Delivering Guaranteed Display Ads Under Reach and Frequency Requirements
Abstract
We propose a novel idea in the allocation and serving of online advertising. We show that by using predetermined fixed-length streams of ads (which we call patterns) to serve advertising, we can incorporate a variety of interesting features into the ad allocation optimization problem. In particular, our formulation optimizes for representativeness as well as user-level diversity and pacing of ads, under reach and frequency requirements. We show how the problem can be solved efficiently using a column generation scheme in which only a small set of best patterns are kept in the optimization problem. Our numerical tests suggest that with parallelization of the pattern generation process, the algorithm has a promising run time and memory usage.
Cite
Text
Hojjat et al. "Delivering Guaranteed Display Ads Under Reach and Frequency Requirements." AAAI Conference on Artificial Intelligence, 2014. doi:10.1609/AAAI.V28I1.9030Markdown
[Hojjat et al. "Delivering Guaranteed Display Ads Under Reach and Frequency Requirements." AAAI Conference on Artificial Intelligence, 2014.](https://mlanthology.org/aaai/2014/hojjat2014aaai-delivering/) doi:10.1609/AAAI.V28I1.9030BibTeX
@inproceedings{hojjat2014aaai-delivering,
title = {{Delivering Guaranteed Display Ads Under Reach and Frequency Requirements}},
author = {Hojjat, S. Ali and Turner, John G. and Cetintas, Suleyman and Yang, Jian},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2014},
pages = {2278-2284},
doi = {10.1609/AAAI.V28I1.9030},
url = {https://mlanthology.org/aaai/2014/hojjat2014aaai-delivering/}
}