • Rank 118,855 (Top 3 %)
  • Language
    Jupyter Notebook
  • License
    MIT License
  • Created almost 7 years ago
  • Updated over 5 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

This is a kaggle challenge project called Display Advertising Challenge by CriteoLabs at 2014.这是2014年由CriteoLabs在kaggle上发起的广告点击率预估挑战项目。

kaggle_criteo_ctr_challenge-

This is a kaggle challenge project called Display Advertising Challenge by CriteoLabs at 2014. 这是2014年由CriteoLabs在kaggle上发起的广告点击率预估挑战项目。 使用TensorFlow1.0和Python 3.5开发。

Author chengstone

e-Mail [email protected]

代码详解请参见jupyter notebook和↓↓↓

知乎专栏:https://zhuanlan.zhihu.com/p/32500652

博客:http://blog.csdn.net/chengcheng1394/article/details/78940565

欢迎转发扩散 ^_^

本文使用GBDT、FM、FFM和神经网络构建了点击率预估模型。

网络模型

image

LogLoss曲线

image

验证集上的训练信息

  • 平均准确率
  • 平均损失
  • 平均Auc
  • 预测的平均点击率
  • 精确率、召回率、F1 Score等信息

image

更多内容请参考代码,Enjoy!

许可

Licensed under the MIT License with the 996ICU License.