Algorithmic collusion in a two-sided market: A rideshare example

TL;DR

This paper investigates how a sophisticated reinforcement learning algorithm, PPO, can lead to collusive or competitive outcomes in a complex rideshare market model, highlighting the emergent collusion without explicit communication.

Contribution

It extends a rideshare market model to a temporal multi origin-destination setting and analyzes PPO's ability to induce collusion in a complex double-sided market.

Findings

PPO can converge to either collusive or competitive equilibria.

Market characteristics influence the equilibrium outcome.

Hyper-parameters alone do not determine the outcome.

Abstract

With dynamic pricing on the rise, firms are using sophisticated algorithms for price determination. These algorithms are often non-interpretable and there has been a recent interest in their seemingly emergent ability to tacitly collude with each other without any prior communication whatsoever. Most of the previous works investigate algorithmic collusion on simple reinforcement learning (RL) based algorithms operating on a basic market model. Instead, we explore the collusive tendencies of Proximal Policy Optimization (PPO), a state-of-the-art continuous state/action space RL algorithm, on a complex double-sided hierarchical market model of rideshare. For this purpose, we extend a mathematical program network (MPN) based rideshare model to a temporal multi origin-destination setting and use PPO to solve for a repeated duopoly game. Our results indicate that PPO can either converge to a competitive or a collusive equilibrium depending upon the underlying market characteristics, even when the hyper-parameters are held constant.