Andrew Ellis - LSE
Equilibrium Effects of Machine Learning
Date: 11/21/2022 (Mon)
Time: 3:30pm- 4:45pm
Location: Seminar will be held on-site: Gardner 211 (UNC)
Organizer: Huseyin Yildirim, Ph.D.
Meeting Schedule: Login or email the organizer to schedule a meeting.
All meetings will be held in the same location as the seminar unless otherwise noted.
11:00am - Zichang Wang (GA204)
11:30am - Peter Norman (300C)
12:00pm - lunch: Peter Norman, Stan Rabinovich
1:30pm - Jaden Chen
2:00pm - Fei Li (300 B)
2:30pm - Huseyin Yildirim (204)
3:00pm - Curt Taylor (204)
3:30pm - Seminar Presentation (3:30pm to 4:45pm)
5:00pm - drink at Carolina Inn: everyone is welcome
6:30pm - dinner at Osteria Georgi: Fei, Mehdi, Jaden
Additional Comments: ABSTRACT: We introduce a tractable framework for studying the equilibrium effects of machine learning. Agents process information using a Chow-Liu (1968) tree, a widely-used machine learning procedure that admits a closed-form solution. We apply the model to an asset market with dispersed information based on Hellwig (1980). In equilibrium, ex-ante identical agents' beliefs are based on different trees. Agents react asymmetrically to high-dimensional public information. Equilibrium prices are bounded away from the informationally efficient ones.