Learning to Clear the Market

Weiran Shen, Sebastien Lahaie, Renato Paes Leme
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:5710-5718, 2019.

Abstract

The problem of market clearing is to set a price for an item such that quantity demanded equals quantity supplied. In this work, we cast the problem of predicting clearing prices into a learning framework and use the resulting models to perform revenue optimization in auctions and markets with contextual information. The economic intuition behind market clearing allows us to obtain fine-grained control over the aggressiveness of the resulting pricing policy, grounded in theory. To evaluate our approach, we fit a model of clearing prices over a massive dataset of bids in display ad auctions from a major ad exchange. The learned prices outperform other modeling techniques in the literature in terms of revenue and efficiency trade-offs. Because of the convex nature of the clearing loss function, the convergence rate of our method is as fast as linear regression.

Cite this Paper


BibTeX
@InProceedings{pmlr-v97-shen19b, title = {Learning to Clear the Market}, author = {Shen, Weiran and Lahaie, Sebastien and Leme, Renato Paes}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {5710--5718}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/shen19b/shen19b.pdf}, url = {https://proceedings.mlr.press/v97/shen19b.html}, abstract = {The problem of market clearing is to set a price for an item such that quantity demanded equals quantity supplied. In this work, we cast the problem of predicting clearing prices into a learning framework and use the resulting models to perform revenue optimization in auctions and markets with contextual information. The economic intuition behind market clearing allows us to obtain fine-grained control over the aggressiveness of the resulting pricing policy, grounded in theory. To evaluate our approach, we fit a model of clearing prices over a massive dataset of bids in display ad auctions from a major ad exchange. The learned prices outperform other modeling techniques in the literature in terms of revenue and efficiency trade-offs. Because of the convex nature of the clearing loss function, the convergence rate of our method is as fast as linear regression.} }
Endnote
%0 Conference Paper %T Learning to Clear the Market %A Weiran Shen %A Sebastien Lahaie %A Renato Paes Leme %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-shen19b %I PMLR %P 5710--5718 %U https://proceedings.mlr.press/v97/shen19b.html %V 97 %X The problem of market clearing is to set a price for an item such that quantity demanded equals quantity supplied. In this work, we cast the problem of predicting clearing prices into a learning framework and use the resulting models to perform revenue optimization in auctions and markets with contextual information. The economic intuition behind market clearing allows us to obtain fine-grained control over the aggressiveness of the resulting pricing policy, grounded in theory. To evaluate our approach, we fit a model of clearing prices over a massive dataset of bids in display ad auctions from a major ad exchange. The learned prices outperform other modeling techniques in the literature in terms of revenue and efficiency trade-offs. Because of the convex nature of the clearing loss function, the convergence rate of our method is as fast as linear regression.
APA
Shen, W., Lahaie, S. & Leme, R.P.. (2019). Learning to Clear the Market. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:5710-5718 Available from https://proceedings.mlr.press/v97/shen19b.html.

Related Material