Projects per year
A high percentage of online advertising is currently performed through real time bidding. Impressions are generated once a user visits the websites containing empty ad slots, which are subsequently sold in an online ad exchange market. Nowadays, one of the most important sources of income for publishers who own websites is through online advertising. From a publisher’s point of view it is critical to send its impressions to most profitable ad networks and to fill its ad slots quickly in order to increase their revenue. In this paper we present a method for helping publishers to decide which ad networks to use for each available impression. Our proposed method uses reinforcement learning with initial state-action values obtained from a prediction model to find the best ordering of ad networks in the waterfall fashion. We show that this method increases the expected revenue of the publisher.
|Title of host publication||ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence|
|Editors||Jaap van den Herik, Luc Steels, Ana Rocha|
|Publisher||SciTePress Digital Library|
|Number of pages||10|
|Publication status||Published - 2019|
|Event||11th International Conference on Agents and Artificial Intelligence, ICAART 2019 - Prague, Czech Republic|
Duration: 19 Feb 2019 → 21 Feb 2019
|Conference||11th International Conference on Agents and Artificial Intelligence, ICAART 2019|
|Period||19/02/19 → 21/02/19|
- Ad Network
- Online AD Auction
- Predictive Model
- Real Time Bidding
- Reinforcement Learning
- Supply Side Platform
FingerprintDive into the research topics of 'A reinforcement learning method to select ad networks in Waterfall Strategy'. Together they form a unique fingerprint.
- 1 Finished
Eurostars E! 11582 PADS (Programmatic Advertising Decision System)
Kaymak, U. & Refaei Afshar, R.
1/10/17 → 28/02/22
Project: Research direct