Microfoundation inference for strategic prediction

Daniele Bracale, Subha Maity, Felipe Maia Polo, Seamus Somerstep, Moulinath Banerjee, Yuekai Sun
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258:919-927, 2025.

Abstract

Often in prediction tasks, the predictive model itself can influence the distribution of the target variable, a phenomenon termed \emph{performative prediction}. Generally, this influence stems from strategic actions taken by stakeholders with a vested interest in predictive models. A key challenge that hinders the widespread adaptation of performative prediction in machine learning is that practitioners are generally unaware of the social impacts of their predictions. To address this gap, we propose a methodology for learning the distribution map that encapsulates the long-term impacts of predictive models on the population. Specifically, we model agents’ responses as a cost-adjusted utility maximization problem and propose estimates for said cost. Our approach leverages optimal transport to align pre-model exposure (\emph{ex ante}) and post-model exposure (\emph{ex post}) distributions. We provide a rate of convergence for this proposed estimate and assess its quality through empirical demonstrations on a credit scoring dataset.

Cite this Paper

BibTeX
@InProceedings{pmlr-v258-bracale25a, title = {Microfoundation inference for strategic prediction}, author = {Bracale, Daniele and Maity, Subha and Polo, Felipe Maia and Somerstep, Seamus and Banerjee, Moulinath and Sun, Yuekai}, booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics}, pages = {919--927}, 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/bracale25a/bracale25a.pdf}, url = {https://proceedings.mlr.press/v258/bracale25a.html}, abstract = {Often in prediction tasks, the predictive model itself can influence the distribution of the target variable, a phenomenon termed \emph{performative prediction}. Generally, this influence stems from strategic actions taken by stakeholders with a vested interest in predictive models. A key challenge that hinders the widespread adaptation of performative prediction in machine learning is that practitioners are generally unaware of the social impacts of their predictions. To address this gap, we propose a methodology for learning the distribution map that encapsulates the long-term impacts of predictive models on the population. Specifically, we model agents’ responses as a cost-adjusted utility maximization problem and propose estimates for said cost. Our approach leverages optimal transport to align pre-model exposure (\emph{ex ante}) and post-model exposure (\emph{ex post}) distributions. We provide a rate of convergence for this proposed estimate and assess its quality through empirical demonstrations on a credit scoring dataset.} }
Endnote
%0 Conference Paper %T Microfoundation inference for strategic prediction %A Daniele Bracale %A Subha Maity %A Felipe Maia Polo %A Seamus Somerstep %A Moulinath Banerjee %A Yuekai Sun %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-bracale25a %I PMLR %P 919--927 %U https://proceedings.mlr.press/v258/bracale25a.html %V 258 %X Often in prediction tasks, the predictive model itself can influence the distribution of the target variable, a phenomenon termed \emph{performative prediction}. Generally, this influence stems from strategic actions taken by stakeholders with a vested interest in predictive models. A key challenge that hinders the widespread adaptation of performative prediction in machine learning is that practitioners are generally unaware of the social impacts of their predictions. To address this gap, we propose a methodology for learning the distribution map that encapsulates the long-term impacts of predictive models on the population. Specifically, we model agents’ responses as a cost-adjusted utility maximization problem and propose estimates for said cost. Our approach leverages optimal transport to align pre-model exposure (\emph{ex ante}) and post-model exposure (\emph{ex post}) distributions. We provide a rate of convergence for this proposed estimate and assess its quality through empirical demonstrations on a credit scoring dataset.
APA
Bracale, D., Maity, S., Polo, F.M., Somerstep, S., Banerjee, M. & Sun, Y.. (2025). Microfoundation inference for strategic prediction. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 258:919-927 Available from https://proceedings.mlr.press/v258/bracale25a.html.

Related Material