Eurostars E! 11582 PADS (Programmatic Advertising Decision System)

Project: Research direct

Project Details

Description

Online advertising plays a great role in the income of an online publisher. The company can easily place ad slots in its website and increase its revenue by selling these ad slots to the advertisers. When a user opens a website containing an ad slot, a request to fill the slot is generated and sent to ad networks. Ad networks are entities between advertisers and publishers that run auctions to find an appropriate advertisement for each ad request. Advertisers build and manage advertising campaigns to participate in the auction and find appropriate platform to render their products or brands. There are two other stakeholders in the bidding environment: Supply Side Platforms (SSP) to help publishers in managing their ad slots and Demand Side Platforms (DSP) for assisting advertisers in making and bidding advertisement campaigns. In the publisher side, whenever a user opens a website, a request is sent to the SSP and the response is either an advertisement filling the ad slot, or a message showing that this attempt was unsuccessful. Depending which auction a publisher opts for filling their advertising slot, there are three main problems.
Determining floor price: The first problem that publishers face is how to set the price of their inventories to obtain the maximum revenue.
Participating in the auction: After determining the floor price, publishers should participate in an auction to find proper ads. Many ad networks are available to receive ad requests and run auctions.
Considering the auction as a multi-agent environment: The third problem for a publisher is making decisions based on the other publishers, advertisers, and ad networks.

Key findings

Online Advertising, Real Time Bidding
StatusActive
Effective start/end date1/10/1730/09/20

Research Output

  • 4 Conference contribution

A decision support method to increase the revenue of ad publishers in waterfall strategy

Refaei Afshar, R., Zhang, Y., Firat, M. & Kaymak, U., 1 May 2019, CIFEr 2019 - IEEE Conference on Computational Intelligence for Financial Engineering and Economics. Piscataway: Institute of Electrical and Electronics Engineers, 8 p. 8759106

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Open Access
File
  • 5 Citations (Scopus)
    65 Downloads (Pure)

    A reinforcement learning method to select ad networks in waterfall strategy

    Afshar, R. R. A., Zhang, Y., Firat, M. & Kaymak, U., 1 Jan 2019, BNAIC/BENELEARN 2019: Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019). Beuls, K., Bogaerts, B. & Bontempi, G. (eds.). CEUR-WS.org, 2 p. 112. (CEUR Workshop Proceedings; vol. 2491).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Open Access
    File
    19 Downloads (Pure)

    A reinforcement learning method to select ad networks in Waterfall Strategy

    Refaei Afshar, R., Zhang, Y., Firat, M. & Kaymak, U., 2019, ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence. van den Herik, J., Steels, L. & Rocha, A. (eds.). SCITEPRESS-Science and Technology Publications, Lda., Vol. 2. p. 256-265 10 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Open Access
    File
  • 6 Citations (Scopus)
    48 Downloads (Pure)