[CW Paper-Club] A Sleeping, Recovering Bandit Algorithm for Optimizing Recurring Notifications

In this week's session, Caio Damasceno presents the paper "A Sleeping, Recovering Bandit Algorithm for Optimizing Recurring Notifications" published in 2020 by Kevin P. Yancey and Burr Settles from Duolingo.

The paper introduces the Recovering Difference Softmax Algorithm to optimize daily notifications for user engagement in apps. It addresses challenges in traditional bandit algorithms, achieving a 0.5% increase in daily active users and a 2% increase in new user retention for Duolingo. Technical details and evaluation results are also provided.

If you're interested in joining our team at CloudWalk, please check out our job openings on LinkedIn! Don't forget to check out the paper, which is available at the link provided below.

Paper Link: https://research.duolingo.com/papers/yancey.kdd20.pdf

Recording Date: May 24 2024
00:00 Paper presentation

CW Paper-Club Sessions is a weekly meeting presented by CloudWalk's R&D team members, where they dive into interesting research papers, providing valuable insights into the latest developments in technology and research.

Full Paper Abstract:
Many online and mobile applications rely on daily emails and push notifications to increase and maintain user engagement. The multi-armed 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 led 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.

Видео [CW Paper-Club] A Sleeping, Recovering Bandit Algorithm for Optimizing Recurring Notifications канала CloudWalk