Social Learning in Non-Stationary Environments

Etienne Boursier, Vianney Perchet, Marco Scarsini
Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:128-129, 2022.

Abstract

Potential buyers of a product or service, before making their decisions, tend to read reviews written by previous consumers. We consider Bayesian consumers with heterogeneous preferences, who sequentially decide whether to buy an item of unknown quality, based on previous buyers’ reviews. The quality is multi-dimensional and may occasionally vary over time; the reviews are also multi-dimensional. In the simple uni-dimensional and static setting, beliefs about the quality are known to converge to its true value. Our paper extends this result in several ways. First, a multi-dimensional quality is considered, second, rates of convergence are provided, third, a dynamical Markovian model with varying quality is studied. In this dynamical setting the cost of learning is shown to be small.

Cite this Paper

BibTeX
@InProceedings{pmlr-v167-boursier22a, title = {Social Learning in Non-Stationary Environments}, author = {Boursier, Etienne and Perchet, Vianney and Scarsini, Marco}, booktitle = {Proceedings of The 33rd International Conference on Algorithmic Learning Theory}, pages = {128--129}, year = {2022}, editor = {Dasgupta, Sanjoy and Haghtalab, Nika}, volume = {167}, series = {Proceedings of Machine Learning Research}, month = {29 Mar--01 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v167/boursier22a/boursier22a.pdf}, url = {https://proceedings.mlr.press/v167/boursier22a.html}, abstract = {Potential buyers of a product or service, before making their decisions, tend to read reviews written by previous consumers. We consider Bayesian consumers with heterogeneous preferences, who sequentially decide whether to buy an item of unknown quality, based on previous buyers’ reviews. The quality is multi-dimensional and may occasionally vary over time; the reviews are also multi-dimensional. In the simple uni-dimensional and static setting, beliefs about the quality are known to converge to its true value. Our paper extends this result in several ways. First, a multi-dimensional quality is considered, second, rates of convergence are provided, third, a dynamical Markovian model with varying quality is studied. In this dynamical setting the cost of learning is shown to be small. } }
Endnote
%0 Conference Paper %T Social Learning in Non-Stationary Environments %A Etienne Boursier %A Vianney Perchet %A Marco Scarsini %B Proceedings of The 33rd International Conference on Algorithmic Learning Theory %C Proceedings of Machine Learning Research %D 2022 %E Sanjoy Dasgupta %E Nika Haghtalab %F pmlr-v167-boursier22a %I PMLR %P 128--129 %U https://proceedings.mlr.press/v167/boursier22a.html %V 167 %X Potential buyers of a product or service, before making their decisions, tend to read reviews written by previous consumers. We consider Bayesian consumers with heterogeneous preferences, who sequentially decide whether to buy an item of unknown quality, based on previous buyers’ reviews. The quality is multi-dimensional and may occasionally vary over time; the reviews are also multi-dimensional. In the simple uni-dimensional and static setting, beliefs about the quality are known to converge to its true value. Our paper extends this result in several ways. First, a multi-dimensional quality is considered, second, rates of convergence are provided, third, a dynamical Markovian model with varying quality is studied. In this dynamical setting the cost of learning is shown to be small.
APA
Boursier, E., Perchet, V. & Scarsini, M.. (2022). Social Learning in Non-Stationary Environments. Proceedings of The 33rd International Conference on Algorithmic Learning Theory, in Proceedings of Machine Learning Research 167:128-129 Available from https://proceedings.mlr.press/v167/boursier22a.html.

Related Material