mlsanityData to 7 Oct 2026

Revisiting the Predictability of Performative, Social Events

arXiv 2503.11713 ↗First posted 12 Mar 2025cs.CY cs.LG econ.THcited by 11

Not on the map. Why?

Abstract (arXiv)

Social predictions do not passively describe the future; they actively shape it. They inform actions and change individual expectations in ways that influence the likelihood of the predicted outcome. Given these dynamics, to what extent can social events be predicted? This question was discussed throughout the 20th century by authors like Merton, Morgenstern, Simon, and others who considered it a central issue in social science methodology. In this work, we provide a modern answer to this old problem. Using recent ideas from performative prediction and outcome indistinguishability, we establish that one can always efficiently predict social events accurately, regardless of how predictions influence data. While achievable, we also show that these predictions are often undesirable, highlighting the limitations of previous desiderata. We end with a discussion of various avenues forward.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 19 of its 41 references that are in the map. First posted on arXiv 12 Mar 2025.

Builds on

19 of 41 references.

References · 19

  1. 2020Performative Predictioncited by 318
  2. 2021Outside the Echo Chamber: Optimizing the Performative Riskcited by 95
  3. 2020Stochastic Optimization for Performative Predictioncited by 92
  4. 2020Performative Prediction in a Stateful Worldcited by 90
  5. 2020Outcome Indistinguishabilitycited by 74
  6. 2020Stochastic optimization with decision-dependent distributionscited by 65
  7. 2022Loss Minimization through the Lens of Outcome Indistinguishabilitycited by 61
  8. 2022Data Feedback Loops: Model-driven Amplification of Dataset Biasescited by 59
  9. 2023Performative Prediction: Past and Futurecited by 52
  10. 2021Online Multivalid Learning: Means, Moments, and Prediction Intervalscited by 48
  11. 2023Difficult Lessons on Social Prediction from Wisconsin Public Schoolscited by 35
  12. 2023Performative Prediction with Neural Networkscited by 33
7 more
  1. 2025Near-Optimal Algorithms for Omnipredictioncited by 33
  2. 2022Making Decisions under Outcome Performativitycited by 32
  3. 2024Omnipredictors for Regression and the Approximate Rank of Convex Functionscited by 14
  4. 2025Sample Efficient Omniprediction and Downstream Swap Regret for Non-Linear Lossescited by 14
  5. 2024From Fairness to Infinity: Outcome-Indistinguishable (Omni)Prediction in Evolving Graphscited by 13
  6. 2023Incentivizing honest performative predictions with proper scoring rulescited by 9
  7. 2024Tight Lower Bounds and Improved Convergence in Performative Predictioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 8.

11 papers.

  1. 2025Generalization Bounds and Stopping Rules for Learning with Self-Selected Datacited by 5
  2. 2025In Defense of Defensive Forecastingcited by 5
  3. 2025Statistical Inference under Performativitycited by 4
  4. 2026The Stability of Online Algorithms in Performative Predictioncited by 4
  5. 2026Dissecting Performative Prediction: A Comprehensive Surveycited by 2
  6. 2026Partially Performative Predictioncited by 2
  7. 2026Unbiased Canonical Set-Valued Oracles Via Lattice Theorycited by 1
  8. 2026Retraining Seeks Stable Signalscited by 1
  9. 2026Performative Learning Theorycited by 0
  10. 2026Off-Policy Evaluation with Strategic Agents via Local Disclosurecited by 0
  11. 2026Stabilizing Performative Feedback Loops with Minimal Model Deploymentscited by 0