基于淘宝广告数据的点击概率预估模型研究

Journal of Shenyang Institute of Chemical Technology(2022)

Cited 0|Views10
No score
Abstract
提出一种将压缩交互网络、因子分解机模型和神经网络3种模型相结合构成的因子交互全连接网络预估模型预测淘宝广告数据中用户对广告的点击概率.利用TensorFlow搭建整个算法模型,并使用淘宝广告展示数据集进行训练.最终训练出的模型可以得到数据中用户对任意一条广告的点击概率.采用曲线下面积(AUC)与对数损失函数(Logloss)值作为模型的评价指标,得到的结果与LR、FM、DeepFM等点击概率预估模型进行对比,AUC值提高了 0.05,Logloss值降低了0.04,效果得到明显提升.
More
Translated text
Key words
factor interaction fully connected network,factorization machine,compressed interactive network,deep neural network
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined