# Concept Drift Detection and Adaptation with Hierarchical Hypothesis Testing

arXiv: https://arxiv.org/abs/1707.07821 · HTML: https://mlsanity.com/paper/1707.07821/

## Key facts

- Cited by 6 papers in the map (data through 13 Oct 2026).
- First posted on arXiv 25 Jul 2017.

## Built on by (most cited first, 6 of 6)

- [From Concept Drift to Model Degradation: An Overview on Performance-Aware Drift Detectors](https://mlsanity.com/paper/2203.11070/) (2022)
- [Statistically Valid Post-Deployment Monitoring Should Be Standard for AI-Based Digital Health](https://mlsanity.com/paper/2506.05701/) (2025)
- [A unified framework for dataset shift diagnostics](https://mlsanity.com/paper/2205.08340/) (2022)
- [Towards an MLOps Architecture for XAI in Industrial Applications](https://mlsanity.com/paper/2309.12756/) (2023)
- [MLE-UVAD: Minimal Latent Entropy Autoencoder for Fully Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2603.23868/) (2026)
- [Control and Monitoring of Artificial Intelligence Algorithms](https://mlsanity.com/paper/2307.13705/) (2023)

## Abstract (arXiv)

A fundamental issue for statistical classification models in a streaming environment is that the joint distribution between predictor and response variables changes over time (a phenomenon also known as concept drifts), such that their classification performance deteriorates dramatically. In this paper, we first present a hierarchical hypothesis testing (HHT) framework that can detect and also adapt to various concept drift types (e.g., recurrent or irregular, gradual or abrupt), even in the presence of imbalanced data labels. A novel concept drift detector, namely Hierarchical Linear Four Rates (HLFR), is implemented under the HHT framework thereafter. By substituting a widely-acknowledged retraining scheme with an adaptive training strategy, we further demonstrate that the concept drift adaptation capability of HLFR can be significantly boosted. The theoretical analysis on the Type-I and Type-II errors of HLFR is also performed. Experiments on both simulated and real-world datasets illustrate that our methods outperform state-of-the-art methods in terms of detection precision, detection delay as well as the adaptability across different concept drift types.