<ul><li>Performative prediction is a phenomenon where the predictive model itself can influence the distribution of the target variable.</li><li>The social impacts of predictions in machine learning are often unknown to practitioners, hindering widespread adaptation.</li><li>A new methodology is proposed to learn the distribution map that captures the long-term impacts of predictive models on the population.</li><li>The approach leverages optimal transport to align pre-model and post-model exposure distributions.</li></ul>

Microfoundation Inference for Strategic Prediction

Discover more