Cognitive Information Filters: Algorithmic Choice Architecture for Boundedly Rational Choosers
Abstract
We introduce cognitive information filters as an algorithmic approach to mitigating information overload using choice architecture: We develop a rational inattention model of boundedly rational multi-attribute choice and leverage it to programmatically select information that is effective in inducing desirable behavioral outcomes. By inferring preferences and cognitive constraints from boundedly rational behavior, our methodology can optimize for revealed welfare and hence promises better alignment with boundedly rational users than recommender systems optimizing for imperfect welfare proxies such as engagement. This has implications beyond economics, for example for alignment research in artificial intelligence.
Cite
Text
Bucher and Dayan. "Cognitive Information Filters: Algorithmic Choice Architecture for Boundedly Rational Choosers." NeurIPS 2023 Workshops: InfoCog, 2023.Markdown
[Bucher and Dayan. "Cognitive Information Filters: Algorithmic Choice Architecture for Boundedly Rational Choosers." NeurIPS 2023 Workshops: InfoCog, 2023.](https://mlanthology.org/neuripsw/2023/bucher2023neuripsw-cognitive/)BibTeX
@inproceedings{bucher2023neuripsw-cognitive,
title = {{Cognitive Information Filters: Algorithmic Choice Architecture for Boundedly Rational Choosers}},
author = {Bucher, Stefan and Dayan, Peter},
booktitle = {NeurIPS 2023 Workshops: InfoCog},
year = {2023},
url = {https://mlanthology.org/neuripsw/2023/bucher2023neuripsw-cognitive/}
}