Identifying Predictions That Influence the Future: Detecting Performative Concept Drift in Data Streams
Brandon Gower-Winter, Georg Krempl, Sergey Dragomiretskiy, Tineke Jelsma, Arno Siebes
Abstract
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 drift the system experiences. Closer inspection reveals that this is not always the case. Automated trading might be prone to self-fulfilling feedback loops. Likewise, malicious entities might adapt to evade detectors in the adversarial setting resulting in a self-negating feedback loop that requires the deployed models to constantly retrain. Such settings where a model may induce concept drift are called performative. In this work, we investigate this phenomenon.
Our contributions are as follows: First, we define performative drift within a stream learning setting and distinguish it from other causes of drift. We introduce a novel type of drift detection task, aimed at identifying potential performative concept drift in data streams. We propose a first such performative drift detection approach, called CheckerBoard Performative Drift Detection (CB-PDD). We apply CB-PDD to both synthetic and semi-synthetic datasets that exhibit varying degrees of self-fulfilling feedback loops. Results are positive with CB-PDD showing high efficacy, low false detection rates, resilience to intrinsic drift, comparability to other drift detection techniques, and an ability to effectively detect performative drift in semi-synthetic datasets. Secondly, we highlight the role intrinsic (traditional) drift plays in obfuscating performative drift and discuss the implications of these findings as well as the limitations of CB-PDD.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers2
- TRACE: A Generalizable Drift Detector for Streaming Data-Driven OptimizationYuan-Ting Zhong, Ting Huang, Xiaolin Xiao, Yue-Jiao GongAAAI 2026 · 1 citation
- RC-FCL: Combating Asynchronous Concept Drift in Federated Continual Learning via Retrospective CalibrationHang Su, Yijun Mo, Zhiyu Zhang, Yankai Jiang et al.ICML 2026
Builds on3
- Performative PredictionJuan C. Perdomo, Tijana Zrnic, Celestine Mendler-Dünner, Moritz HardtICML 2020 · 422 citations
- Data Feedback Loops: Model-driven Amplification of Dataset BiasesRohan Taori, Tatsunori HashimotoICML 2023 · 67 citations
- Learning Adversarial Markov Decision Processes with Delayed FeedbackTal Lancewicki, Aviv Rosenberg, Yishay MansourAAAI 2022 · 40 citations
Related papers
- DriftSurf: Stable-State / Reactive-State Learning under Concept DriftAshraf Tahmasbi, Ellango Jothimurugesan, Srikanta Tirthapura, Phillip B. GibbonsICML 2021 · 44 citations
- Online Drift Detection with Maximum Concept DiscrepancyKe Wan, Yi Liang, Susik YoonKDD 2024 · 4 citations
- DDG-DA: Data Distribution Generation for Predictable Concept Drift AdaptationWendi Li, Xiao Yang, Weiqing Liu, Yingce Xia et al.AAAI 2022 · 79 citations
- Performative Time-Series ForecastingZhiyuan Zhao, Haoxin Liu, Alexander Rodríguez, B. Aditya PrakashKDD 2025
- METER: A Dynamic Concept Adaptation Framework for Online Anomaly DetectionJiaqi Zhu, Shaofeng Cai, Fang Deng, Beng Chin Ooi et al.VLDB 2024 · 18 citations
