Automated Mechanisation Design with Self Interested Designer

Student: Kurchishvili Josef

Supervisor: Emiliano Catonini

Faculty: International College of Economics and Finance

Educational Programme: Double degree programme in Economics of the NRU HSE and the University of London (Bachelor)

Final Grade: 8

Year of Graduation: 2020

This paper attempts to answer the question of how to optimally allocate N items to M agents. The single-item case was resolved in a seminal piece of work by Myerson in 1981, however, the multi-item case is unresolved to this day. We use deep learning methodology to design near revenue-optimal, near incentive compatible mechanisms using real world data from Real-Time-Bidding Auctions. We model the mechanism as a multi-layer neural network, estimate it on real data and show that it behaves well on analytically known settings and new settings alike.

Full text (added June 11, 2020)

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses