A Parametric Contextual Online Learning Theory of Brokerage

François Bachoc, Tommaso Cesari, Roberto Colomboni
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2293-2309, 2025.

Abstract

We study the role of contextual information in the online learning problem of brokerage between traders. In this sequential problem, at each time step, two traders arrive with secret valuations about an asset they wish to trade. The learner (a broker) suggests a trading (or brokerage) price based on contextual data about the asset and the market conditions. Then, the traders reveal their willingness to buy or sell based on whether their valuations are higher or lower than the brokerage price. A trade occurs if one of the two traders decides to buy and the other to sell, i.e., if the broker’s proposed price falls between the smallest and the largest of their two valuations. We design algorithms for this problem and prove optimal theoretical regret guarantees under various standard assumptions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-bachoc25a, title = {A Parametric Contextual Online Learning Theory of Brokerage}, author = {Bachoc, Fran\c{c}ois and Cesari, Tommaso and Colomboni, Roberto}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {2293--2309}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/bachoc25a/bachoc25a.pdf}, url = {https://proceedings.mlr.press/v267/bachoc25a.html}, abstract = {We study the role of contextual information in the online learning problem of brokerage between traders. In this sequential problem, at each time step, two traders arrive with secret valuations about an asset they wish to trade. The learner (a broker) suggests a trading (or brokerage) price based on contextual data about the asset and the market conditions. Then, the traders reveal their willingness to buy or sell based on whether their valuations are higher or lower than the brokerage price. A trade occurs if one of the two traders decides to buy and the other to sell, i.e., if the broker’s proposed price falls between the smallest and the largest of their two valuations. We design algorithms for this problem and prove optimal theoretical regret guarantees under various standard assumptions.} }
Endnote
%0 Conference Paper %T A Parametric Contextual Online Learning Theory of Brokerage %A François Bachoc %A Tommaso Cesari %A Roberto Colomboni %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-bachoc25a %I PMLR %P 2293--2309 %U https://proceedings.mlr.press/v267/bachoc25a.html %V 267 %X We study the role of contextual information in the online learning problem of brokerage between traders. In this sequential problem, at each time step, two traders arrive with secret valuations about an asset they wish to trade. The learner (a broker) suggests a trading (or brokerage) price based on contextual data about the asset and the market conditions. Then, the traders reveal their willingness to buy or sell based on whether their valuations are higher or lower than the brokerage price. A trade occurs if one of the two traders decides to buy and the other to sell, i.e., if the broker’s proposed price falls between the smallest and the largest of their two valuations. We design algorithms for this problem and prove optimal theoretical regret guarantees under various standard assumptions.
APA
Bachoc, F., Cesari, T. & Colomboni, R.. (2025). A Parametric Contextual Online Learning Theory of Brokerage. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:2293-2309 Available from https://proceedings.mlr.press/v267/bachoc25a.html.

Related Material