English

Social Learning in Non-Stationary Environments

Optimization and Control 2022-02-24 v3 Machine Learning Other Statistics

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.

Keywords

Cite

@article{arxiv.2007.09996,
  title  = {Social Learning in Non-Stationary Environments},
  author = {Etienne Boursier and Vianney Perchet and Marco Scarsini},
  journal= {arXiv preprint arXiv:2007.09996},
  year   = {2022}
}
R2 v1 2026-06-23T17:14:29.733Z