Towards an Efficient Market for Information
Events

Towards an Efficient Market for Information

JANUARY 26, 2023

Featured image 1

Haifeng Xu
Chicago University

DEIB - Seminar Room "N. Schiavoni" (Bldg. 20)
January 26th, 2023
2.00 pm

Contacts:
Alberto Marchesi

Research Line:
Artificial intelligence and robotics

Abstract

On January 26th, 2023 at 2.00 pm Haifeng Xu, Professor at University of Chicago, will give a seminar on "Towards an Efficient Market for Information" in DEIB Seminar Room.

One of the most fruitful products of today's digital world is perhaps the unprecedented amount of information generated each day. Such information -- often distilled from massive data via machine learning techniques -- can be used to help advertisers to more accurately target customers, loan companies to better determine borrowers' credit, investors to choose more profitable portfolios, just to list a few. Unsurprisingly, many companies have seen the great value of information and run on a business of collecting and selling information.
Despite the rich literature of mechanism design for selling goods, the problem of selling information turns out to be fundamentally different and far from being well-understood even in very basic setups. For example, information can be sold at any coarser level by adding random noise, but once sold, it can be copied freely. In this talk, I will focus on perhaps the most basic setup where one seller sells information to a single Bayesian decision maker. I will talk about the major challenges of mechanism design for selling information and present our recent progress on designing optimal and practical mechanisms for selling.

Short Bio

Haifeng Xu is an assistant professor in the Department of Computer Science at the University of Chicago. His research aims at developing an economic foundation for data and machine learning, including designing learning algorithms for multi-agent decision making and designing markets for data and ML algorithms. His research has been recognized by multiple awards, including a Google Faculty Research Award, ACM SIGecom Dissertation Award (honorable mention), IFAAMAS Distinguished Dissertation Award (runner-up), and multiple best paper awards.