Principal Investigator: Prof. Dr. Sven Seuken
Market designers study how to set the "rules of a marketplace" such that the market works well. However, markets are getting increasingly complex such that designing good market mechanisms "by hand" is often infeasible, in particular when certain design desiderata (such as efficiency, strategyproofness, or fairness) are in conflict with each other. Moreover, human agents are boundedly-rational: already in small domains, they are best modeled as having incomplete preferences, because they may only know a ranking or the values of their top choices. In combinatorial domains, the number of choices grows exponentially, such that it quickly becomes impossible for an agent to report its full valuation, even if it had complete preferences. In this ERC project, we aim to combine techniques from "machine learning" with "market design" to address these challenges.
|First, we will develop a new, automated approach to design mechanisms with the help of machine learning (ML). In contrast to prior ML-based automated mechanism design work, we will work towards the design of ML algorithms that exploit regularities in the mechanism design space. Second, we will study the "design of machine learning-based mechanisms." These are mechanisms that use machine learning internally to achieve good efficiency, revenue, fairness, or incentives even when agents have incomplete knowledge about their own preferences.||
In addition to pushing the scientific boundaries of market design research, this ERC project will also have an immediate impact on practical market design. We will apply our techniques in two different settings: (1) for the design of combinatorial spectrum auctions, a multi-billion dollar domain; and (2) for the design of school choice matching markets, which are used to match millions of students to high school every year.
- Principal Investigator:
- PhD Students:
- We are hiring!
- External Collaborators:
Open Positions: We are looking for 1 PostDoc with expertise in Machine Learning to join this project! Please apply here!
Related Publications and Working Papers
- Fast Iterative Combinatorial Auctions via Bayesian Learning. Gianluca Brero, Sébastien Lahaie, and Sven Seuken. Working Paper. September 2018. [pdf]
- Combinatorial Auctions via Machine Learning-based Preference Elicitation. Gianluca Brero, Benjamin Lubin, and Sven Seuken. In Proceedings of the 27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence (IJCAI-ECAI), Stockholm, Sweden, July 2018.[pdf]
- Probably Approximately Efficient Combinatorial Auctions via Machine Learning.
Gianluca Brero, Benjamin Lubin, and Sven Seuken. In Proceedings of the 31st Conference on Artificial Intelligence (AAAI), San Francisco, CA, February 2017.[pdf]