Learning with Abandonment
Abstract
Consider a platform that wants to learn a personalized policy for each user, but the platform faces the risk of a user abandoning the platform if they are dissatisfied with the actions of the platform. For example, a platform is interested in personalizing the number of newsletters it sends, but faces the risk that the user unsubscribes forever. We propose a general thresholded learning model for scenarios like this, and discuss the structure of optimal policies. We describe salient features of optimal personalization algorithms and how feedback the platform receives impacts the results. Furthermore, we investigate how the platform can efficiently learn the heterogeneity across users by interacting with a population and provide performance guarantees.
Cite
Text
Schmit and Johari. "Learning with Abandonment." International Conference on Machine Learning, 2018.Markdown
[Schmit and Johari. "Learning with Abandonment." International Conference on Machine Learning, 2018.](https://mlanthology.org/icml/2018/schmit2018icml-learning/)BibTeX
@inproceedings{schmit2018icml-learning,
title = {{Learning with Abandonment}},
author = {Schmit, Sven and Johari, Ramesh},
booktitle = {International Conference on Machine Learning},
year = {2018},
pages = {4509-4517},
volume = {80},
url = {https://mlanthology.org/icml/2018/schmit2018icml-learning/}
}