Algorithmic Collusion: Insights from Deep Learning

19 Pages Posted: 18 Feb 2021 Last revised: 24 Nov 2021

See all articles by Matthias Hettich

Matthias Hettich

Technische Universität Berlin (TU Berlin) - Faculty of Economics and Management

Date Written: November 24, 2021

Abstract

Increasingly, firms use algorithms powered by artificial intelligence to set prices. Previous research simulated interactions among Q-learning algorithms in an oligopoly model of price competition. The algorithms learn collusive strategies but require a long time that corresponds to several years to do so. We show that pricing algorithms using deep learning (DQN) can collude significantly faster. The availability of these more powerful pricing algorithms enables simulations in larger markets. Collusion disappears in wide oligopolies with up to 10 firms. However, incorporating knowledge of the learning behavior by reformulating the state representation increases the ability to collude effectively.

Keywords: Algorithmic Pricing, Collusion, Artificial Intelligence, Reinforcement Learning, DQN

JEL Classification: D21, D43, D83, L12, L13

Suggested Citation

Hettich, Matthias, Algorithmic Collusion: Insights from Deep Learning (November 24, 2021). Available at SSRN: https://ssrn.com/abstract=3785966 or http://dx.doi.org/10.2139/ssrn.3785966

Matthias Hettich (Contact Author)

Technische Universität Berlin (TU Berlin) - Faculty of Economics and Management ( email )

Berlin, 10585
Germany

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
565
Abstract Views
1,994
Rank
90,252
PlumX Metrics