English

Meta Dynamic Pricing: Transfer Learning Across Experiments

Machine Learning 2021-01-07 v4 Machine Learning

Abstract

We study the problem of learning shared structure \emph{across} a sequence of dynamic pricing experiments for related products. We consider a practical formulation where the unknown demand parameters for each product come from an unknown distribution (prior) that is shared across products. We then propose a meta dynamic pricing algorithm that learns this prior online while solving a sequence of Thompson sampling pricing experiments (each with horizon TT) for NN different products. Our algorithm addresses two challenges: (i) balancing the need to learn the prior (\emph{meta-exploration}) with the need to leverage the estimated prior to achieve good performance (\emph{meta-exploitation}), and (ii) accounting for uncertainty in the estimated prior by appropriately "widening" the estimated prior as a function of its estimation error. We introduce a novel prior alignment technique to analyze the regret of Thompson sampling with a mis-specified prior, which may be of independent interest. Unlike prior-independent approaches, our algorithm's meta regret grows sublinearly in NN, demonstrating that the price of an unknown prior in Thompson sampling can be negligible in experiment-rich environments (large NN). Numerical experiments on synthetic and real auto loan data demonstrate that our algorithm significantly speeds up learning compared to prior-independent algorithms.

Keywords

Cite

@article{arxiv.1902.10918,
  title  = {Meta Dynamic Pricing: Transfer Learning Across Experiments},
  author = {Hamsa Bastani and David Simchi-Levi and Ruihao Zhu},
  journal= {arXiv preprint arXiv:1902.10918},
  year   = {2021}
}
R2 v1 2026-06-23T07:53:50.391Z