Computational antitrust comes to us at a time when courts and agencies are underfunded and overwhelmed, all while having to apply indeterminate rules to massive amounts of information in fast-moving markets. In the same way that Amazon disrupted e-commerce through its inventory and sales algorithms and TikTok’s progressive recommendation system keeps users hooked, computational antitrust holds the promise to revolutionize antitrust law. Implemented well, computational antitrust can help courts curate and refine precedential antitrust cases, identify anticompetitive effects, and model innovation effects and counterfactuals in killer acquisition cases. The beauty of AI is that it can reach outcomes humans alone cannot define as “good” or “better” as the untrained neural network interrogates itself via the process of trial and error. The maximization process is dynamic, with the AI being capable of scouring options to optimize the best rewards under the given circumstances, 1 mirroring how courts operationalize antitrust policy–computing the expected reward from executing a policy in a given environment. At the same time, any system is only as good as its weakest link, and computational antitrust is no exception. The synergistic possibilities that humans and algorithms offer depend on their interplay. Humans may lean on ideology as a heuristic when they must interpret the rule of reason according to economic theory and evidence. For this reason, it becomes imperative to understand, mitigate, and, where appropriate, harness those biases.
Daryl Lim, Can Computational Antitrust Succeed?, 1 Stan. Computational Antitrust 38 (2021)