Learning with Abandonment

Sven Schmit, Ramesh Johari
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:4509-4517, 2018.

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 this Paper


BibTeX
@InProceedings{pmlr-v80-schmit18a, title = {Learning with Abandonment}, author = {Schmit, Sven and Johari, Ramesh}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {4509--4517}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/schmit18a/schmit18a.pdf}, url = {https://proceedings.mlr.press/v80/schmit18a.html}, 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.} }
Endnote
%0 Conference Paper %T Learning with Abandonment %A Sven Schmit %A Ramesh Johari %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-schmit18a %I PMLR %P 4509--4517 %U https://proceedings.mlr.press/v80/schmit18a.html %V 80 %X 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.
APA
Schmit, S. & Johari, R.. (2018). Learning with Abandonment. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:4509-4517 Available from https://proceedings.mlr.press/v80/schmit18a.html.

Related Material