Machine-Learning to Trust

TL;DR

This paper investigates how machine-learning-based beliefs influence long-term trust in a game setting, showing that complexity penalties reduce trust compared to traditional equilibrium concepts.

Contribution

It introduces a novel equilibrium concept where agents' beliefs are shaped by machine-learning methods with complexity penalties, affecting trust dynamics.

Findings

Complexity penalties in machine-learning beliefs reduce trust.

Equilibrium beliefs minimize prediction error plus complexity cost.

Trust is significantly narrowed compared to Nash equilibrium.

Abstract

Can players sustain long-run trust when their equilibrium beliefs are shaped by machine-learning methods that penalize complexity? I study a game in which an infinite sequence of agents with one-period recall decides whether to place trust in their immediate successor. The cost of trusting is state-dependent. Each player's best response is based on a belief about others' behavior, which is a coarse fit of the true population strategy with respect to a partition of relevant contingencies. In equilibrium, this partition minimizes the sum of the mean squared prediction error and a complexity penalty proportional to its size. Relative to symmetric mixed-strategy Nash equilibrium, this solution concept significantly narrows the scope for trust.