Identifying Predictions That Influence the Future: Detecting Performative Concept Drift in Data Streams
This addresses a critical issue for stream learning systems in domains like automated trading or adversarial detection, where feedback loops can degrade model performance, though it is incremental in extending drift detection to performative scenarios.
The paper tackles the problem of performative concept drift in data streams, where a model's predictions influence future data, and proposes CB-PDD, a novel detection method that shows high efficacy with low false detection rates and resilience to intrinsic drift in synthetic and semi-synthetic datasets.
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.