Learning the Distribution Map in Reverse Causal Performative Prediction

Daniele Bracale, Subha Maity, Yuekai Sun, Moulinath Banerjee
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258:973-981, 2025.

Abstract

In numerous predictive scenarios, the predictive model affects the sampling distribution; for example, job applicants often meticulously craft their resumes to navigate through a screening system. Such shifts in distribution are particularly prevalent in social computing, yet, the strategies to learn these shifts from data remain remarkably limited. Inspired by a microeconomic model that adeptly characterizes agents’ behavior within labor markets, we introduce a novel approach to learning the distribution shift. Our method is predicated on a \emph{reverse causal model}, wherein the predictive model instigates a distribution shift exclusively through a finite set of agents’ actions. Within this framework, we employ a microfoundation model for the agents’ actions and develop a statistically justified methodology to learn the distribution shift map, which we demonstrate to effectively minimize the performative prediction risk.

Cite this Paper

BibTeX
@InProceedings{pmlr-v258-bracale25b, title = {Learning the Distribution Map in Reverse Causal Performative Prediction}, author = {Bracale, Daniele and Maity, Subha and Sun, Yuekai and Banerjee, Moulinath}, booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics}, pages = {973--981}, year = {2025}, editor = {Li, Yingzhen and Mandt, Stephan and Agrawal, Shipra and Khan, Emtiyaz}, volume = {258}, series = {Proceedings of Machine Learning Research}, month = {03--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v258/main/assets/bracale25b/bracale25b.pdf}, url = {https://proceedings.mlr.press/v258/bracale25b.html}, abstract = {In numerous predictive scenarios, the predictive model affects the sampling distribution; for example, job applicants often meticulously craft their resumes to navigate through a screening system. Such shifts in distribution are particularly prevalent in social computing, yet, the strategies to learn these shifts from data remain remarkably limited. Inspired by a microeconomic model that adeptly characterizes agents’ behavior within labor markets, we introduce a novel approach to learning the distribution shift. Our method is predicated on a \emph{reverse causal model}, wherein the predictive model instigates a distribution shift exclusively through a finite set of agents’ actions. Within this framework, we employ a microfoundation model for the agents’ actions and develop a statistically justified methodology to learn the distribution shift map, which we demonstrate to effectively minimize the performative prediction risk.} }
Endnote
%0 Conference Paper %T Learning the Distribution Map in Reverse Causal Performative Prediction %A Daniele Bracale %A Subha Maity %A Yuekai Sun %A Moulinath Banerjee %B Proceedings of The 28th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2025 %E Yingzhen Li %E Stephan Mandt %E Shipra Agrawal %E Emtiyaz Khan %F pmlr-v258-bracale25b %I PMLR %P 973--981 %U https://proceedings.mlr.press/v258/bracale25b.html %V 258 %X In numerous predictive scenarios, the predictive model affects the sampling distribution; for example, job applicants often meticulously craft their resumes to navigate through a screening system. Such shifts in distribution are particularly prevalent in social computing, yet, the strategies to learn these shifts from data remain remarkably limited. Inspired by a microeconomic model that adeptly characterizes agents’ behavior within labor markets, we introduce a novel approach to learning the distribution shift. Our method is predicated on a \emph{reverse causal model}, wherein the predictive model instigates a distribution shift exclusively through a finite set of agents’ actions. Within this framework, we employ a microfoundation model for the agents’ actions and develop a statistically justified methodology to learn the distribution shift map, which we demonstrate to effectively minimize the performative prediction risk.
APA
Bracale, D., Maity, S., Sun, Y. & Banerjee, M.. (2025). Learning the Distribution Map in Reverse Causal Performative Prediction. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 258:973-981 Available from https://proceedings.mlr.press/v258/bracale25b.html.

Related Material