Evaluating Prediction-based Interventions with Human Decision Makers In Mind

Inioluwa Deborah Raji, Lydia T. Liu
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258:1180-1188, 2025.

Abstract

Automated decision systems (ADS) are broadly deployed to inform or support human decision- making across a wide range of consequential contexts. However, various context-specific details complicate the goal of establishing meaningful experimental evaluations for prediction-based interventions. Notably, specific experimental design decisions may induce cognitive biases in human decision makers, which could then significantly alter the observed effect sizes of the prediction intervention. In this paper, we formalize and investigate various models of human decision-making in the presence of a predictive model aid. We show that each of these behavioral models produces dependencies across decision subjects and results in the violation of existing assumptions, with consequences for treatment effect estimation. This work aims to further advance the scientific validity of intervention-based evaluation schemes for the assessment of ADS deployments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v258-raji25a, title = {Evaluating Prediction-based Interventions with Human Decision Makers In Mind}, author = {Raji, Inioluwa Deborah and Liu, Lydia T.}, booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics}, pages = {1180--1188}, 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/raji25a/raji25a.pdf}, url = {https://proceedings.mlr.press/v258/raji25a.html}, abstract = {Automated decision systems (ADS) are broadly deployed to inform or support human decision- making across a wide range of consequential contexts. However, various context-specific details complicate the goal of establishing meaningful experimental evaluations for prediction-based interventions. Notably, specific experimental design decisions may induce cognitive biases in human decision makers, which could then significantly alter the observed effect sizes of the prediction intervention. In this paper, we formalize and investigate various models of human decision-making in the presence of a predictive model aid. We show that each of these behavioral models produces dependencies across decision subjects and results in the violation of existing assumptions, with consequences for treatment effect estimation. This work aims to further advance the scientific validity of intervention-based evaluation schemes for the assessment of ADS deployments.} }
Endnote
%0 Conference Paper %T Evaluating Prediction-based Interventions with Human Decision Makers In Mind %A Inioluwa Deborah Raji %A Lydia T. Liu %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-raji25a %I PMLR %P 1180--1188 %U https://proceedings.mlr.press/v258/raji25a.html %V 258 %X Automated decision systems (ADS) are broadly deployed to inform or support human decision- making across a wide range of consequential contexts. However, various context-specific details complicate the goal of establishing meaningful experimental evaluations for prediction-based interventions. Notably, specific experimental design decisions may induce cognitive biases in human decision makers, which could then significantly alter the observed effect sizes of the prediction intervention. In this paper, we formalize and investigate various models of human decision-making in the presence of a predictive model aid. We show that each of these behavioral models produces dependencies across decision subjects and results in the violation of existing assumptions, with consequences for treatment effect estimation. This work aims to further advance the scientific validity of intervention-based evaluation schemes for the assessment of ADS deployments.
APA
Raji, I.D. & Liu, L.T.. (2025). Evaluating Prediction-based Interventions with Human Decision Makers In Mind. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 258:1180-1188 Available from https://proceedings.mlr.press/v258/raji25a.html.

Related Material