A Sleeping, Recovering Bandit Algorithm for Optimizing Recurring Notifications - CrossMinds.ai
A Sleeping, Recovering Bandit Algorithm for Optimizing Recurring Notifications
Aug 13, 202053 views
Kevin Yancey
Many online and mobile applications rely on daily emails and push,notifications to increase and maintain user engagement. The multiarmed bandit approach provides a useful framework for optimizing the content of these notifications, but a number of complications (such as novelty effects and conditional eligibility) make conventional bandit algorithms unsuitable in practice. In this paper,,we introduce the,Recovering Difference Softmax Algorithm,to address the particular challenges of this problem domain, and,use it to successfully optimize millions of daily reminders for the,online language-learning app Duolingo. This lead to a 0.5 % increase in total daily active users (DAUs) and a 2 % increase in new,user retention over a strong baseline. We provide technical details,of its design and deployment, and demonstrate its efficacy through,both offline and online evaluation experiments.
SIGKDD_2020
Applied Research
Recommended