From Individual Experience to Collective Evidence: A Reporting-Based Framework for Identifying Systemic Harms

Jessica Dai, Paula Gradu, Inioluwa Deborah Raji, Benjamin Recht
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12063-12083, 2025.

Abstract

When an individual reports a negative interaction with some system, how can their personal experience be contextualized within broader patterns of system behavior? We study the reporting database problem, where individual reports of adverse events arrive sequentially, and are aggregated over time. In this work, our goal is to identify whether there are subgroups—defined by any combination of relevant features—that are disproportionately likely to experience harmful interactions with the system. We formalize this problem as a sequential hypothesis test, and identify conditions on reporting behavior that are sufficient for making inferences about disparities in true rates of harm across subgroups. We show that algorithms for sequential hypothesis tests can be applied to this problem with a standard multiple testing correction. We then demonstrate our method on real-world datasets, including mortgage decisions and vaccine side effects; on each, our method (re-)identifies subgroups known to experience disproportionate harm using only a fraction of the data that was initially used to discover them.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-dai25g, title = {From Individual Experience to Collective Evidence: A Reporting-Based Framework for Identifying Systemic Harms}, author = {Dai, Jessica and Gradu, Paula and Raji, Inioluwa Deborah and Recht, Benjamin}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {12063--12083}, 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/dai25g/dai25g.pdf}, url = {https://proceedings.mlr.press/v267/dai25g.html}, abstract = {When an individual reports a negative interaction with some system, how can their personal experience be contextualized within broader patterns of system behavior? We study the reporting database problem, where individual reports of adverse events arrive sequentially, and are aggregated over time. In this work, our goal is to identify whether there are subgroups—defined by any combination of relevant features—that are disproportionately likely to experience harmful interactions with the system. We formalize this problem as a sequential hypothesis test, and identify conditions on reporting behavior that are sufficient for making inferences about disparities in true rates of harm across subgroups. We show that algorithms for sequential hypothesis tests can be applied to this problem with a standard multiple testing correction. We then demonstrate our method on real-world datasets, including mortgage decisions and vaccine side effects; on each, our method (re-)identifies subgroups known to experience disproportionate harm using only a fraction of the data that was initially used to discover them.} }
Endnote
%0 Conference Paper %T From Individual Experience to Collective Evidence: A Reporting-Based Framework for Identifying Systemic Harms %A Jessica Dai %A Paula Gradu %A Inioluwa Deborah Raji %A Benjamin Recht %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-dai25g %I PMLR %P 12063--12083 %U https://proceedings.mlr.press/v267/dai25g.html %V 267 %X When an individual reports a negative interaction with some system, how can their personal experience be contextualized within broader patterns of system behavior? We study the reporting database problem, where individual reports of adverse events arrive sequentially, and are aggregated over time. In this work, our goal is to identify whether there are subgroups—defined by any combination of relevant features—that are disproportionately likely to experience harmful interactions with the system. We formalize this problem as a sequential hypothesis test, and identify conditions on reporting behavior that are sufficient for making inferences about disparities in true rates of harm across subgroups. We show that algorithms for sequential hypothesis tests can be applied to this problem with a standard multiple testing correction. We then demonstrate our method on real-world datasets, including mortgage decisions and vaccine side effects; on each, our method (re-)identifies subgroups known to experience disproportionate harm using only a fraction of the data that was initially used to discover them.
APA
Dai, J., Gradu, P., Raji, I.D. & Recht, B.. (2025). From Individual Experience to Collective Evidence: A Reporting-Based Framework for Identifying Systemic Harms. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:12063-12083 Available from https://proceedings.mlr.press/v267/dai25g.html.

Related Material