A contextual bandit algorithm for ad creative under ad fatigue

Daisuke Moriwaki, Komei Fujita, Shota Yasui, Takahiro Hoshino

Research output: Contribution to journalArticlepeer-review


Selecting ad creative is one of the most important task for DSPs (Demand-Side Platform) in online advertising. DSPs should not only consider the effectiveness of the ad creative but also the user’s psychological status when selecting ad creative. In this study, we propose an efficient and easy-to-implement ad creative selection algorithm that explicitly considers wear-in and wear-out effects of ad creative due to the repetitive ad exposures. The proposed system was deployed in a real-world production environment and tested against the baseline. It out-performed the existing system in most of the KPIs.

Original languageEnglish
JournalUnknown Journal
Publication statusPublished - 2019 Aug 20


  • AB testing
  • Advertising fatigue
  • Advertising repetition
  • Awareness
  • Bandit algorithm
  • Online display ad
  • Online experiment
  • Wear-in wear-out effect

ASJC Scopus subject areas

  • General

Fingerprint Dive into the research topics of 'A contextual bandit algorithm for ad creative under ad fatigue'. Together they form a unique fingerprint.

Cite this