Revisiting the Predictability of Performative, Social Events

Juan Carlos Perdomo
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48948-48961, 2025.

Abstract

Social predictions do not passively describe the future; they actively shape it. They inform actions and change individual expectations in ways that influence the likelihood of the predicted outcome. Given these dynamics, to what extent can social events be predicted? This question was discussed throughout the 20th century by authors like Merton, Morgenstern, Simon, and others who considered it a central issue in social science methodology. In this work, we provide a modern answer to this old problem. Using recent ideas from performative prediction and outcome indistinguishability, we establish that one can always efficiently predict social events accurately, regardless of how predictions influence data. While achievable, we also show that these predictions are often undesirable, highlighting the limitations of previous desiderata. We end with a discussion of various avenues forward.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-perdomo25a, title = {Revisiting the Predictability of Performative, Social Events}, author = {Perdomo, Juan Carlos}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {48948--48961}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/perdomo25a/perdomo25a.pdf}, url = {https://proceedings.mlr.press/v267/perdomo25a.html}, abstract = {Social predictions do not passively describe the future; they actively shape it. They inform actions and change individual expectations in ways that influence the likelihood of the predicted outcome. Given these dynamics, to what extent can social events be predicted? This question was discussed throughout the 20th century by authors like Merton, Morgenstern, Simon, and others who considered it a central issue in social science methodology. In this work, we provide a modern answer to this old problem. Using recent ideas from performative prediction and outcome indistinguishability, we establish that one can always efficiently predict social events accurately, regardless of how predictions influence data. While achievable, we also show that these predictions are often undesirable, highlighting the limitations of previous desiderata. We end with a discussion of various avenues forward.} }
Endnote
%0 Conference Paper %T Revisiting the Predictability of Performative, Social Events %A Juan Carlos Perdomo %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-perdomo25a %I PMLR %P 48948--48961 %U https://proceedings.mlr.press/v267/perdomo25a.html %V 267 %X Social predictions do not passively describe the future; they actively shape it. They inform actions and change individual expectations in ways that influence the likelihood of the predicted outcome. Given these dynamics, to what extent can social events be predicted? This question was discussed throughout the 20th century by authors like Merton, Morgenstern, Simon, and others who considered it a central issue in social science methodology. In this work, we provide a modern answer to this old problem. Using recent ideas from performative prediction and outcome indistinguishability, we establish that one can always efficiently predict social events accurately, regardless of how predictions influence data. While achievable, we also show that these predictions are often undesirable, highlighting the limitations of previous desiderata. We end with a discussion of various avenues forward.
APA
Perdomo, J.C.. (2025). Revisiting the Predictability of Performative, Social Events. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:48948-48961 Available from https://proceedings.mlr.press/v267/perdomo25a.html.

Related Material