Performative Prediction: Past and Future
Statistical Science · 01.08.2025 · 40 (3) · 417-436
DOI: 10.1214/25-sts986 ↗Kurz gefasst
Fachartikel in der Zeitschrift Statistical Science, erschienen am 01.08.2025. Verfasst von Moritz Hardt und 1 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 106 Literaturangaben.
Abstract (Originalsprache)
Predictions in the social world generally influence the target of prediction, a phenomenon known as performativity. Self-fulfilling and self-negating predictions are examples of performativity. Of fundamental importance to economics, finance and the social sciences, the notion has been absent from the development of machine learning. In machine learning applications, performativity often surfaces as distribution shift. A predictive model deployed on a digital platform, for example, influences consumer behavior, thus changing the data-generating distribution. We survey the recently founded area of performative prediction that provides a definition and conceptual framework to study performativity in machine learning. A consequence of performative prediction is a natural equilibrium notion that gives rise to new optimization challenges. Another consequence is a distinction between learning and steering, two mechanisms at play in performative prediction. The notion of steering is in turn intimately related to questions of power in digital markets. We review the notion of performative power that gives an answer to the question how much a platform can steer participants through its predictions. We end on a discussion of future directions, such as the role that performativity plays in contesting algorithmic systems.
Zitieren
APA
Hardt, M., & Mendler-Dünner, C. (2025). Performative Prediction: Past and Future. Statistical Science, 40(3), 417-436. https://doi.org/10.1214/25-sts986
Vancouver
Hardt M, Mendler-Dünner C. Performative Prediction: Past and Future. Statistical Science. 2025;40(3):417-436. doi:10.1214/25-sts986
BibTeX
@article{Hardt2025,
author = {Hardt, Moritz and Mendler-Dünner, Celestine},
title = {Performative Prediction: Past and Future},
journal = {Statistical Science},
year = {2025},
volume = {40},
number = {3},
pages = {417--436},
doi = {10.1214/25-sts986}
}
EUVIMED