On behalf of the organizers…
The Workshop on Algorithmic Game Theory and Data Science
(with the Conference on Economics and Computation)
June 15, 2015 in Portland, Oregon, USA.
Computer systems have become the primary mediator of social and economic interactions, enabling transactions at ever-increasing scale. Mechanism design when done on a large scale needs to be a data-driven enterprise. It seeks to optimize some objective with respect to a huge underlying population that the mechanism designer does not have direct access to. Instead, the mechanism designer typically will have access to sampled behavior from that population (e.g. bid histories, or purchase decisions). This means that, on the one hand, mechanism designers will need to bring to bear data-driven methodology from statistical learning theory, econometrics, and revealed preference theory. On the other hand, strategic settings pose new challenges in data science, and approaches for learning and inference need to be adapted to account for strategization.
The goal of this workshop is to frame the agenda for research at the interface of algorithms, game theory, and data science. Papers from a rich set of experimental, empirical, and theoretical perspectives are invited. Topics of interest include but are not limited to:
- Can good mechanisms be learned by observing agent behavior in response to other mechanisms? How hard is it to “learn” a revenue maximizing auction given a sampled bid history? How hard is it to learn a predictive model of customer purchase decisions, or better yet, a set of prices that will accurately maximize profit under these behavioral decisions?
- What is the sample complexity of mechanism design? How much data is necessary to enable good mechanism design?
- How does mechanism design affect inference? Are outcomes of some mechanisms more informative than those of others from the viewpoint of inference?
- How does inference affect mechanism design? If participants know that their data is to be used for inference, how does this knowledge affect their behavior in a mechanism?
- Can tools from computer science and game theory be used to contribute rigorous guarantees to interactive data analysis? Strategic interactions between a mechanism and a user base are often interactive (e.g. in the case of an ascending price auction, or repeated interaction with a customer and an online retailer), which is a setting in which traditional methods for preventing data over-fitting are weak.
- Is data an economic model? Can data be used to evaluate or replace existing economic models? What is the consequence for game theory and economics for replacing the model with data.
Submissions are due April 27, 2015. See the workshop website for further details and submission instructions.