From the 1 of 4 linked papers with an AI index.
4 papers
Actions Have Consequences: Detecting Outcome Performativity using Intervention Testing
Brandon Gower-Winter, Georg Krempl
The paper proposes a method called Outcome Performativity A/B Detection (OPAB) to identify when predictions causally affect the outcomes they forecast, by comparing outcome distrib…
The Window Dilemma: Why Concept Drift Detection is Ill-Posed
Brandon Gower-Winter, Misja Groen, Georg Krempl
Non-stationarity of an underlying data generating process that leads to distributional changes over time is a key characteristic of Data Streams. This phenomenon, commonly referred…
Performative Drift Resistant Classification Using Generative Domain Adversarial Networks
Maciej Makowski, Brandon Gower-Winter, Georg Krempl
Performative Drift is a special type of Concept Drift that occurs when a model's predictions influence the future instances the model will encounter. In these settings, retraining…
Identifying Predictions That Influence the Future: Detecting Performative Concept Drift in Data Streams
Brandon Gower-Winter, Georg Krempl, Sergey Dragomiretskiy +2
Concept Drift has been extensively studied within the context of Stream Learning. However, it is often assumed that the deployed model's predictions play no role in the concept dri…