A training and testing framework supporting experiments in CIKM 2016 paper "User Response Learning for Directly Optimizing Campaign Performance in Display Advertising"
An experimental framework to support experiments in CIKM 2016 paper "User Response Learning for Directly Optimizing Campaign Performance in Display Advertising". PDF
If you have any problem, please send an E-mail to Kan Ren.
iPinYou
has been decribed in this page.YOYI
is the newly published dataset in our CIKM paper. The detail of this dataset is here.We use yzx
data structure to formalize bidding logs.
Each record contains
y
: true label of user response (1 for positive and 0 otherwise).z
: the market price of this sample.x
: pre-processed features of the bid request.Other details of yzx
data can be found in this benchmarking paper
iPinYou
dataset as described here. Note that, please put make-ipinyou-data
folder in the same parent folder as optimal-ctr-bidding
project.|-- code-folder
----|-- make-ipinyou-data
--------|-- yoyi-data
--------|-- 1458
--------|-- 2259
--------...
----|-- optimal-ctr-bidding
--------|-- python
--------|-- scripts
--------|-- README.md
YOYI
dataset and put the folder in make-ipinyou-data
.script
folder and execute run_MODEL
scripts, where MODEL
is a placeholder of model names including "lr", "sqlr", "eu" and "rr". Details of the models can be found in our paper.sh run-lr.sh "1458 2261 2821"
@inproceedings{ren2016user,
title={User response learning for directly optimizing campaign performance in display advertising},
author={Ren, Kan and Zhang, Weinan and Rong, Yifei and Zhang, Haifeng and Yu, Yong and Wang, Jun},
booktitle={Proceedings of the 25th ACM International on Conference on Information and Knowledge Management},
pages={679--688},
year={2016},
organization={ACM}
}
@article{ren2018bidding,
title={Bidding Machine: Learning to Bid for Directly Optimizing Profits in Display Advertising},
author={Ren, Kan and Zhang, Weinan and Chang, Ke and Rong, Yifei and Yu, Yong and Wang, Jun},
journal={IEEE Transactions on Knowledge and Data Engineering},
volume={30},
number={4},
pages={645--659},
year={2018},
publisher={IEEE}
}