Optimal and Robust Price Experimentation: Learning by Lottery

Christopher Dance, Onno Zoeter
Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, PMLR 15:242-250, 2011.

Abstract

This paper studies optimal price learning for one or more items. We introduce the Schrödinger price experiment (SPE) which superimposes classical price experiments using lotteries, and thereby extracts more information from each customer interaction. If buyers are perfectly rational we show that there exist SPEs that in the limit of infinite superposition learn optimally and exploit optimally. We refer to the new resulting mechanism as the hopeful mechanism (HM) since although it is incentive compatible, buyers can deviate with extreme consequences for the seller at very little cost to themselves. For real-world settings we propose a robust version of the approach which takes the form of a Markov decision process where the actions are functions. We provide approximate policies motivated by the best of sampled set (BOSS) algorithm coupled with approximate Bayesian inference. Numerical studies show that the proposed method significantly increases seller revenue compared to classical price experimentation, even for the single-item case.

Cite this Paper


BibTeX
@InProceedings{pmlr-v15-dance11a, title = {Optimal and Robust Price Experimentation: Learning by Lottery}, author = {Dance, Christopher and Zoeter, Onno}, booktitle = {Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics}, pages = {242--250}, year = {2011}, editor = {Gordon, Geoffrey and Dunson, David and Dudík, Miroslav}, volume = {15}, series = {Proceedings of Machine Learning Research}, address = {Fort Lauderdale, FL, USA}, month = {11--13 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v15/dance11a/dance11a.pdf}, url = {https://proceedings.mlr.press/v15/dance11a.html}, abstract = {This paper studies optimal price learning for one or more items. We introduce the Schrödinger price experiment (SPE) which superimposes classical price experiments using lotteries, and thereby extracts more information from each customer interaction. If buyers are perfectly rational we show that there exist SPEs that in the limit of infinite superposition learn optimally and exploit optimally. We refer to the new resulting mechanism as the hopeful mechanism (HM) since although it is incentive compatible, buyers can deviate with extreme consequences for the seller at very little cost to themselves. For real-world settings we propose a robust version of the approach which takes the form of a Markov decision process where the actions are functions. We provide approximate policies motivated by the best of sampled set (BOSS) algorithm coupled with approximate Bayesian inference. Numerical studies show that the proposed method significantly increases seller revenue compared to classical price experimentation, even for the single-item case.} }
Endnote
%0 Conference Paper %T Optimal and Robust Price Experimentation: Learning by Lottery %A Christopher Dance %A Onno Zoeter %B Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2011 %E Geoffrey Gordon %E David Dunson %E Miroslav Dudík %F pmlr-v15-dance11a %I PMLR %P 242--250 %U https://proceedings.mlr.press/v15/dance11a.html %V 15 %X This paper studies optimal price learning for one or more items. We introduce the Schrödinger price experiment (SPE) which superimposes classical price experiments using lotteries, and thereby extracts more information from each customer interaction. If buyers are perfectly rational we show that there exist SPEs that in the limit of infinite superposition learn optimally and exploit optimally. We refer to the new resulting mechanism as the hopeful mechanism (HM) since although it is incentive compatible, buyers can deviate with extreme consequences for the seller at very little cost to themselves. For real-world settings we propose a robust version of the approach which takes the form of a Markov decision process where the actions are functions. We provide approximate policies motivated by the best of sampled set (BOSS) algorithm coupled with approximate Bayesian inference. Numerical studies show that the proposed method significantly increases seller revenue compared to classical price experimentation, even for the single-item case.
RIS
TY - CPAPER TI - Optimal and Robust Price Experimentation: Learning by Lottery AU - Christopher Dance AU - Onno Zoeter BT - Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics DA - 2011/06/14 ED - Geoffrey Gordon ED - David Dunson ED - Miroslav Dudík ID - pmlr-v15-dance11a PB - PMLR DP - Proceedings of Machine Learning Research VL - 15 SP - 242 EP - 250 L1 - http://proceedings.mlr.press/v15/dance11a/dance11a.pdf UR - https://proceedings.mlr.press/v15/dance11a.html AB - This paper studies optimal price learning for one or more items. We introduce the Schrödinger price experiment (SPE) which superimposes classical price experiments using lotteries, and thereby extracts more information from each customer interaction. If buyers are perfectly rational we show that there exist SPEs that in the limit of infinite superposition learn optimally and exploit optimally. We refer to the new resulting mechanism as the hopeful mechanism (HM) since although it is incentive compatible, buyers can deviate with extreme consequences for the seller at very little cost to themselves. For real-world settings we propose a robust version of the approach which takes the form of a Markov decision process where the actions are functions. We provide approximate policies motivated by the best of sampled set (BOSS) algorithm coupled with approximate Bayesian inference. Numerical studies show that the proposed method significantly increases seller revenue compared to classical price experimentation, even for the single-item case. ER -
APA
Dance, C. & Zoeter, O.. (2011). Optimal and Robust Price Experimentation: Learning by Lottery. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 15:242-250 Available from https://proceedings.mlr.press/v15/dance11a.html.

Related Material