Deep Bayesian Bandits: Exploring in Online Personalized Recommendations

@article{Guo2020DeepBB,
  title={Deep Bayesian Bandits: Exploring in Online Personalized Recommendations},
  author={Dalin Guo and S. Ktena and Ferenc Husz{\'a}r and Pranay K. Myana and Wenzhe Shi and Alykhan Tejani},
  journal={Fourteenth ACM Conference on Recommender Systems},
  year={2020}
}
Recommender systems trained in a continuous learning fashion are plagued by the feedback loop problem, also known as algorithmic bias. This causes a newly trained model to act greedily and favor items that have already been engaged by users. This behavior is particularly harmful in personalised ads recommendations, as it can also cause new campaigns to remain unexplored. Exploration aims to address this limitation by providing new information about the environment, which encompasses user… Expand
Underestimation Refinement: A General Enhancement Strategy for Exploration in Recommendation Systems
  • Yuhai Song, Lu Wang, +6 authors Jingping Shao
  • Computer Science
  • SIGIR
  • 2021
Online Learning for Recommendations at Grubhub
  • A. Egg
  • Computer Science
  • ArXiv
  • 2021