Machine-learning algorithms are now making decisions about what you see online, how much you pay for products, and whether you get a loan — but economists lack good models for predicting how these algorithms will behave when they interact with people or with each other. Standard game theory assumes that human decision-makers pursue clear goals and understand their environment correctly. That assumption breaks down when algorithms are involved, because algorithms are not rational in the human sense. This project tackles that gap by building new theoretical models based on a key observation: machine-learning algorithms are "simplicity seeking." They avoid overly complex explanations because complexity leads to poor predictions on new data. The researcher will develop new concepts of equilibrium — stable outcomes in strategic interactions — that incorporate this simplicity-seeking behaviour. These will be applied to credit markets, online content provision, and oligopoly pricing, among other settings. This is fundamental theoretical work. It will not produce a practical tool or policy recommendation directly. But if successful, it could reshape how regulators think about market competition when algorithms set prices, how platforms decide what content to show, and how lenders assess risk — systems that quietly govern large parts of modern life.
View original technical description
One of the salient recent technological developments has been the growing role of automated decision-making, based on machine learning (ML) algorithms. Examples include online content provision, product pricing, credit scoring and autonomous driving. When modeling strategic interactions between human agents, economists conventionally use game theory, which assumes that agents pursue well-defined objectives with a correct understanding of causal and statistical regularities in their environment. When some agents are ML algorithms, we need to find new, analytically tractable ways to model how they interact with humans or among themselves. My aim in this project is to develop such theoretical methodologies and examine their implications in economic settings such as oligopolistic competition, credit markets or online content provision, including potential implications for market regulation. The cornerstone of my theoretical approach is the observation that ML algorithms are "simplicity seeking". They attempt to predict outcomes from a sample that contains data about observable characteristics, and they overcome the overfitting problem (namely, complex estimated models' tendency toward poor out-of-sample predictions) by penalizing complex models. Simplicity is also an aspect of "explainability" of ML algorithms - an important criterion for enhancing users' willingness to interact with such algorithms. I plan to formulate notions of equilibrium behavior in strategic and market interactions that incorporate simplicity seeking as a criterion in the formation of equilibrium beliefs. One notion will focus on the sample-based selection of predictive models, while another will focus on explainability as a criterion for selecting models that is traded off against their predictive accuracy. I will apply these new equilibrium concepts to economic settings such as credit markets with adverse selection, dynamic trust games and oligopoly pricing, congestion games and online content provision.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know